Patent application number | Description | Published |
20080298718 | Image Stitching - Disclosed are embodiments of systems and methods to stitch two or more images together into a composite image. By finding matching point pairs for a pair of images, a homography transform may be obtained for the pair of images. The homography transform may be used to generate a composite image of the image pair. In an embodiment, the process of identifying a homography transform may be iterated. In an embodiment, when forming the composite image, the transformed foreground regions may be selected such that there is no intersection of foreground pixel regions. In an embodiment, foreground pixel regions on the border of an image may be removed. The resulting composite image is a larger image generated from the selected regions from the input images. In embodiments, the process may be repeated for sets of images with more than two images. | 12-04-2008 |
20090003700 | Precise Identification of Text Pixels from Scanned Document Images - A system or method for identifying text in a document. A group of connected components is created. A plurality of characteristics of different types is calculated for each connected component. Statistics are computed which describe the group of characteristics. Outlier components are identified as connected components whose computed characteristics are outside a statistical range. The outlier components are removed from the group of connected components. Text pixels are identified by segmenting pixels in the group of connected components into a group of text pixels and a group of background pixels. | 01-01-2009 |
20090046931 | Segmentation-based image labeling - Disclosed are embodiments of systems and methods for segmenting an image into at least two layers, a foreground and a background layer. An embodiment of the present invention includes rough labeling or segmenting at least a portion of the image into foreground and background pixels. The rough labeled pixels may be refined by using local classifications. In embodiments, additional processes may be performed on the image including, but not limited to, filtering, image enhancing, shape refining, image compression, etc. | 02-19-2009 |
20090060331 | Image Background Suppression - Disclosed are embodiments of systems and methods for suppressing the background of an image. In embodiments, the number of foreground pixels or background pixels within a neighborhood of an identified background pixel may be compared against an aggressiveness threshold. Responsive to the number of foreground pixels within a neighborhood of an identified background pixel not exceeding an aggressiveness threshold, the color of the identified background pixel may be changed to an average local background color. Alternatively, responsive to the number of background pixels within a neighborhood of an identified background pixel exceeding an aggressiveness threshold, the color of the identified background pixel may be changed to an average local background color. In embodiments, additional processes may be performed on the image including, but not limited to, color adjusting, filtering, image enhancing, compression, format conversion, watermarking, special effects, video editing, etc. | 03-05-2009 |
20090060354 | Reducing Compression Artifacts in Multi-Layer Images - Disclosed are embodiments of systems, devices, and methods to reduce compression artifacts in multi-layer images. Pixel dilation operations, such as morphological dilations, are performed to identify unlabeled pixels at boundaries between layers, and the colors of those pixels are adjusted to mitigate formation of artifacts during layer compression. | 03-05-2009 |
20090086081 | Color-Based Feature Identification - Disclosed are embodiments of systems and methods for identifying features using color information in an image. The image may be formed from one or more display images comprising color information and features or feature components. Because color information may be used to identify features, more than one feature or feature component may be displayed in a display image. Because a plurality of features may be identified in a calibration image, an image system, such as a projector-camera system, can reduce the number of display images needed to calibrate the system. | 04-02-2009 |
20090129625 | Extracting Data From Images - Disclosed are embodiments of systems and methods for embedding and/or extracting data from images. In embodiments, an image may be segmented into regions, and characters or other image groups within a segmented region may be determined to be embedding sites. A data vector may be embedded into a set of corresponding ordered embedding sites by representing each data element as different intensity values assigned to the pixels within one portion of an embedding site relative to the pixels in another portion of the embedding site. In embodiments, embedded data may be extracted from an image by extracting and decoding a set of bit values from a set of identified and ordered embedding sites. | 05-21-2009 |
20090129670 | Identifying Steganographic Data in an Image - Disclosed are embodiments of systems and methods for embedding and/or extracting data from images. In embodiments, an image may be segmented into regions, and characters or other image groups within a segmented region may be determined to be embedding sites. A data vector may be embedded into a set of corresponding ordered embedding sites by representing each data element as different intensity values assigned to the pixels within one portion of an embedding site relative to the pixels in another portion of the embedding site. In embodiments, embedded data may be extracted from an image by extracting and decoding a set of bit values from a set of identified and ordered embedding sites. | 05-21-2009 |
20090129676 | Segmenting a String Using Similarity Values - Disclosed are systems and methods for segmenting a string comprised of one or more string segments using similarity values. In embodiments, each string segment may contain at least a variation of a marker string that may be used to separate string segments in the string. In embodiments, a similarity value representing the result of comparing the marker string to substrings of the string may be computed, and a similarity vector representing the set of comparisons for the locations on the string may be generated. In embodiments, the similarity vector may be used to identify candidate segmentation locations in the string. In embodiments, a set of segmentation locations in the string may be derived from the candidate segmentation locations in the string, and the string may be segmented according to the set of segmentation locations. | 05-21-2009 |
20090136082 | Embedding Data in Images - Disclosed are embodiments of systems and methods for embedding and/or extracting data from images. In embodiments, an image may be segmented into regions, and characters or other image groups within a segmented region may be determined to be embedding sites. A data vector may be embedded into a set of corresponding ordered embedding sites by representing each data element as different intensity values assigned to the pixels within one portion of an embedding site relative to the pixels in another portion of the embedding site. In embodiments, embedded data may be extracted from an image by extracting and decoding a set of bit values from a set of identified and ordered embedding sites. | 05-28-2009 |
20090140892 | String Reconstruction Using Multiple Strings - Disclosed are systems and methods for reconstructing a string comprising characters given multiple strings that may contain one or more errors. In embodiments, pairwise comparisons of strings within a set of candidate strings that may contain errors is performed so that measures related to similarity between the strings in each pair may be calculated. In embodiments, an alignment and voting method using at least some of the similarity measures may be employed to generate a reconstructed string. In embodiments, the reconstructed string may be validated, and in embodiments, its characters may be converted to another encoding, if necessary. | 06-04-2009 |
20100013832 | Model-Based Object Image Processing - Aspects of the present invention include systems and methods for forming generative models, for utilizing those models, or both. In embodiments, an object model fitting system can be developed comprising a 3D active appearance model (AAM) model. The 3D AAM comprises an appearance model comprising a set of subcomponent appearance models that is constrained by a 3D shape model. In embodiments, the 3D AAM may be generated using a balanced set of training images. The object model fitting system may further comprise one or more manifold constraints, one or more weighting factors, or both. Applications of the present invention include, but are not limited to, modeling and/or fitting face images, although the teachings of the present invention can be applied to modeling/fitting other objects. | 01-21-2010 |
20100014768 | Model-Based Error Resilience in Data Communication - Disclosed are embodiments of systems and methods to use a model-based technique for image error recovery in data communication. A low-dimensional representation is constructed of an image that contains errors. A manifold comprising image representations and a statistical model of the manifold are used to correct the errors in the image. | 01-21-2010 |
20100019965 | Data Compression by Multi-Order Differencing - Embodiments of the present invention enable compression and decompression of data. Applications of the present invention are its use in embodiments of systems for compression and decompression of GPS long-term Ephemeris (LTE) data, although the present invention is not limited to such applications. In embodiments, the LTE data may be grouped into a set of data values associated with a parameter. In embodiments, a data set may be compressed by using a multi-order differencing scheme. In such a scheme, a set of the differences between values may be compressed because the differences have smaller magnitudes than the values. In embodiments, a multi-order differencing scheme determines how many levels (orders) of differencing may be applied to an original data set before it is compressed. In embodiments, the original data may be recovered from a compressed data set based on the type of multi-order differencing scheme used to generate the compressed data. | 01-28-2010 |
20100020167 | Image Capture, Alignment, and Registration - Embodiments of the present invention enable image capture, alignment, and registration. Certain applications of the present invention are its use in various embodiments of a system for inspection of a printed circuit board (“PCB”) substrate. In embodiments, an image capture system comprising a camera and a two-dimensional surface supporting an image may be calibrated based on configuration parameters of an image to be captured and of a simulated reference bitmap based on the image. In embodiments, the position of the image to be captured on the two-dimensional surface is determined based on calibration parameters. In embodiments, a sequence of images may be captured of sections of an image that cannot be captured in a single scan. A scan path across the image may be determined that is based in part on calibration parameters. In embodiments, consistency of quality of captured images is maintained by validating selected characteristics of each image as it is being captured and by validating the alignment of each captured image with a corresponding simulated reference bitmap. | 01-28-2010 |
20100106998 | Robust Generative Features - Disclosed are systems and methods for developing robust features for representing data. In embodiments, a linear generative model is computed using data. In embodiments, based upon a robustness measure, a set of features is selected. In embodiments, the set of features may be evaluated to gauge the capacity of the set of features to represent the data. Responsive to the set of features not satisfying an evaluation criterion or criteria, the set of features may be refined until the selected set of features complies with the evaluation criterion or criteria. | 04-29-2010 |
20100123784 | Catadioptric Projectors - Herein is presented a catadioptric projector by combining a commodity digital projector with additional optical units. By using specially shaped reflectors and/or refractors, a catadioptric projector can offer an unprecedented level of flexibility in aspect ratio, size, and field of view. Also presented, are methods to reduce projection artifacts in catadioptric projectors, such as distortions, scattering, and defocusing. By analysis of projection defocus of reflector and thin refractor based catadioptric projectors, it is shown that defocus blur can be interpreted as spatially-varying Gaussian blurs on an input image. Kernels are measured directly from a light transport matrix, T, and de-convolution is applied to optimize an input image. Practical uses of catadioptric projectors in panoramic and omni-directional projections are also demonstrated. | 05-20-2010 |
20100124371 | Content-Aware Image and Video Resizing by Anchor Point Sampling and Mapping - Aspects of the present invention include systems and methods for resizing a set of images, which may comprises one or more images, while preserving the important content. In embodiments, the saliency of pixels in the set of images is determined using one or more image features. A small number of pixels, called anchor points, are selected from the set of images by saliency-based sampling. The corresponding positions of these anchor points in the set of target images are obtained using pixel mapping. In embodiments, to prevent mis-ordering of pixel mapping, an iterative approach is used to constrain the mapped pixels to be within the boundaries of the target image/video. In embodiments, based on the mapping of neighboring anchor points, other pixels in the target are inpainted by back-projection and interpolation. The combination of sampling and mapping greatly reduces the computational cost yet leads to a global solution to content-aware image/video resizing. | 05-20-2010 |
20100150406 | Virtual Masking Using Rigid Parametric Modeling - Disclosed are systems and methods for masking at least a portion of one image with another image. Aspects of the present invention facilitate the placing of a virtual mask onto an item in an image even if that items moves in subsequent images, such as between different image frames in a video. | 06-17-2010 |
20100161568 | Data Compression by Multi-Order Differencing - Embodiments of the present invention enable compression and decompression of data. Applications of the present invention are its use in embodiments of systems for compression and decompression of GPS long-term Ephemeris (LTE) data, although the present invention is not limited to such applications. In embodiments, the LTE data may be grouped into a set of data values associated with a parameter. In embodiments, a data set may be compressed by using a multi-order differencing scheme. In such a scheme, a set of the differences between values may be compressed because the differences have smaller magnitudes than the values. In embodiments, a multi-order differencing scheme determines how many levels (orders) of differencing may be applied to an original data set before it is compressed. In embodiments, the original data may be recovered from a compressed data set based on the type of multi-order differencing scheme used to generate the compressed data. | 06-24-2010 |
20100214288 | Combining Subcomponent Models for Object Image Modeling - Aspects of the present invention include systems and methods for forming generative models, for utilizing those models, or both. In embodiments, an object model fitting system can be developed comprising a 3D active appearance model (AAM) model. The 3D AAM comprises an appearance model comprising a set of subcomponent appearance models that is constrained by a 3D shape model. In embodiments, the 3D AAM may be generated using a balanced set of training images. The object model fitting system may further comprise one or more manifold constraints, one or more weighting factors, or both. Applications of the present invention include, but are not limited to, modeling and/or fitting face images, although the teachings of the present invention can be applied to modeling/fitting other objects. | 08-26-2010 |
20100214289 | Subdivision Weighting for Robust Object Model Fitting - Aspects of the present invention include systems and methods for forming generative models, for utilizing those models, or both. In embodiments, an object model fitting system can be developed comprising a 3D active appearance model (AAM) model. The 3D AAM comprises an appearance model comprising a set of subcomponent appearance models that is constrained by a 3D shape model. In embodiments, the 3D AAM may be generated using a balanced set of training images. The object model fitting system may further comprise one or more manifold constraints, one or more weighting factors, or both. Applications of the present invention include, but are not limited to, modeling and/or fitting face images, although the teachings of the present invention can be applied to modeling/fitting other objects. | 08-26-2010 |
20100214290 | Object Model Fitting Using Manifold Constraints - Aspects of the present invention include systems and methods for forming generative models, for utilizing those models, or both. In embodiments, an object model fitting system can be developed comprising a 3D active appearance model (AAM) model. The 3D AAM comprises an appearance model comprising a set of subcomponent appearance models that is constrained by a 3D shape model. In embodiments, the 3D AAM may be generated using a balanced set of training images. The object model fitting system may further comprise one or more manifold constraints, one or more weighting factors, or both. Applications of the present invention include, but are not limited to, modeling and/or fitting face images, although the teachings of the present invention can be applied to modeling/fitting other objects. | 08-26-2010 |
20100215255 | Iterative Data Reweighting for Balanced Model Learning - Aspects of the present invention include systems and methods for forming generative models, for utilizing those models, or both. In embodiments, an object model fitting system can be developed comprising a 3D active appearance model (AAM) model. The 3D AAM comprises an appearance model comprising a set of subcomponent appearance models that is constrained by a 3D shape model. In embodiments, the 3D AAM may be generated using a balanced set of training images. The object model fitting system may further comprise one or more manifold constraints, one or more weighting factors, or both. Applications of the present invention include, but are not limited to, modeling and/or fitting face images, although the teachings of the present invention can be applied to modeling/fitting other objects. | 08-26-2010 |
20100245591 | Small Memory Footprint Light Transport Matrix Capture - A projection system uses a transformation matrix to transform a projection image p in such a manner so as to compensate for surface 5irregularities on a projection surface. The transformation matrix makes use of properties of light transport relating a projector to a camera. A display pipeline of user-supplied image modification processing modules are reduced by first representing the processing modules as multiple, individual matrix operations. All the matrix operations are then combined with, i.e., multiplied to, the transformation matrix to create a modified transformation matrix. The created transformation matrix is then used in place of the original transformation matrix to simultaneously achieve both image transformation and any pre and post image processing defined by the image modification processing modules. | 09-30-2010 |
20100245684 | Resolution Scalable View Projection - A projection system uses a transformation matrix to transform a projection image p in such a manner so as to compensate for surface irregularities on a projection surface. The transformation matrix makes use of properties of light transport relating a projector to a camera. If the resolution a camera is lower than that of a projector within said projection system, then the transformation matrix will have holes where image data corresponding to a projector pixel will have been lost. In this, case, new image are generated to fill-in the holes. | 09-30-2010 |
20100253915 | Retro-Reflective Light Diffusing Display Systems - Aspects of the present invention involve novel display screens comprising light diffusion and retro-reflectivity. In embodiments, a retro-reflective light diffusion screen can be used to generate a three-dimensional autostereoscopic display by generating a plurality of viewing windows wherein each viewing window depicts a unique perspective image view. | 10-07-2010 |
20100253916 | Retro-Reflective Light Diffusing Display Systems - Aspects of the present invention involve novel display screens comprising light diffusion and retro-reflectivity. In embodiments, a retro-reflective light diffusion screen can be used to generate a three-dimensional autostereoscopic display by generating a plurality of viewing windows wherein each viewing window depicts a unique perspective image view. In embodiments, the retro-reflective light diffusion screen comprises a transparent medium layer between the retro-reflector surface and the light diffuser layer to help reduce ghost images. In embodiments, the retro-reflective light diffusion screen comprises a lenticular layer positioned such that the light diffuser layer is between the lenticular layer and the retro-reflective surface and is also positioned so that the light diffuser layer is at a focal plane of the lenticular layer. | 10-07-2010 |
20100253917 | Aerial Three-Dimensional Image Display Systems - Aspects of the present invention involve novel three-dimensional display systems. Multi-view-window-based display systems are used to generate floating three-dimensional displays. In embodiments, an optical focusing element is positioned at a distance that is greater than or equal to the focal length of the optical focusing element from the viewing windows to form projected viewing windows through which a user can see a floating 3D image. In alternative embodiments, an optical focusing element is positioned at a distance that is less than the focal length of the optical focusing element from the viewing windows to form a rear-projection-like three-dimensional display system. In embodiments, a retro-reflective light diffusion screen is used in the multi-view-window-based display systems. | 10-07-2010 |
20100299379 | Non-Negative Matrix Factorization as a Feature Selection Tool for Maximum Margin Classifiers - Non-negative matrix factorization, NMF, is combined with identification of a maximum margin classifier by minimizing a cost function that contains a generative component and the discriminative component. The relative weighting between the generative component and the discriminative component are adjusting during subsequent iterations such that initially, when confidence is low, the generative model is favored. But as the iterations proceed, confidence increases and the weight of the discriminative component is steadily increased until it is of equal weight as the generative model. Preferably, the cost function to be minimized is: | 11-25-2010 |
20110025929 | Light Transport Matrix from Homography - Aspects of the present invention include systems and methods for obtaining a light transport between a projector and a camera. In embodiments, the light transport between the projector and the camera is represented as a matrix and is obtained assuming that the projector displays on a surface that is planar or at least substantially planar. The light transport matrix is obtained by finding a homography between the projector and the camera. Using the homography to correlate camera and projector pixels and using color values in a captured solid color image, the light transport matrix can be obtained. In embodiments, at least an approximation of an inverse light transport matrix can also be computed, which is useful for many applications, such as inferring unknown projector images. | 02-03-2011 |
20110051989 | Orientation Free Watermarking Message Decoding from Document Scans - Bit data is encoded into characters in an input image by providing different darkness levels for pixels in either half of a text character. To determine if the input image is of a right-side up document, or an upside-down document, multiple scans of the input image at 90° rotations between scans may be made. Each scan result is searched for occurrences of a indicator prefix bit-sequence. The scan that contains the indicator prefix bit-sequence is elected as the right-side up orientation for the input image. If multiple scans show occurrences of the indicator prefix bit-sequence, then the scan that has the highest number of occurrences is elected as the correct orientation. Alternatively, the number of data bits between repeated occurrences of the indicator prefix bit-sequence is compared with a predefined message bit size, and the scan that matches most closely is elected as the correct orientation. | 03-03-2011 |
20110052094 | Skew Correction for Scanned Japanese/English Document Images - Bit data is encoded into characters in an input image by providing different darkness levels for pixels in either half of a text character. In order to detect document skew angle error prior to attempting to extract an encoded message, the orientation angle of text line(s) in the input image is determined, and a document skew angle is estimated from the line orientation angle(s). A Hough transform may be used to estimate line orientation angle. To determine if an input image of a document is orientated horizontally or vertically, the input image may be scanned for text characters along a first reference angle, and along a second angle 90° to the first angle. The scan that provides the higher number of potential text character is selected as the correct orientation for the input image. | 03-03-2011 |
20110081058 | Reconstructing Three-Dimensional Current Sources from Magnetic Sensor Data - Magnetic source imaging (MSI) involves the reconstruction of the current sources in a portion of a body, such as an organ, from measured magnetic field data. The measured magnetic field data may be from one-dimensional or three-dimensional sensors. Aspects of the present invention include systems and methods for reconstructing the electrical current of an organ given magnetic data. In embodiments, reconstruction of three-dimensional current sources is accomplished knowing or estimating the position, or offset, of the sensor plane with respect to the patient in order to form a set of linear equations. Alternatively, reconstruction of three-dimensional current sources is accomplished without knowing the offset of the sensor plane with respect to the patient. In embodiments, the linear and nonlinear systems of equations are iteratively used to obtain the current source information. In embodiments, multi-scale strategies are employed. | 04-07-2011 |
20110115921 | Context Constrained Novel View Interpolation - Aspects of the present invention include systems and methods for generating a novel view interpolation. In embodiments, feature correspondences and geometrical contexts are used to find additional correspondences based on the assumption of the local linear transformation. The accuracy and the number of correspondence matches may be improved by iterative refinement. Having obtained a set of correspondences, a novel view image can be generated. | 05-19-2011 |
20110176007 | Real-Time Geometry Aware Projection and Fast Re-Calibration - Aspects of the present invention include systems and methods for recalibrating projector-camera systems. In embodiments, systems and methods are able to recalibrate automatically the projector with arbitrary intrinsic and pose, as well as render for arbitrarily desired viewing point. In contrast to previous methods, the methods disclosed herein use the observing camera and the projector to form a stereo pair. Structured light is used to perform pixel-level fine reconstruction of the display surface. In embodiments, the geometric warping is implemented as a direct texture mapping problem. As a result, re-calibration of the projector movement is performed by simply computing the new projection matrix and setting it as a camera matrix. For re-calibrating the new view point, the texture mapping is modified according to the new camera matrix. | 07-21-2011 |
20110191400 | L1 Projections with Box Constraints - Similarities between simplex projection with upper bounds and L | 08-04-2011 |
20110194690 | Data Adaptive Message Embedding For Visible Watermarking - A watermarking system uses distinct bit patterns to identify a logic 0, a logic 1, and a marker bit, which demarcates segments of logic bit information. Marker bits, which are printed on both foreground and background areas of an image, outline message blocks. In message extraction, a preprocessing step removes any white boarders, identifies the best defined corner of a message block, crops the image, and rotates the image to place the identified corner at the top-left corner. Message extraction scans the rotated image in window segments of increasing size during multiple cycles. During each cycle, if a bit pattern cannot be identified as a data bit, then the size of the examined bit area is increased and rechecked to see it specifically is a marker bit. If no bit information can be definitively identified, then it is assigned a logic bit value based on a 50% random assignment. | 08-11-2011 |
20110194725 | Novel Bit Pattern Design For Visible Watermarking - A watermarking system uses distinct bit patterns to identify a logic 0, a logic 1, and a marker bit, which demarcates segments of logic bit information. Marker bits, which are printed on both foreground and background areas of an image, outline message blocks. In message extraction, a preprocessing step removes any white boarders, identifies the best defined corner of a message block, crops the image, and rotates the image to place the identified corner at the top-left corner. Message extraction scans the rotated image in window segments of increasing size during multiple cycles. During each cycle, if a bit pattern cannot be identified as a data bit, then the size of the examined bit area is increased and rechecked to see it specifically is a marker bit. If no bit information can be definitively identified, then it is assigned a logic bit value based on a 50% random assignment. | 08-11-2011 |
20110194726 | Embedded Message Extraction For Visible Watermarking - A watermarking system uses distinct bit patterns to identify a logic 0, a logic 1, and a marker bit, which demarcates segments of logic bit information. Marker bits, which are printed on both foreground and background areas of an image, outline message blocks. In message extraction, a preprocessing step removes any white boarders, identifies the best defined corner of a message block, crops the image, and rotates the image to place the identified corner at the top-left corner. Message extraction scans the rotated image in window segments of increasing size during multiple cycles. During each cycle, if a bit pattern cannot be identified as a data bit, then the size of the examined bit area is increased and rechecked to see it specifically is a marker bit. If no bit information can be definitively identified, then it is assigned a logic bit value based on a 50% random assignment. | 08-11-2011 |
20110200269 | Fast Approximation For Bilateral Filter - Multiple filters of a bilateral filter are decoupled to form into multple linear filtering operations, which permits faster processing. The bilateral filter is re-presented as an approximate bilateral filter, and subjected to a logarithm whose resultant components are further subjected to a series of Jensen approximations. The errors resulting from each Jensen approximation are collected into a single cumulative error factor, and it is then shown that the cumulative error may be ignored without adversed affect to the result. Thus, the original bilateral filter may be implemented as log(y | 08-18-2011 |
20110228042 | Various Configurations Of The Viewing Window Based 3D Display System - A panoramic 3D image is created by using multiple projectors whose field-of-view is narrower than the screen's width. Each projector provides a different image of a common subject from a different view angle, and the different images are mosaiced onto the screen. An observer may have a limited view of the composite image depending on which projectors are within the observer's field-of-view. A viewing volume is also extended by using space beyond a far limit line dependent upon the observer's inter-pupillary distance, the width of each projector's viewing window, and the distance from the projection baseline to the screen | 09-22-2011 |
20110228054 | Methods To Eliminate/Reduce The Crosstalk Artifacts Of The Retro-Reflective Auto-Stereoscopic 3D Display - Crosstalk artifacts in a retro-reflective auto-stereoscopic 3D display system are compensated by providing various methods of directing surface reflections of a screen away from a viewing region, i.e. a region from which the screen is viewed. This is achieved by splitting the screen in two, and tilting the left-side and right-side of the screen either towards, or away, from a projection baseline so as to direct mirror reflections away from the viewing region. Alternatively, the screen is not split, but virtical v-shaped grooves are made along the surface of the screen facing the projection line. The angle of the v-shaped groove direct surface reflections away from the viewing region, but the groove are substantially small that the screen appears flat to an observer. | 09-22-2011 |
20110243428 | Bi-Affinity Filter: A Bilateral Type Filter for Color Images - An edge preserving filter that works on the principle of matting affinity allows a better representation of the range filter term in bilateral class filters. The definition of the affinity term can be relaxed to suit different applications. An approximate bi-affinity filter whose output is shown to be very similar to the traditional bilateral filter is defined. The present technique has the added advantage that no color space changes are required and hence an input image can be handled in its original color space. This is a big benefit over the traditional bilateral filter, which needs conversion to perception based spaces, such as CIELAB, to generate results close to the present invention. The full bi-affinity filter preserves very minute details of the input image, and thus permits an enhanced zooming functionality. | 10-06-2011 |
20110304888 | Removing Leakage from a Double-Sided Document - Aspects of the present invention include systems and methods for mitigating the effects of leakage when duplicating an image from a double-sided document. In embodiments, a device is calibrated by computing a leakage function. The leakage function is used to obtain a leakage mitigation function. Given the leakage function and the leakage mitigation function, an estimate of a true version of the document image can be obtained using as inputs only the images of the front-side and back-side of the double-sided document. | 12-15-2011 |
20110316728 | Data Compression by Multi-Order Differencing - Embodiments of the present invention enable compression and decompression of data. Applications of the present invention are its use in embodiments of systems for compression and decompression of GPS long-term Ephemeris (LTE) data, although the present invention is not limited to such applications. In embodiments, the LTE data may be grouped into a set of data values associated with a parameter. In embodiments, a data set may be compressed by using a multi-order differencing scheme. In such a scheme, a set of the differences between values may be compressed because the differences have smaller magnitudes than the values. In embodiments, a multi-order differencing scheme determines how many levels (orders) of differencing may be applied to an original data set before it is compressed. In embodiments, the original data may be recovered from a compressed data set based on the type of multi-order differencing scheme used to generate the compressed data. | 12-29-2011 |
20120008862 | Bi-Affinity Filter: A Bilateral Type Filter for Color Images - Application of an image filtering algorithm, which defines an algorithm window within which a center pixel is processed relative to the other pixels within the algorithm window, is improved by use of an extended window larger than and encompassing the algorithm window. This approached is applied with an edge preserving filter that works on the principle of matting affinity and allows a better representation of the range filter term in bilateral class filters. An approximate bi-affinity filter whose output is shown to be very similar to the traditional bilateral filter is defined. The present technique has the added advantage that no color space changes are required and hence an input image can be handled in its original color space. | 01-12-2012 |
20120041725 | Supervised Nonnegative Matrix Factorization - Graph embedding is incorporated into nonnegative matrix factorization, NMF, while using the original formulation of graph embedding. Negative values are permitted in the definition of graph embedding without violating the nonnegative requirement of NMF. The factorized matrices of NMF are found by an iterative process. | 02-16-2012 |
20120041905 | Supervised Nonnegative Matrix Factorization - Supervised nonnegative matrix factorization (SNMF) generates a descriptive part-based representation of data, based on the concept of nonnegative matrix factorization (NMF) aided by the discriminative concept of graph embedding. An iterative procedure that optimizes suggested formulation based on Pareto optimization is presented. The present formulation removes any dependence on combined optimization schemes. Analytical and empirical evidence is presented to show that SNMF has advantages over popular subspace learning techniques as well as current state-of-the-art techniques. | 02-16-2012 |
20120041906 | Supervised Nonnegative Matrix Factorization - Supervised kernel nonnegative matrix factorization generates a descriptive part-based representation of data, based on the concept of kernel nonnegative matrix factorization (kernel NMF) aided by the discriminative concept of graph embedding. An iterative procedure that optimizes suggested formulation based on Pareto optimization is presented. The present formulation removes any dependence on combined optimization schemes. | 02-16-2012 |
20120121204 | IMPORTANCE FILTERING FOR IMAGE RETARGETING - A content-aware image retargeting technique uses an “importance filtering” technique to preserve important information in the resizing of an image. The image saliency is first filtered, guided by the image itself to achieve a structure-consistent importance map. The pixel importance is then used as the key constraint in computing the gradient map of pixel shifts from the original resolution to the target resolution. Finally the shift gradient is integrated across the image by a weighted filtering process to construct a smooth pixel shift-map and render the target image. The weight is again controlled by the pixel importance. The two filtering processes enforce the maintaining of structural consistency while preserving the important contents in the target image. The simple nature of the present filter operations allow for real-time applications and easy extension to video retargeting, as the structural constraints from the original image naturally convey the temporal coherence between frames. | 05-17-2012 |
20120141018 | L1-Optimized AAM Alignment - An Active Appearance Model, AAM, uses an L | 06-07-2012 |
20120195495 | Hierarchical Tree AAM - An active appearance model is built by arranging the training images in its training library into a hierarchical tree with the training images at each parent node being divided into two child nodes according to similarities in characteristic features. The number of node levels is such that the number of training images associated with each leaf node is smaller than a predefined maximum. A separate AAM, one per leaf node, is constructed using each leaf node's corresponding training images. In operation, starting at the root node, a test image is compared with each parent node's two child nodes and follows a node-path of model images that most closely matches the test image. The test image is submitted to an AAM selected for being associated with the leaf node at which the test image rests. The selected AAM's output aligned image may be resubmitted to the hierarchical tree if sufficient alignment is not achieved. | 08-02-2012 |
20120197145 | High-Resolution Magnetocardiogram Restoration for Cardiac Electric Current Localization - Magnetocardiogram (MCG) provides temporal and spatial measurements of cardiac electric activities, which permits current localization. An MCG device usually consists of a small number of magnetic sensors in a planar array. Each sensor provides a highly low-resolution 2D MCG map. Such a low-res map is insufficient for cardiac electric current localization. To create a high resolution MCG image from the sparse measurements, an algorithm based on model learning is used. The model is constructed using a large number of randomly generated high resolution MCG images based on the Biot-Savart Law. By fitting the model with the sparse measurements, high resolution MCG image are created. Next, the 2D position of the electric current is localized by finding the peak in the tangential components of the high resolution MCG images. Finally, the 2D current localization is refined by a non-linear optimization algorithm, which simultaneously recovers the depth of the electric current from the sensor and its magnitude and orientation. | 08-02-2012 |
20120219186 | Continuous Linear Dynamic Systems - Aspects of the present invention include systems and methods for segmentation and recognition of action primitives. In embodiments, a framework, referred to as the Continuous Linear Dynamic System (CLDS), comprises two sets of Linear Dynamic System (LDS) models, one to model the dynamics of individual primitive actions and the other to model the transitions between actions. In embodiments, the inference process estimates the best decomposition of the whole sequence into continuous alternating between the two set of models, using an approximate Viterbi algorithm. In this way, both action type and action boundary may be accurately recognized. | 08-30-2012 |
20120219195 | 3D Current Reconstruction From 2D Dense MCG Images - A current dipole is determined by solving the inverse problem multiple times in consecutive stages. At each stage, a new high resolution image is generated from a magnetic field map from the immediately previous stage, and at each stage more constraints are extracted from the current high resolution image than were available in the immediately previous stage. After the constraints are extracted from a current high resolution image, the current high resolution is updated to incorporate constraints from the immediately previous stage. The updated high resolution image, and the currently extracted constraints are used to resolve the inverse problem, and the Biot-Savart law is used to calculated the current dipole. | 08-30-2012 |
20120219210 | Multi-Scale, Perspective Context, and Cascade Features for Object Detection - Systems and methods for object detection are presented herein. Embodiments of the present invention utilizing a cascade feature, one or more features at different scales, one or more multi-scale features in combination with a perspective feature, or combinations thereof to detect an object of interest in an input image. In embodiments, the various features are used to train classifiers. In embodiments, the trained classifiers are used in detecting an object of interest in one or more input images. | 08-30-2012 |
20120219211 | Contextual Boost for Object Detection - Aspects of the present invention includes systems and methods for generating detection models that consider contextual information of an image patch and for using detection models that consider contextual information. In embodiments, a multi-scale image context descriptor is generated to represent the contextual cues in multiple parameters, such as spatial, scaling, and color spaces. In embodiments, a classification context is defined using the contextual features and is used in a contextual boost classification scheme. In embodiments, the contextual boost propagates contextual cues to larger coverage through iterations to improve the detection accuracy. | 08-30-2012 |
20120219213 | Embedded Optical Flow Features - Aspects of the present invention include systems and methods for generating an optical flow-based feature. In embodiments, to extract an optical flow feature, the optical flow at sparse interest points is obtained, and Locality-constrained Linear Coding (LLC) is applied to the sparse interest points to embed each flow into a higher-dimensional code. In embodiments, for an image frame, the multiple codes are combined together using a weighted pooling that is related to the distribution of the optical flows in the image frame. In embodiments, the feature may be used in training models to detect actions, in trained models for action detection, or both. | 08-30-2012 |
20120219224 | Local Difference Pattern Based Local Background Modeling For Object Detection - Systems and methods for object detection that consider background information are presented. Embodiments of the present invention utilizing a feature called Local Difference Pattern (LDP), which is more discriminative for modeling local background image features. In embodiments, the LDP feature is used to train detection models. In embodiments, the LDP feature may be used in detection to differentiate different image background conditions and adaptively adjust classification to yield higher detection rates. | 08-30-2012 |
20120237116 | Identifying Text Pixels in Scanned Images - A processor and method make use of multiple weak classifiers to construct a single strong classifier to identify regions that contain text within an input image document. The weak classifiers are grouped by their computing cost from low to median to high, and each weak classifier is assigned a weight value based on its ability to accurately identify text regions. A level 1 classifier is constructed by selecting weak classifiers from the low group, a level 2 classifier is constructed by selecting weak classifiers from the low and median groups, and a level 3 classifier is constructed by selecting weak classifiers from the low, median and high groups. Regions that the level 1 classifier identifies as containing text are submitted to the level 2 classifier, and regions that the level 2 classifier identifies as containing text are submitted to the level 3 classifier. | 09-20-2012 |
20120250985 | Context Constraints for Correcting Mis-Detection of Text Contents in Scanned Images - Misclassified text components are identified and corrected by comparing non-text components with their neighboring text components. If a non-text component being examined is found to be substantially aligned with its neighboring text components, and is further found to have a similar average color and size as its neighboring text components, then it is reclassified as a text component. Misclassified non-text components are reduced by restricting text labeling to areas of a document image defined by an edge map. The edge map is made by smoothing the document image, and applying edge detection to the smooth image. | 10-04-2012 |
20120269435 | Contact Text Detection in Scanned Images - A device and method for identifying text pixels that are erroneously classified as non-text pixels, includes accessing an image region containing a non-text component. For each non-text component within the image region component, only one determines if there are any long line structures within the bounding box defined by the non-text component. If the long line structures are greater than a predefined percentage of the span of the dimension of the bounding box parallel to the line structure, then the line structure is removed. Any remaining non-text pixels within the bounding box are reclassified as text-pixels. | 10-25-2012 |
20120299906 | Model-Based Face Image Super-Resolution - An output image of higher resolution than an input image is constructed by using a low resolution (LR) dictionary of triangle data entries, each having a one-to-one correlation with a high resolution (HR) data entry in an HR dictionary of triangle data entries. The input image is triangularized, and the closest matching LR data entry in the LR dictionary for each triangle in the triangularized input image is identified. The HR data entry correlated to each identified matching LR data entry is then used to construct the output image by wrapping the correlated HR data entry onto the corresponding triangle on the triangularized input image. | 11-29-2012 |
20130002828 | Context and Epsilon Stereo Constrained Correspondence Matching - A catadioptric camera having a perspective camera and multiple curved mirrors, images the multiple curved mirrors and uses the epsilon constraint to establish a vertical parallax between points in one mirror and their corresponding reflection in another. An ASIFT transform is applied to all the mirror images to establish a collection of corresponding feature points, and edge detection is applied on mirror images to identify edge pixels. A first edge pixel in a first imaged mirror is selected, its 25 nearest feature points are identified, and a rigid transform is applied to them. The rigid transform is fitted to 25 corresponding feature points in a second imaged mirror. The closes edge pixel to the expected location as determined by the fitted rigid transform is identified, and its distance to the vertical parallax is determined. If the distance is not greater than predefined maximum, then it is deemed correlate to the edge pixel in the first imaged mirror. | 01-03-2013 |
20130034263 | Adaptive Threshold for Object Detection - Systems and methods for developing and using adaptive threshold values for different input images for object detection are disclosed. In embodiments, detector response histogram-based systems and methods train models for predicting optimal threshold values for different images. In embodiments, when training the model, an optimal threshold value for an image is defined as the value that maximizes the reduction of false positive image patches while preserving as many true positive image patches as possible. Once trained, the model may be used to set different threshold values for different images by inputting a detector response histogram for the image patches of an image into the model to determine a threshold value for detection. | 02-07-2013 |
20130038696 | Ray Image Modeling for Fast Catadioptric Light Field Rendering - A catadioptric camera creates images light fields from a 3D scene by creating ray images defined as 2D arrays of ray-structure picture-elements (ray-xels). Each ray-xel capture light intensity, mirror-reflection location, and mirror-incident light ray direction. A 3D image is then rendered from the ray images by combining the corresponding ray-xels. | 02-14-2013 |
20130079622 | Denoise MCG Measurements - A magnetocardiogram (MCG) system with reduced noise artifacts is produced by first creating high-resolution image representations of low-resolution measurements obtained with a magnetic field sensor unit. The high-resolution image representations are created by use of a PCA model that has been trained using a library of ideal, no-noise, high-resolution images. The Biot-Sarvart Law is then used to create a 3D model of a current impulse, given the high-resolution image representations. From the 3D current impulse model, ideal sensor unit measurements as they would have been obtained using a theoretical sensor unit observing the 3D current impulse model are synthesized. | 03-28-2013 |
20130127827 | Multiview Face Content Creation - New views of a 2D image are generated by identifying an object class within the image, such as through a face detector. The face is then fitted to a model face by means of an AAM, and the results extended to a fitted 3D polygon mesh face. A boundary perimeter with predefined anchor points and a predefined triangulation with the 3D polygon mesh is defined a predefined depth distance from the depth center of known landmarks within the 3D polygon mesh face. By rotating the 3D polygon mesh face relative to the boundary perimeter, which may follow the perimeter of the input image, new views of the input image are generated. | 05-23-2013 |
20130129143 | Global Classifier with Local Adaption for Objection Detection - Aspects of the present invention include object detection training systems and methods and using object detection systems and methods that have been trained. Embodiments presented herein include hybrid learning approaches that combine global classification and local adaptations, which automatically adjust model complexity according to data distribution. Embodiments of the present invention automatically determine model complexity of the local learning algorithm according to the distribution of ambiguous samples. And, embodiments of the local adaptation from global classifier avoid the common under-training problem for local classifier. | 05-23-2013 |
20130132316 | Substructure and Boundary Modeling for Continuous Action Recognition - Embodiments of the present invention include systems and methods for improved state space modeling (SSM) comprising two added layers to model the substructure transition dynamics and action duration distribution. In embodiments, the first layer represents a substructure transition model that encodes the sparse and global temporal transition probability. In embodiments, the second layer models the action boundary characteristics by injecting discriminative information into a logistic duration model such that transition boundaries between successive actions can be located more accurately; thus, the second layer exploits discriminative information to discover action boundaries adaptively. | 05-23-2013 |
20130266195 | Hash-Based Face Recognition System - In a face recognition system, overlapping patches are defined on a canonical face. Random clusters of pixel pairs are defined within each patch, and binary features are determined for each pixel pair by comparing their respective feature values. An inverted index hash table is constructed of the binary features. Similar binary features are then determined on a library of registrable samples of identified faces. A log probability of each registrable sample generating a binary feature from a corresponding cluster of pixel pairs at each specific patch location is determined and stored in the hash table. In a search phase, similar binary features are determined, and a hash key is determined for each binary feature. The log probabilities for each identity found in the hash table are summed for all clusters of pixel pairs and locations and sorted to find the high probability match. | 10-10-2013 |
20130268563 | Fast and Robust Classification Algorithm for Vein Recognition Using Infrared Images - A specific item within an item class is identified by defining sets of descriptor data from a training library. The collected descriptor data is grouped and organized into a hierarchical tree, where each leaf node is defined by relations between corresponding parts of the descriptor data. Registrable sets of descriptor data are then identified from a collection of registrable samples. The registrable sets of descriptors are sorted into the hierarchical tree. When an input sample to be identified is received, a test set of descriptor data is generated from the input sample. The test set is then sorted into the hierarchical tree. Each leaf node that receives a part of the test set provides a vote for the registered samples it contains. The registered sample with the most votes is deemed a match for the input sample. | 10-10-2013 |
20130317337 | Continuous Modeling for Dipole Localization from 2D MCG Images with Unknown Depth - A system identifies double-layer dipoles in a magnetic image by defining two-dimensional patches of distributed point charges that simulate the double-layer dipoles. The geometric center of a two-dimensional patch is used as the location of an equivalent dipole moment of the double-layer dipole. The momentum of the equivalent dipole moment is determined by submitting the magnetic image to a dipole construction system that identifies the location and momentum based on the submitted magnetic image. | 11-28-2013 |
20130324832 | 2D Dipole Localization Using Absolute Value of MCG Measurements - A magnetic imaging systems produces magnetic magnitude images using magnetic sensors capable of determining only the absolute value of a detected magnetic field and provide no information regarding the positive or negative sign of the detected magnetic image. A 2D dipole location is determines the 2D location of a dipole within a magnetic magnitude image by finding the minimum of the derivative of the absolute value of the magnetic field. This 2D dipole location is then used to determine the 3D position and momentum of a current dipole responsible for the observed magnetic magnitude image. The current dipole is used to generate a magnetic image that incorporate positive and negative sign information. | 12-05-2013 |
20140016830 | Small Vein Image Recognition and Authorization Using Constrained Geometrical Matching and Weighted Voting Under Generic Tree Model - An automated registration and authentication system combines a generative and discriminative approach to improve the matching of a query object to a database of registered objects. The discriminative approach uses a voting mechanism to identify a most likely match, and the generative approach uses ASIFT transforms to determine a best geometric match. The two results are combined using a technique base on Bayesian inference theory. | 01-16-2014 |
20140019489 | Constructing Incremental Tree Model for Vein Image Recognition and Authentication - An indexed hierarchical tree search structure implements incremental tree modification to add new registrants to the tree without requiring reconstruction of the tree. Only data within a leaf node that receives new data is used in the incremental tree modification. Consequently, the original data set used in the creation of the hierarchical tree may be deleted after construction of the tree. | 01-16-2014 |
20140025607 | Confidence Based Vein Image Recognition and Authentication - An indexed hierarchical tree search structure converts each registration sample into an equivalent registration model based on the clustering of its registration item descriptors in the leaf nodes of the hierarchical tree. Query item descriptors from a query sample from someone wanting to be recognized are distributed into the hierarchical tree. A query model is defined based on the clustering of query item descriptors at the leaf nodes, and registration and verification are made based on comparison of the query model and the registration models. | 01-23-2014 |
20140126810 | Computer Vision Methods And Systems To Recognize And Locate An Object Or Objects In One Or More Images - Embodiments of the present invention include systems and methods for identifying and locating an object in an image. In embodiments, an object in an image may be identified by segmenting a first image of an object into one or more superpixels; extracting local descriptors from the first image, each of the descriptors having an interest point with a location; correlating the local descriptors to the superpixels based on locations of the local descriptors and superpixels; determining a probability for an object label for each of a set of the superpixels; and assigning an object label to each of the set of the superpixels based on the probability and a smoothness factor that includes weighting in terms of one or more of spatial, colors, angular distances between superpixels. The superpixels of an image may be concatenated to predict an object label for the image and to determine the location of the image. | 05-08-2014 |
20140133742 | Detector Evolution With Multi-Order Contextual Co-Occurrence - Aspects of the present invention comprise generating and using Multi-Order Contextual co-Occurrence (MOCO) descriptors to implicitly model the high level context using detection responses from a baseline object detector. In embodiments, a 1 | 05-15-2014 |
20140133762 | Point Set Matching with Outlier Detection - Aspects of the present invention include point set matching systems and methods. In embodiments, a tree model is used to find candidate matching locations for a set of query points. In embodiments, a similitude transform is assumed, and the parameters are separately solved to reduce computation complexity. In embodiments, the dominant scaling (α) and rotation (R) parameters are obtained by identifying a maximum in an accumulator space. A translation (t) matrix is calculated in another 1D accumulator space. With the obtained similitude transform, outliers can be reliably detected. This two-stage approach reduces the complexity and calculation time of determining a similitude transform and increases the accuracy and ability to detect outliers. | 05-15-2014 |
20140161355 | Sparse Coding Based Superpixel Representation Using Hierarchical Codebook Constructing And Indexing - Embodiments of the present invention include systems and methods for identifying an object in an image. In embodiments, object identification includes using smooth encoding from a tree structure to generate a feature from a descriptor. In embodiments, the smooth encoding may be performed by, having identifying a leaf node for a descriptor, moving up the tree voting structure a number of levels from the identified leaf node to a branch node to identify leaf nodes dependent from the branch node; and then, by determining a sparse code under a condition that a distance between the descriptor and centroids of the leaf nodes dependent from the branch node weighted by the sparse code is minimized, wherein each element of the sparse code representing a weight corresponding to leaf nodes. | 06-12-2014 |
20140211989 | Component Based Correspondence Matching for Reconstructing Cables - In a stereoscopic pair of images, global homography at the image level is applied to feature points extracted from connected components (CC) to identify corresponding CC's and feature points, and to discard any CC's that do not have a corresponding pair in the stereoscopic pair of images. Local homography at the CC level is then applied to individual footprint areas of the previously identified paired CC to further clean feature point correspondence. Any CC or feature point or pixel within a paired CC footprint not satisfying local homography constraint is discarded. A correspondence is also extrapolated between unknown pixels within a paired CC footprint using a weighing mechanism and the unknown pixel's surrounding pixels that do have a known correspondence. This provides a dense correspondence of pixels, or feature points, which is then used to create a dense 3D point cloud of identified objects within a 3D space. | 07-31-2014 |
20140253554 | Context Constrained Novel View Interpolation - Aspects of the present invention include systems and methods for generating a novel view interpolation. In embodiments, feature correspondences and geometrical contexts are used to find additional correspondences based on the assumption of the local linear transformation. The accuracy and the number of correspondence matches may be improved by iterative refinement. Having obtained a set of correspondences, a novel view image can be generated. | 09-11-2014 |
20140267614 | 2D/3D Localization and Pose Estimation of Harness Cables Using A Configurable Structure Representation for Robot Operations - A robot is made to recognize and manipulate different types of cable harnesses in an assembly line. This is achieved by using a stereo camera system to define a 3D cloud of a given cable harness. Pose information of specific parts of the cable harness are determined from the 3D point cloud, and the cable harness is then re-presented as a collection of primitive geometric shapes of known dimensions, whose positions and orientations follow the spatial position of the represented cable harness. The robot can then manipulate the cable harness by using the simplified representation as a reference. | 09-18-2014 |
20140355889 | Tree-Model-Based Stereo Matching - Aspects of the present invention include feature point matching systems and methods. In embodiments, a tree model is used to find candidate matching features for query feature points. In embodiments, the tree model may be pre-learned using a set of sample images, or alternatively, the tree model may be constructed using one or more of the input images. In embodiments, features in one of the stereo images are registered with the tree model, and then features from the other stereo image are queried through the tree model to identify their correspondences in the registered stereo image. As compared to prior brute force matching methodologies, embodiments disclosed herein reduce the complexity and calculation time for determining matching feature points in stereo images. | 12-04-2014 |
20150055839 | Intelligent Weighted Blending for Ultrasound Image Stitching - Ultrasound images are stitched together by extracting target image regions within each ultrasound image, identifying interest points for the extracted target images and then identifying interest point correspondences between the interest points of all the extracted target image regions. The interest point correspondence is used to define a common, word coordinate for all extracted target images, and the extracted target images are warped onto the world coordinates. A distance weight, w | 02-26-2015 |
20150055840 | Ultrasound Image Object Boundary Localization by Intensity Histogram Classification Using Relationships Among Boundaries - Fatty tissue boundary depths and muscle tissue boundary depths are identified in an ultrasound image by first creating an average intensity histogram of the ultrasound image. The histogram has a plurality of peaks, but has the characteristic that one of its peaks corresponds to a fat boundary depth, and a second of its peaks corresponds to a muscle boundary depth. A first classifier based solely on the local-characteristics of individual peaks is used to identify a first fat tissue depth. A second classifier trained to find a muscle depth given a fat depth, receives the output from the first classifier and identifies an output muscle tissue depth relative to the first fat tissue depth. A third classifier trained to find a fat boundary depth given a muscle boundary depth, receives the output muscle tissue depth and outputs a second fat boundary depth. | 02-26-2015 |
20150055841 | Orientation-Aware Average Intensity Histogram to Indicate Object Boundary Depth in Ultrasound Images - Linear candidate lines at different angles are used to determine an average intensity for each pixel level of an ultrasound image. The resultant average intensities are collected into a histogram, and the histogram is used to determine the depth positions of tissue boundary lines within an ultrasound image. | 02-26-2015 |