| 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 |
