Class / Patent application number | Description | Number of patent applications / Date published |
382157000 | Network learning techniques (e.g., back propagation) | 27 |
20090141969 | Transfer Learning Methods and systems for Feed-Forward Visual Recognition Systems - A method and system for training a neural network of a visual recognition computer system, extracts at least one feature of an image or video frame with a feature extractor; approximates the at least one feature of the image or video frame with an auxiliary output provided in the neural network; and measures a feature difference between the extracted at least one feature of the image or video frame and the approximated at least one feature of the image or video frame with an auxiliary error calculator. A joint learner of the method and system adjusts at least one parameter of the neural network to minimize the measured feature difference. | 06-04-2009 |
20100061624 | DETECTING ANOMALOUS EVENTS USING A LONG-TERM MEMORY IN A VIDEO ANALYSIS SYSTEM - Techniques are described for detecting anomalous events using a long-term memory in a video analysis system. The long-term memory may be used to store and retrieve information learned while a video analysis system observes a stream of video frames depicting a given scene. Further, the long-term memory may be configured to detect the occurrence of anomalous events, relative to observations of other events that have occurred in the scene over time. A distance measure may used to determine a distance between an active percept (encoding an observed event depicted in the stream of video frames) and a retrieved percept (encoding a memory of previously observed events in the long-term memory). If the distance exceeds a specified threshold, the long-term memory may publish the occurrence of an anomalous event for review by users of the system. | 03-11-2010 |
20120045119 | METHOD OF IDENTIFYING AN OBJECT IN A VISUAL SCENE - A plurality of features determined from at least a portion of an image containing information about an object are processed with an inclusive neural network, and with a plurality of exclusive neural networks, so as to provide a plurality of inclusive probability values representing probabilities that the portion of the image corresponds to at least one of at least two different classes of objects, and for each exclusive neural network, so as to provide first and second exclusive probability values representing probabilities that the portion of the image respectively corresponds. or not. to at least one class of objects. The plurality of inclusive probability values, and the first and second exclusive probability values from each of the exclusive neural networks, provide for identifying whether the portion of the image corresponds, or not, to any of the at least two different classes of objects. | 02-23-2012 |
20130148879 | INFORMATION PROCESSING APPARATUS, INFORMATION PROCESSING METHOD, AND PROGRAM - An information processing apparatus includes a network learning portion that performs learning of an appearance/position recognition network by constraining first to third weights and using a learning image, wherein the appearance/position recognition network has a foreground layer including a position node, a background layer including a background node, and an image layer including a pixel node, and is a neural network in which the position node, the background node, and the pixel node are connected to each other, and wherein the first weight is a connection weight between the position node and the pixel node, the second weight is a connection weight between the position node and the background node, and the third weight is a connection weight between the background node and the pixel node. | 06-13-2013 |
20140270488 | METHOD AND APPARATUS FOR CHARACTERIZING AN IMAGE - The present invention relates to a method and system for characterizing an image. The characterization may then be used to conduct a search for similar images, for example using a learning system trained using previously characterized images. A face may be identified within the image and a subsection extracted from said image which does not contain said face. At least one fixed size patch is taken from said extracted subsection; and input into said learning network to characterize said image. | 09-18-2014 |
20150117759 | SYSTEM FOR SEARCH AND METHOD FOR OPERATING THEREOF - Provided are a system for search and a method for operating thereof. The system for search includes: a preliminary data analysis part which extracts a variety of attributes through analysis of images being input, analyzes a trend about a category as information requested by a client with the image analysis result, and stores the trend analysis result as metadata; an index part which stores the image analysis result, and structuralizes, organizes and stores the stored metadata in order to easily search the metadata; and a search part which extracts trend information matching a category input by a client, from the index part and provides the trend information in a predetermined format. | 04-30-2015 |
20150117760 | Regionlets with Shift Invariant Neural Patterns for Object Detection - Systems and methods are disclosed for detecting an object in an image by determining convolutional neural network responses on the image; mapping the responses back to their spatial locations in the image; and constructing features densely extract shift invariant activations of a convolutional neural network to produce dense features for the image. | 04-30-2015 |
20160034788 | LEARNING IMAGE CATEGORIZATION USING RELATED ATTRIBUTES - A first set of attributes (e.g., style) is generated through pre-trained single column neural networks and leveraged to regularize the training process of a regularized double-column convolutional neural network (RDCNN). Parameters of the first column (e.g., style) of the RDCNN are fixed during RDCNN training Parameters of the second column (e.g., aesthetics) are fine-tuned while training the RDCNN and the learning process is supervised by the label identified by the second column (e.g., aesthetics). Thus, features of the images may be leveraged to boost classification accuracy of other features by learning a RDCNN. | 02-04-2016 |
20160035078 | IMAGE ASSESSMENT USING DEEP CONVOLUTIONAL NEURAL NETWORKS - Deep convolutional neural networks receive local and global representations of images as inputs and learn the best representation for a particular feature through multiple convolutional and fully connected layers. A double-column neural network structure receives each of the local and global representations as two heterogeneous parallel inputs to the two columns. After some layers of transformations, the two columns are merged to form the final classifier. Additionally, features may be learned in one of the fully connected layers. The features of the images may be leveraged to boost classification accuracy of other features by learning a regularized double-column neural network. | 02-04-2016 |
20160086078 | OBJECT RECOGNITION WITH REDUCED NEURAL NETWORK WEIGHT PRECISION - A client device configured with a neural network includes a processor, a memory, a user interface, a communications interface, a power supply and an input device, wherein the memory includes a trained neural network received from a server system that has trained and configured the neural network for the client device. A server system and a method of training a neural network are disclosed. | 03-24-2016 |
20160125572 | DEVICE AND METHOD TO GENERATE IMAGE USING IMAGE LEARNING MODEL - At least some example embodiments disclose a device and a method for generating a synthetic image and a different-angled image and eliminating noise. The method may include receiving input images, extracting feature values corresponding to the input images using an image learning model, the image learning model permitting an input and an output to be identical and generating a synthetic image based on the feature values corresponding to the input images using the image learning model. | 05-05-2016 |
20160140408 | Neural Network Patch Aggregation and Statistics - Neural network patch aggregation and statistical techniques are described. In one or more implementations, patches are generated from an image, e.g., randomly, and used to train a neural network. An aggregation of outputs of patches processed by the neural network may be used to label an image using an image descriptor, such as to label aesthetics of the image, classify the image, and so on. In another example, the patches may be used by the neural network to calculate statistics describing the patches, such as to describe statistics such as minimum, maximum, median, and average of activations of image characteristics of the individual patches. These statistics may also be used to support a variety of functionality, such as to label the image as described above. | 05-19-2016 |
20160148079 | OBJECT DETECTION USING CASCADED CONVOLUTIONAL NEURAL NETWORKS - Different candidate windows in an image are identified, such as by sliding a rectangular or other geometric shape of different sizes over an image to identify portions of the image (groups of pixels in the image). The candidate windows are analyzed by a set of convolutional neural networks, which are cascaded so that the input of one convolutional neural network layer is based on the input of another convolutional neural network layer. Each convolutional neural network layer drops or rejects one or more candidate windows that the convolutional neural network layer determines does not include an object (e.g., a face). The candidate windows that are identified as including an object (e.g., a face) are analyzed by another one of the convolutional neural network layers. The candidate windows identified by the last of the convolutional neural network layers are the indications of the objects (e.g., faces) in the image. | 05-26-2016 |
20160148080 | METHOD AND APPARATUS FOR RECOGNIZING OBJECT, AND METHOD AND APPARATUS FOR TRAINING RECOGNIZER - A recognition method includes receiving an input image; and recognizing a plurality of elements associated with the input image using a single recognizer pre-trained to recognize a plurality of elements simultaneously. | 05-26-2016 |
20160180200 | LARGE-SCALE CLASSIFICATION IN NEURAL NETWORKS USING HASHING | 06-23-2016 |
20160379352 | LABEL-FREE NON-REFERENCE IMAGE QUALITY ASSESSMENT VIA DEEP NEURAL NETWORK - A method for training a neural network to perform assessments of image quality is provided. The method includes: inputting into the neural network at least one set of images, each set including an image and at least one degraded version of the image; performing comparative ranking of each image in the at least one set of images; and training the neural network with the ranking information. A neural network and image signal processing tuning system are disclosed. | 12-29-2016 |
20190147296 | CREATING AN IMAGE UTILIZING A MAP REPRESENTING DIFFERENT CLASSES OF PIXELS | 05-16-2019 |
20190147298 | META-LEARNING FOR MULTI-TASK LEARNING FOR NEURAL NETWORKS | 05-16-2019 |
20190147304 | FONT RECOGNITION BY DYNAMICALLY WEIGHTING MULTIPLE DEEP LEARNING NEURAL NETWORKS | 05-16-2019 |
20190147305 | AUTOMATICALLY SELECTING IMAGES USING MULTICONTEXT AWARE RATINGS | 05-16-2019 |
20190147321 | IMAGE GENERATION METHOD, IMAGE GENERATION APPARATUS, AND IMAGE GENERATION PROGRAM | 05-16-2019 |
20190147586 | DEFECT INSPECTION APPARATUS, DEFECT INSPECTION METHOD, AND PROGRAM THEREOF | 05-16-2019 |
20220138490 | IMAGE PROCESSING APPARATUS, IMAGE PROCESSING METHOD, AND NON-TRANSITORY COMPUTER-READABLE STORAGE MEDIUM - A connected layer feature is generated by connecting outputs of a plurality of layers of a hierarchical neural network obtained by processing an input image using the hierarchical neural network. An attribute score map representing an attribute of each region of the input image is generated for each attribute using the connected layer feature. A recognition result for a recognition target is generated and output by integrating the generated attribute score maps for respective attributes. | 05-05-2022 |
20220138494 | METHOD AND APPARATUS FOR CLASSIFICATION USING NEURAL NETWORK - A method and apparatus for classification using a neural network. A classification apparatus includes at least one processor and a memory. The memory is configured to store a classifier and a preprocessor including a defensive noise generator. The at least one processor generates defensive noise from an input image through the defensive noise generator in the preprocessor, generates a combined image by combining the input image and the defensive noise, and outputs a classification result by inputting the combined image to the classifier. | 05-05-2022 |
20220138507 | RECORDING MEDIUM DETERMINATION APPARATUS AND METHOD OF DETERMINING TYPE OF RECORDING MEDIUM - A recording medium determination apparatus includes an image data acquisition unit configured to acquire image data obtained by capturing an image of a predetermined area in a recording medium, a first extraction unit configured to extract a first feature amount by processing the image data using a first parameter, a second extraction unit configured to extract a second feature amount by processing the image data using a second parameter different from the first parameter, and a determination unit configured to determine a type of the recording medium based on the first feature amount and the second feature amount. | 05-05-2022 |
20220138910 | METHODS AND SYSTEMS FOR TRAINING CONVOLUTIONAL NEURAL NETWORKS - A computer-implemented method for training a convolutional neural network includes receiving a captured image. A denoised image is generated by applying the convolutional neural network to the captured image. The convolutional neural network is trained based on a high frequency loss function, as well as the captured image and the denoised image. | 05-05-2022 |
20220138957 | METHODS AND SYSTEMS FOR MEDICAL IMAGE SEGMENTATION - A method may include obtaining a first image associated with an image to be segmented, and performing an iteration process for obtaining a target image. The iteration process may include one or more iterations each of which includes: obtaining an image to be modified; obtaining one or more modifications performed on the image to be modified; generating a second image by inputting the image to be segmented, the image to be modified, and the one or more modifications into the image segmentation model; in response to determining that the second image satisfies the first condition, terminating the iteration process by determining the second image as the target image; or in response to determining that the second image does not satisfy the first condition, initiating a new iteration of the iteration process by determining the second image as the image to be modified. | 05-05-2022 |