Abstract: The invention relates to a method for generating a representation of a finger print minutiae information. The invention also relates to a method for generating a representation of a finger print for biometric template protection purposes Biometric template protection techniques provide technological means to protect the privacy of biometric reference information stored in biometric. systems These methods stand in sharp contrast to approaches where biometric information is protected only by legislation and procedures around storage facilities. These systems are not reliable as they are susceptible to human and procedural errors. Template protection guarantees the protection of biometric information without the assumption that individuals are trusted or procedures are properly implemented.

Abstract: This specification relates to presenting image search results. In general, one aspect of the subject matter described in this specification can be embodied in methods that include the actions of receiving an image query, the image query being a query for image search results; receiving ranked image search results responsive to the image query, the image search results each including an identification of a corresponding image resource; generating a similarity matrix for images identified by the image search results; generating a hierarchical grouping of the images using the similarity matrix; identifying a canonical image for each group in the hierarchical grouping using a ranking measure; and presenting a visual representation of the image search results based on the hierarchical grouping and the identified canonical images.

Abstract: An information processing device includes: a foreground state estimating unit configured to estimate a foreground state of an image using an actual image which is an image to be actually observed; and a visible model updating unit configured to update a background visible model which is visibility of the background of an image and a foreground visible model which is visibility of the foreground using an estimation result of the foreground state.

Abstract: Methods, systems, and apparatus, including computer programs encoded on computer storage media, for classifying resources using scores from multiple classifiers. In general, one aspect of the subject matter described in this specification can be embodied in methods that include the actions of receiving identifying a collection of documents to classify; receiving a plurality of classifiers for scoring a document with respect to a specified property; for each document in the collection, applying each of the plurality of classifiers, each classifier generating a score associated with a likelihood that the document has the specified property, combining the scores from each classifier including applying a multiple classifier model that uses monotonic regression to combine the plurality of classifiers, and classifying the document as having the specified property based on the combined score.

Abstract: Image curation techniques are described. In one or more implementations, one or more modules are launched for execution on a computing device. Responsive to the launch, criteria are generated automatically and without user intervention through execution of the one or more modules by a computing device. Images are curated using the generated criteria automatically and without user intervention through execution of the one or more modules, the curated images identified from a plurality of different image sources that are associated with a user. The curated images are caused to be displayed by a display device of the computing device automatically and without user intervention through execution of the one or more modules.

Abstract: A radiation imaging apparatus is provided. The apparatus has moving means moving a pair of an X-ray tube and a detector relatively to an object. The apparatus further has means which acquire digital frame data outputted from the detector. The frame data are acquired from the same portion being imaged of the same object at different time points. The apparatus has means which use the frame data to produce a plurality of three-dimensional optimally focused images at the respective time points, an actual position and shape of the portion being imaged being reflected in the images, and means which estimate changes of the plural three-dimensional optimally focused images.

Abstract: Technologies pertaining to object detection are described herein. A cascaded classifier executes over subwindows of an image in a plurality of stages. A crosstalk cascade is employed to reject subwindows as being candidates for including an object that is desirably detected, where the crosstalk cascade is a combination of multiple cascades.

Abstract: A system, method, and computer program product are provided for automatically segmenting input document images into regions of black text, white space, and image content. A set of scanned training documents representing the range of text and images to be processed is coarsely tagged to classify regions by content type. The training images are divided into bricks, parameters describing individual brick features are evaluated, and the bricks are classified according to the parameter values. A classification map that relates parameter values to classification codes describing content type is constructed by generating linear equations separating a parameter space into parameter regions along classification boundaries. After training, input documents are scanned and divided into bricks, and brick parameters are converted into an index into the classification map, to classify document regions by content.

Abstract: According to a conventional image classification device that extracts a feature from an image and classifies the image with use of the extracted feature, in the case where one image and another one image, which are included in an image group, each have a different feature, the one image and the other one image might be each classified into a different category. In order to solve this problem, an image classification device relating to the present invention calculates, with respect to each of persons appearing in a plurality of images included in an image group which have been photographed with respect to one event, a main character degree that is an index indicating an important degree in units of image groups, and classifies the images into any one of different classification destination events in units of image groups based on the calculated main character degrees.

Abstract: An image processing apparatus includes an image retrieving unit that retrieves an image including a symbol, a noise detecting unit that detects noise of the image, a comparative image retrieving unit that retrieves a comparative image that is to be compared with a detection region of the image detected as the noise by the noise detecting unit, and a removing unit that, in accordance with comparison results of the detection region with the comparative image, removes from the image one portion of the detection region excluding the other portion of the detection region where at least part of the symbol included in the image is detected as the noise.

Abstract: An image processing apparatus includes a first acquiring unit that acquires an image to be processed; a setting unit that sets multiple partial image areas in the image to be processed; a second acquiring unit that acquires a first classification result indicating a possibility that an object of a specific kind is included in each of the multiple partial image areas; and a generating unit that generates a second classification result indicating a possibility that the object of the specific kind is included in the image to be processed on the basis of the first classification result of each of the multiple partial image areas.

Abstract: Identification of objects in images. All images are scanned for key-points and a descriptor is computed for each region. A large number of descriptor examples are clustered into a Vocabulary of Visual Words. An inverted file structure is extended to support clustering of matches in the pose space. It has a hit list for every visual word, which stores all occurrences of the word in all reference images. Every hit stores an identifier of the reference image where the key-point was detected and its scale and orientation. Recognition starts by assigning key-points from the query image to the closest visual words. Then, every pairing of the key-point and one of the hits from the list casts a vote into a pose accumulator corresponding to the reference image where the hit was found. Every pair key-point/hit predicts specific orientation and scale of the model represented by the reference image.

Abstract: A system and method of processing an image of a document using an optical character recognition process is disclosed. In one example, the method comprises acts of extracting, by a computer system, a plurality of recognizable units from the document, extracting, by the computer system, a plurality of features from the plurality of recognizable units, separating, by the computer system, the plurality of recognizable units, based on the plurality of extracted features into a plurality of fragments having at least one fragment type, determining a distance metric between the plurality of recognizable units, based on the plurality of extracted features, and classifying, by the computer system, the plurality of recognizable units into a plurality of clusters based on the distance metric, each cluster including a set of recognizable units associated with a shape classification.

Abstract: Systems and methods are provided to facilitate architectural modeling. In one aspect, repetitive patterns are automatically detected and analyzed to generate modeled structural images such as building facades. In another aspect, structural symmetry is analyzed to facilitate architectural modeling and enhanced image generation.

Abstract: Provided are an age estimation apparatus, an age estimation method, and an age estimation program capable of obtaining a recognition result closely matching the result perceived by human. An age estimation apparatus 10 for estimating an age of a person on image data includes a dimension compressor 11 for applying dimension compression to the image data to output low dimensional data; and an identification device 12 for estimating an age of a person on the basis of a learning result using a feature amount contained in the low dimensional data, wherein a parameter used for the dimension compression by the dimension compressor 11 and the feature amount used for age estimation by the identification device 12 are set on the basis of a result of an evaluation of a generalization capability using a weighting function that shows a degree of seriousness of an age estimation error for every age, and learning of the identification device 12 is performed on the basis of the weighting function.

Abstract: Techniques are disclosed for performing robust feature matching for visual search. An apparatus comprising an interface and a feature matching unit may implement these techniques. The interface receives a query feature descriptor. The feature matching unit then computes a distance between a query feature descriptor and reference feature descriptors and determines a first group of the computed distances and a second group of the computed distances in accordance with a clustering algorithm, where this second group of computed distances comprises two or more of the computed distances. The feature matching unit then determines whether the query feature descriptor matches one of the reference feature descriptors associated with a smallest one of the computed distances based on the determined first group and second group of the computed distances.

Abstract: A system for automatically extracting or isolating structures or areas of interest (e.g., built-up structures such as buildings, houses, shelters, tents; agricultural areas; etc.) from HR/VHR overhead imagery data by way of making as little as a single pass through a hierarchical data structure of input image components (where pixels are grouped into components based on any appropriate definition or measure of dissimilarity between adjacent pixels of the input image) to identify candidate components (e.g., possible structures of interest) free of necessarily having to re-iterate the same operator configured with different threshold parameters for a plurality of values.

Abstract: A computing system for automatically identifying individual regions in a digital image that include a human face, forming combined padded regions and automatically evaluating each of the regions including calculating a fitness score for each of the combined padded regions and ignoring at least one of the combined padded regions whose fitness score is below a known threshold.

Abstract: The disclosure relates to a system and a method for generating clothing feature data representative of at least one clothing feature of a piece of clothing being worn by the person in a set of images, and training a discriminative clothing classifier using the clothing feature data to provide a personal clothing model that corresponds to the piece of clothing. The personal clothing model can be used to identify additional images in which the person appears.

Abstract: A server is configured to identify items of visual content; assign the identified items to clusters; assign the identified items, of a particular cluster, to layers; generate a document that includes information regarding the identified items arranged according to the clusters and the layers; and provide the document. The document may include, for the particular cluster, a first item, corresponding to one of the identified items assigned to a first layer, and second items, corresponding to multiple ones of the identified items assigned to a second layer. The size of the first item may be greater than a size of each of the second items. The first item may be presented on top of the second items, within the document, to at least partially cover the second items, where at least one of the second items is at least partially visible within the document.

Abstract: An apparatus for providing pattern detection may include a processor. The processor may be configured to iteratively test different models and corresponding scales for each of the models. The models may be employed for modeling parameters corresponding to a visually detected data. The processor may be further configured to evaluate each of the models over a plurality of iterations based on a function evaluation of each of the models, select one of the models based on the function evaluation of the selected one of the models, and utilize the selected one of the models for fitting the data.

Abstract: Methods and apparatus to monitor environments are disclosed. An example method includes analyzing a plurality of three-dimensional data points having respective depth values representative of distances between a sensor and respective objects of an environment; when a first set of the three-dimensional data points has a first depth value less than a threshold, executing a first type of recognition analysis on a first area of the environment corresponding to the first set of the three-dimensional data points; and when a second set of the three-dimensional data points has a second depth value greater than the threshold, executing a second type of recognition analysis different than the first type of recognition analysis on a second area of the environment corresponding to the second set of the three-dimensional data points.

Abstract: The present disclosure relates to systems and methods for classifying videos based on video content. For a given video file including a plurality of frames, a subset of frames is extracted for processing. Frames that are too dark, blurry, or otherwise poor classification candidates are discarded from the subset. Generally, material classification scores that describe type of material content likely included in each frame are calculated for the remaining frames in the subset. The material classification scores are used to generate material arrangement vectors that represent the spatial arrangement of material content in each frame. The material arrangement vectors are subsequently classified to generate a scene classification score vector for each frame. The scene classification results are averaged (or otherwise processed) across all frames in the subset to associate the video file with one or more predefined scene categories related to overall types of scene content of the video file.

Abstract: Systems and methods for clustering a plurality of feature vectors. A hierarchical clustering algorithm is performed on the plurality of feature vectors to provide a plurality of clusters and a cluster similarity measure for each cluster representing the quality of the cluster. Each cluster of the plurality of clusters with a cluster similarity measure meeting a threshold value is accepted. A clustering algorithm is performed on each cluster that fails to meet the threshold value to provide a set of subclusters each having an associated cluster similarity measure. Each subcluster having a cluster similarity measure meeting the threshold value is accepted.

Abstract: A computer implemented method and apparatus for automatically identifying a representative image for an image group. The method comprises dividing an image group into one or more clusters based on an average time gap of the image group, wherein the images in the image group are in sequential timestamp order wherein the average time gap is calculated using a time span calculated from the timestamp of a first image in the image group to the timestamp of a last image in the image group; recursively dividing a largest cluster in the one or more clusters to determine a resultant cluster, wherein the resultant cluster comprises no time gaps larger than the average time gap of the resultant cluster; and identifying a representative image from the resultant cluster as an image representative for the image group.

Abstract: A method for effectively performing local image similarity measurement is proposed. A system equipped with such a method for effectively performing an image processing task includes an image processor that performs an intermediate-results calculation procedure to calculate intermediate result values that are based upon corresponding pixels of a target patch and one or more similar patches. The image processor typically moves the target patch of the intermediate-results calculation to different locations in a raster order or some other organized order. The image processor then performs an intermediate-results combination procedure by calculating appropriate statistics of the intermediate result values to produce processed pixel values. A processor device typically controls the image processor to effectively perform the image processing tasks including, but not limited to, demosaicing and denoising.

Abstract: Provided is a data processor for generating three-dimensional image data from two-dimensional original image data, the three-dimensional image data including depth value, the apparatus comprising: a first clustering processor for dividing the two-dimensional original image data into a first plurality of clusters based on brightness; a three-dimensional data generating unit for setting a predetermined direction as a brighter-to-darker direction, and for generating information, as first depth information, such that depth value for a first cluster among the plurality of clusters is set to be larger than depth value for a second cluster which neighbors the first cluster and is located nearer to a starting point of the brighter-to-darker direction than the first cluster where the brightness of the first cluster is darker than the brightness of the second cluster.

Abstract: 3D models often have a large number of small to medium sized connected components, with small numbers of large triangles, often with arbitrary connectivity. The efficiency of compact representation of large multi-component 3D models can be improved by detecting and representing similarities between components thereof, even if the components are not exactly equal. The invention uses displacement maps for encoding two or more different but similar geometry patterns differentially, based on clustering and a cluster representative surface. A method for encoding a plurality of geometry patterns comprises detecting and encoding identical copies of geometrical patterns, detecting and clustering similar geometry patterns, and detecting partial similarity. The detecting partial similarity comprises generating a cluster representative surface, generating for at least one clustered geometry pattern a displacement map, and encoding the common surface and the displacement maps.

Abstract: According to an embodiment, a recognition device includes a generation unit to select, plural times, groups each including learning samples from a storage unit, learn a classification metric for classifying the groups selected in each selection, and generate an evaluation metric including the classification metrics; a transformation unit to transform a first feature value of an image including an object into a second feature value using the evaluation metric; a calculation unit to calculate similarities of the object to categories in a table using the second feature value and reference feature values; and a registration unit to register the second feature value as the reference feature value in the table associated with the category of the object and register the first feature value as the learning sample belonging to the category of the object in the storage unit. The generation unit performs the generation again.

Abstract: Implementations for identifying duplicate images in an image space are described. An image space is partitioned into a plurality of coarse clusters based on signatures of the images within the image space. The signatures are determined from compact descriptors of the images. Refined clusters that include one or more images of an individual coarse cluster are created based on pair-wise comparisons of the compact descriptors of images in the coarse cluster, and the refined clusters are identified as sets of duplicate images. The refined clusters are grown by searching in similar coarse clusters for images to add to the refined clusters.

Abstract: A method is provided that includes identifying a plurality of data sets, each data set is associated with a distribution model and each data set is associated with an image having a first noise level. The method includes partitioning the data sets into a plurality of groups and generating a best representative estimate for each group, the estimate is associated with a second noise level that is less than the first noise level. The method further includes annotating each group and receiving an input data set. The method includes assigning the input data set to a group and annotating the input data set according to that group's annotation.

Abstract: A method and system augments a broadcast by detecting an event that occurs while viewing a broadcast data by at least one user; when the event is detected, automatically capturing feedback data with a human computer interaction (HCI) capturing device (HCICD) from the at least one user, the feedback data being indicative of a measurement of the user from viewing the event; generating a feature data as a function of the feedback data; including the feature data in the broadcast data to generate an augmented broadcast data; and transmitting the augmented broadcast data.

Abstract: A method for identifying a set of key video frames from a video sequence comprising extracting feature vectors for each video frame and applying a group sparsity algorithm to represent the feature vector for a particular video frame as a group sparse combination of the feature vectors for the other video frames. Weighting coefficients associated with the group sparse combination are analyzed to determine video frame clusters of temporally-contiguous, similar video frames. The video sequence is segmented into scenes by identifying scene boundaries based on the determined video frame clusters.

Abstract: Systems, methods, and computer storage mediums are provided for matching multiple photographs together. An example method includes receiving a first collection of photographic images. The photographic images in the first collection are clustered into one or more composite sets of photographic images based on a comparison of the metadata associated with each photographic image in the first collection meeting a predetermined similarity threshold. An image overlap is determined between each photographic image within each of the one or composite sets of photographic images. When the image overlap exceeds a predetermined image overlap threshold, a pair of photographic images are matched, for all of the photographic images within each composite set of photographic images to form one or more composite images.

Abstract: A social network application may identify images having common links between a first user's image collection and a second user's image collection. The common links may be identified through metadata or similar portions of the images. Using the first user's image collection, elements of interest may be identified and compared to a second user's image collection to find matches. When matches are found, the results may be selected from groups of results to show a diverse set of matches. The user may be presented with options to select and add matched images to the user's collection, as well as to browse more images that match one or more of the groups.

Abstract: A computer-implemented technique can receive, at a computing device including one or more processors, a plurality of photos. The technique can extract quality features and similarity features for each of the plurality of photos and can obtain weights for the various quality features and similarity features based on an analysis of a reference photo collection. The technique can generate a quality metric for each of the plurality of photos and can generate a similarity matrix for the plurality of photos by analyzing the various quality features and similarity features and using the obtained weights. The technique can perform joint global maximization of photo quality and photo diversity using the quality metrics and the similarity matrix in order to select a subset of the plurality of photos having a high degree of representativeness. The technique can then store the subset of the plurality of photos in a memory.

Abstract: A collection of photos is organized by arranging a limited number of clusters of the photos on a predefined topology, so that similar photos are placed in the same cluster or a nearby cluster. Similarity is measured in attribute space. The attributes may include automatically recognized facial expression attributes.

Abstract: A method for merging face clusters includes analyzing a set of digital images, grouping instances of faces within the set of digital images into a set of face clusters, each of the face clusters corresponding to a particular person, and determining a probability that a person associated with a first face cluster from the set of face clusters is the same person associated with a second face cluster of the set of face clusters. The probability is based on both a social similarity between the first face cluster and the second face cluster in addition to a facial similarity between the first face cluster and the second face cluster.

Abstract: Systems and methods for generating a visual vocabulary build a plurality of visual words via unsupervised learning on set of features of a given type; decompose one or more visual words to a collection of lower-dimensional buckets; generate labeled image representations based on the collection of lower dimensional buckets and labeled images, wherein labels associated with an image are associated with a respective representation of the image; and iteratively select a sub-collection of buckets from the collection of lower-dimensional buckets based on the labeled image representations, wherein bucket selection during any iteration after an initial iteration is based at least in part on feedback from previously selected buckets.

Abstract: The classification and segmentation system of the current invention makes use of information from pixels of an image, namely the magnitude of the pixels, to run specific analytics to classify and segment the image pixels into different groups. This invention includes a system for processing an image, the system including an input device, a processor, a memory and a monitor. The input device is configured to receive image data, where the image data includes pixels and each pixel has a magnitude. The memory has instructions stored in it that, when executed by the processor, cause the processor to run calculations. The calculations include: calculating the log-magnitudes from the magnitudes of at least a plurality of the pixels, calculating standard deviations of the log-magnitudes for subsets of the plurality of pixels and compute an integral of the standard deviations over a desired range. The pixels are classified into different groups based on a value of the integral relative to one or more integral values.

Abstract: A hierarchy machine may be configured as a clustering machine that utilizes local feature embedding to organize visual patterns into nodes that each represent one or more visual patterns. These nodes may be arranged as a hierarchy in which a node may have a parent-child relationship with one or more other nodes. The hierarchy machine may implement a node splitting and tree-learning algorithm that includes hard-splitting of nodes and soft-assignment of nodes to perform error-bounded splitting of nodes into clusters. This may enable the hierarchy machine, which may form all or part of a visual pattern recognition system, to perform large-scale visual pattern recognition, such as font recognition or facial recognition, based on a learned error-bounded tree of visual patterns.

Abstract: Systems and methods of bad pixel cluster detection are disclosed. In a particular embodiment, a system is disclosed that includes a bad pixel correction module coupled to receive image data and adapted to perform a bad pixel cluster detection process. The bad pixel correction module includes logic to determine whether two test pixels have values that exceed a representative value of a group of surrounding pixels by more than a threshold amount. The threshold amount is determined via a table lookup.

Abstract: Methods, systems, and apparatus, including computer programs encoded on a computer storage medium, for graphical overlay object translation. One of the methods includes receiving a first plurality of first feature points, each first feature point being associated with a plurality of feature descriptors and a respective location on the first digital image. The method includes receiving a second plurality of second feature points, each second feature point being associated with a plurality of feature descriptors and a respective location on the second digital image. The method includes determining the translation offset for the second digital image from the first digital image by matching locations of the first feature points with locations of the second feature points without regard to the feature descriptors.

Abstract: A method of compiling an image database for a three-dimensional object recognition including the steps of: when a plurality of images each showing an object from different viewpoint are inputted, extracting local features from each of the images, and expressing the local features using feature vectors; forming sets of the feature vectors, each set representing a same part of the object from a series of the viewpoints, and generating subspaces, each subspace representing a characteristic of each set; and storing each subspace to the image database with an identifier of the object to perform a recognition process that is realized by the steps of: when at least one image of an object is given as a query, extracting query feature vectors; determining the subspace most similar to each query feature vector; and executing a counting process to the identifiers to retrieve an object most similar to the query.

Abstract: Methods and systems for analysis of image data generated from various reference points. Particularly, the methods and systems provided are useful for real time analysis of image and sequence data generated during DNA sequencing methodologies.

Abstract: A computer implemented method identifying calcification in a patient image data set including blood vessels.

Abstract: A method for recognition of a predetermined pattern in an image data set recorded by a device for recording of at least two electromagnetic frequency spectra is provided. A first difference value is formed for the image points of the selected area as a function of a difference between a data vector of a corresponding image point and a first reference data vector. A second difference value is formed for an image point of a selected area as a function of a difference between the data vector of this image point and a second reference data vector. A predetermined pattern is recognized when it is determined at least one pattern correlation quantity is below a predetermined threshold value and a local minimum is present.

Abstract: Disclosed are various embodiments for performing an analysis on images of a product packaging. Capture of at least one image of at least one side of a packaging in initiated. An image analysis is performed on the at least one image. Product attributes are detected based at least upon the at least one image analysis and associated with the product in a data store.

Abstract: A classifier training system trains unified classifiers for categorizing videos representing different categories of a category graph. The unified classifiers unify the outputs of a number of separate initial classifiers trained from disparate subsets of a training set of media items. The training process takes into account the relationships that exist between the various categories of the category graph by relating scores associated with related categories, thus enhancing the accuracy of the unified classifiers.

Abstract: An image-based georeferencing system comprises an image receiver, an image identification processor, a reference feature determiner, and a feature locator. The image receiver is configured for receiving a first image for use in georeferencing. The image comprises digital image information. The system includes a communicative coupling to a georeferenced images database of images. The image identification processor is configured for identifying a second image from the georeferenced images database that correlates to the first image. The system includes a communicative coupling to a geographic location information system. The reference feature determiner is configured for determining a reference feature common to both the second image and the first image. The feature locator is configured for accessing the geographic information system to identify and obtain geographic location information related to the common reference feature.