Abstract: A system, method, and computer program product are provided for generating a subset of a low discrepancy sequence. In use, a low discrepancy sequence is identified. Additionally, a threshold value is determined. Further, a single dimension of the low discrepancy sequence is selected. Further still, for each element included within the low discrepancy sequence, the selected single dimension is compared to the determined threshold value. Also, a subset of the low discrepancy sequence is generated, based on the comparing.

Abstract: A method of detecting recurring events in a digital image collection taken over a pre-determined period of time is disclosed. The method uses a processor for analyzing the digital image collection to produce a two-dimensional representation of the distribution of image capture activity over time and detecting recurring events by identifying spatial clusters in the two-dimensional representation.

Abstract: Foreground and background regions of a digital image of a scene are distinguished from each other automatically. Foreground objects are identified in a binary image map that distinguishes between foreground pixels and background pixels. From the foreground objects, a primary foreground object is identified. Within the identified primary foreground object, a head region of the primary foreground object is located. Within the head region, patterns of foreground pixels and background pixels that are indicative of a head crown region are identified. Within the head crown region, pixels identified as background pixels that actually show portions of the primary foreground object are converted to foreground pixels, thus improving the accuracy of the binary image map.

Abstract: Representative images are selected for display from a group. A dissimilarity measure is selected, by which to compute dissimilarities between features of respective images in the group. Dissimilarities between the images in the group are computed, based on the selected dissimilarity measure. A relative dissimilarity between each image and the other images in the group is determined, based on the relative dissimilarity between the feature of the image and the features of the other images in the group. An image in the group is selected as a representative image for display, using the relative dissimilarity of the image as a probability bias in the selection.

Abstract: There is disclosed a quick and efficient method for analyzing a segment of video, the segment of video having a plurality of frames. A reference portion is acquired from a reference frame of the plurality of frames. Plural subsequent portions are then acquired from a corresponding subsequent frame of the plurality of frames. Each subsequent portion is then compared with the reference portion, and an event is detected based upon each comparison. There is also disclosed a method of optimizing video including selectively storing, labeling, or viewing video based on the occurrence of events in the video. Furthermore, there is disclosed a method for creating a video summary of video which allows a used to scroll through and access selected parts of a video. The methods disclosed also provide advancements in the field of video surveillance analysis.

Abstract: 3D models of the engineering class usually have a large number of connected components, with small numbers of large triangles, often with arbitrary connectivity. To enable compact storage and fast transmission of large 3D mesh models, an efficient compression strategy specially designed for 3D mesh models is provide. A method for encoding a 3D mesh model comprises determining and clustering repeating components, normalizing the components, wherein scaling factors are clustered and orientation axes are clustered, encoding the connected components using references to the clusters, and entropy encoding the connected components.

Abstract: A database of images may be accessed. A feature set may be computed for each image, respectively. Each feature set includes feature integers quantized from interest points of a corresponding image. An initial set of clusters of the feature sets is found based on min hashes of the feature sets. Given the clusters of feature sets, descriptors for each of the clusters are computed, respectively, by selecting feature integers from among the feature sets in a cluster. The clusters are then refined by comparing at least some of the feature sets with at least some of the cluster descriptors, and based on such comparing adding some of the feature sets to clusters whose feature descriptors have similarity to the feature sets.

Abstract: A method and system for performing gesture recognition of a vehicle occupant employing a time of flight (TOF) sensor and a computing system in a vehicle. An embodiment of the method of the invention includes the steps of receiving one or more raw frames from the TOF sensor, performing clustering to locate one or more body part clusters of the vehicle occupant, calculating the location of the tip of the hand of the vehicle occupant, determining whether the hand has performed a dynamic or a static gesture, retrieving a command corresponding to one of the determined static or dynamic gestures, and executing the command.

Abstract: A technology is described for performing structure from motion for unordered images of a scene with multiple object instances. An example method can include obtaining a pairwise match graph using interest point detection for obtaining interest points in images of the scene to identify pairwise image matches using the interest points. Multiple metric two-view and three-view partial reconstructions can be estimated by performing independent structure from motion computation on a plurality of match-pairs and match-triplets selected from the pairwise match graph. Pairwise image matches can be classified into correct matches and erroneous matches using expectation maximization to generate geometrically consistent match labeling hypotheses and a scoring function to evaluate the match labeling hypotheses. A structure from motion computation can then be performed on the subset of match pairs which have been inferred as correct.

Abstract: Systems and methods are disclosed for identifying objects captured by a depth camera by condensing classified image data into centroids of probability that captured objects are correctly identified entities. Output exemplars are processed to detect spatially localized clusters of non-zero probability pixels. For each cluster, a centroid is generated, generally resulting in multiple centroids for each differentiated object. Each centroid may be assigned a confidence value, indicating the likelihood that it corresponds to a true object, based on the size and shape of the cluster, as well as the probabilities of its constituent pixels.

Abstract: Image processing includes receiving a plurality of images to be grouped; dividing the plurality of images into a plurality of groups wherein the images in the same group share the same main color; receiving a given image; searching among the plurality of groups for a result group having the same main color as the main color of the given image; extracting a plurality of image features of the given image and the images in the result-group; comparing the image features of the given image with the image features of each image in the result group; and identifying a near-duplicate image from the result group that meets a preset near-duplicate image determining condition.

Abstract: Methods, apparatuses, and systems for grouping digital media items based on shared features. Multiple digital images are received. Metadata about the digital images is obtained either by analyzing the digital images or by receiving metadata from a source separate from the digital images or both. The obtained metadata is analyzed by data processing apparatus to identify a common feature among two or more of the digital images. A grouping of the two or more images is formed by the data processing apparatus based on the identified common feature.

Abstract: A method of automatically classifying images in a consumer digital image collection, includes generating an event representation of the image collection; computing global time-based features for each event within the hierarchical event representation; computing content-based features for each image in an event within the hierarchical event representation; combining content-based features for each image in an event to generate event-level content-based features; and using time-based features and content-based features for each event to classify an event into one of a pre-determined set of semantic categories.

Abstract: An information processing apparatus, which creates a tree structure used by a recognition apparatus which recognizes specific information using the tree structure, including a memory unit which stores data including the information to be recognized and data not including the information so as to correspond to a label showing whether or not the data includes the information, a recognition device which recognizes the information and outputs a high score value when the data including the information is input, and a grouping unit which performs grouping of the recognition devices using a score distribution obtained when the data is input into the recognition devices.

Abstract: A method for forming a video summary for a digital video having a time sequence of video frames, comprising using a processor to perform the steps of: determining a set of key video frames for the digital video; ranking the key video frames responsive to a predefined criterion; forming key video snippets corresponding to one or more highest-ranked key video frames according to a predefined set of criteria, including a criterion which specifies the total time duration for the video summary and a criterion which specifies the minimum time duration for each of the key video snippets; assembling the key video snippets to form a video summary; and storing a representation of the video summary in a processor-accessible memory.

Abstract: Provided is a face clustering device that detects a face included in an image, detects a direction of the detected face, detects, taking into account the detected direction of the face, a face with a similar feature and forms a collection of pieces of face information showing a feature of this face, narrows down, for each collection of pieces of face information which has been formed, the number of pieces of face information to a number set in advance for each face direction and sets each collection of pieces of face information for which the number has been narrowed down as a unit group, and performs, with the set unit group as a unit, clustering based on pieces of face information included in each unit group.

Abstract: A system and method for tagging an image of an individual in a plurality of photos is disclosed herein. A feature vector of an individual is used to analyze a set of photos on a social networking website such as www.facebook.com to determine if an image of the individual is present in a photo of the set of photos. Photos having an image of the individual are tagged preferably by listing a URL or URI for each of the photos in a database.

Abstract: A method for determining key video frames for a digital video having a time sequence of video frames, comprising using a processor to perform the steps of: analyzing the digital video to determine an importance value as a function of time; forming a warped time representation by temporal relocation of the video frames responsive to the importance value as a function of time; subdividing the warped time digital video sequence representation into a set of equal intervals; selecting a key video frame for each interval by analyzing the video frames within each interval; and storing an indication of the key video frames in a processor-accessible memory.

Abstract: In a method of automatically creating a scalable relevance ordered representation of an image collection, the images in the image collection are classified into a plurality of clusters based upon a feature of the images. In addition, respective relevance levels of the images contained in each of the plurality of clusters are determined and the images in each of the plurality of clusters are ordered according to the relevance levels. Moreover, the images from the ordered plurality of clusters are arranged according to a predefined arrangement process to create the scalable relevance ordered representation of the image collection.

Abstract: A range map of a visual scene generated by a stereo vision and associate image processing system, and is filtered to remove objects beyond a region of interest and for which a collision is not possible, and to remove an associated road surface. Objects clustered in range bins are separated by segmentation. A composite range map is generated using principale components analysis and processed with a connected-components sieve filter. Objects are identified using one or more of a harmonic profile and other features using an object recognition processor using a combination of inclusive, exclusive and harmonic networks to generate a classification metric.

Abstract: Methods for selecting metrics for substrate classification, and apparatus to perform such methods. The methods include determining a value of a metric from an image of a substrate sample for each substrate sample of a plurality of substrate samples, wherein the metric is indicative of a surface texture of each substrate sample and iteratively assigning substrate samples of the plurality of substrate samples to an aggregate of a particular number of aggregates in response to a value of the metric for each substrate sample until a convergence of clustering is deemed achieved, then determining an indication of cluster tightness of the particular number of aggregates. The methods further include selecting or ignoring the metric for substrate classification in response to the indication of cluster tightness of the particular number of aggregates.

Abstract: In one implementation, a computer-implemented method includes receiving, at a computer system, an electronic photograph; and identifying, by the computer system, a plurality of users of depicted in the electronic photograph. The computer-implemented method can also include designating a group of users based on the identified plurality of users; and providing information regarding the designated group of users to one or more computing devices associated with one or more of the plurality of users.

Abstract: The present disclosure discloses a method and apparatus for creating a sample image index table, filtering image, and searching image, to improve accuracy of monitoring images. A method for image filtering comprises: establishing a sample image index table; extracting regional characteristics from an image to be searched; clustering the regional characteristics of the image to be searched into corresponding nodes; obtaining a corresponding sample image identification by indexing the sample image index table using node identifications of the nodes of the image to be searched; determining a number of duplicate nodes between the image to be searched and the sample image; obtaining a degree of similarity of the image to be searched based on a number of the nodes of the image to be searched and a number of the nodes of the sample image; and filtering out the image to be searched when a degree of similarity between the image to be searched and the sample image exceeds a similarity threshold.

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 employed to present image from an event. A plurality of images from the event are received and one or more clusters of images are created, wherein each cluster of images has a similarity greater than a predetermined threshold. A density value of the data distribution within each cluster is estimated and at least one local maximum associated with each cluster is identified via a density function. At least one image from each cluster is selected, wherein each image is a candidate for the presentation. A layout is created to present the images selected.

Abstract: An information processing apparatus includes: a distinguishing unit which, by using an ensemble classifier, which includes a plurality of weak classifiers outputting weak hypotheses which indicates whether a predetermined subject is shown in an image in response to inputs of a plurality of features extracted from the image, and a plurality of features extracted from an input image, sequentially integrates the weak hypotheses output by the weak classifiers in regard to the plurality of features and distinguishes whether the predetermined subject is shown in the input image based on the integrated value. The weak classifier classifies each of the plurality of features to one of three or more sub-divisions based on threshold values, calculates sum divisions of the sub-divisions of the plurality of features as whole divisions into which the plurality of features is classified, and outputs, as the weak hypothesis, a reliability degree of the whole divisions.

Abstract: A clustering procedure for grouping a set of images is selected from amongst plural clustering procedures. A predetermined categorization of objects such as images is input, and image features are extracted from each image in the set of images. A comparison measure is determined, by which to compare respective features of the set of images. Respective features between the images in the set of images are compared, based on the comparison measure, and a group of measures representing the differences between features of respective images is output. The plural clustering procedures are applied to the set of images to cluster the images based in part on the calculated group of measures. A clustering quality score is generated for each clustering procedure, based on the clusters created by the clustering procedure and the predetermined categorization of images. The clustering procedure with a high clustering quality score is selected.

Abstract: A method and system for clustering images, comprising detecting faces in respective images to generate face data, generating a first cluster of images using the face data, the first cluster comprising images with a common face and representing a corresponding person, generating a second cluster of images using clothes data representing a set of clothing signatures, the second cluster comprising images with a common set of clothes, and using the first and second clusters to link an image of the person to the clusters in order to generate a third cluster for the person.

Abstract: A system and a method are provided for determining an estimated age of an individual of interest based on images in an image collection. An example system includes a memory for storing computer executable instructions, and a processing unit for accessing the memory and executing the computer executable instructions. The computer executable instructions include an age class estimator to classify a plurality of images of the individual into age classes, each age class corresponding to an interval of age, and each image having a known time stamp, a probability determination engine to determine, for each age class, a value of class probability that an image in the collection falls within the age class, an age determination engine to determine a transition time based on the values of class probability and the known time stamp, and to determine the estimated age of the individual based on the determined transition time.

Abstract: A system and method are disclosed for detecting and labeling places recognized in a video stream using change-points detection. The system includes a segmentation module and a label learning module. The segmentation module is configured to receive a video stream comprising multiple digital representations of images. The video stream is represented by a measurement stream comprising one or more image histograms of the video stream. The segmentation module segments the measurement stream into multiple segments corresponding to place recognized in the videos stream. The segmentation module detects change-points of the measurement stream and computes probability distributions of the segments over multiple pre-learned place models. The label generation module is configured to generate place labels for the places recognized by the place models.

Abstract: 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.

Abstract: A method and system for clustering the pixels of a multispectral image is provided. A clustering system computes a maximum spectral similarity score for each pixel that indicates the similarity between that pixel and the most similar neighboring. To determine the maximum similarity score for a pixel, the clustering system generates a similarity score between that pixel and each of its neighboring pixels and then selects the similarity score that represents the highest similarity as the maximum similarity score. The clustering system may apply a filtering criterion based on the maximum similarity score so that pixels with similarity scores below a minimum threshold are not clustered. The clustering system changes the current pixel values of the pixels in a cluster based on an averaging of the original pixel values of the pixels in the cluster.

Abstract: A system and method are disclosed for detecting and labeling places in a video stream using change-points detection. The system comprises a place label generation module configured to assign place labels probabilistically to places in the video stream based on the measurements of the measurement stream representing the video. For each measurement in the segment, the place label generation module classifies the measurement by computing the probability of the measurement being classified by a learned Gaussian Process classifier. Based on the probabilities generated with respect to all the measurements in the segment, the place label generation module determines the place label for the segment. In cases where a Gaussian Process classifier cannot positively classify a segment, the place label generation module determines whether the segment corresponds to an unknown place based on the perplexity statistics of the classification and a threshold value.

Abstract: An apparatus and method for generating additional information about moving picture content, including: comparing image feature information about each image frame in moving picture content with image feature information about each image frame in web information, searching for an image frame in the moving picture content, the image frame matching the image frame in the web information, determining location information about the found image frame in the moving picture content, and generating additional information by use of the determined location information and the web information.

Abstract: A clustering processing apparatus comprises: N clustering units that group samples included in the data block into clusters, each clustering unit sequentially taking each sample as a target, grouping the target sample into one of the clusters within the data block, storing cluster information including identification on each cluster into which the samples are grouped within the data block, and storing sample assignment information indicating the cluster to which the target sample belongs; a cluster information transferring unit that selects cluster information on a cluster to be integrated from the cluster information when a predetermined condition is met, and transfers the selected cluster information to a third storage unit; and an updating unit that integrates clusters selected based on the cluster information stored in the third storage unit into an integrated cluster, and updates the sample assignment information based on information of the integrated clusters.

Abstract: A method of partitioning a weighted combinatorial graph representative of a dataset consists of the steps of generating a generalized Laplacian matrix corresponding to the combinatorial graph, computing the eigenstructure of the generalized Laplacian matrix, determining if an end criterion is satisfied using the eigenstructure, and if the end criterion is not satisfied, calculating new values for at least some of the plurality of weighting factors using the eigenstructure, updating the combinatorial graph with the new values for at least some of the weighting factors, and returning to the generating step.

Abstract: Various methods for visual search stability are provided. One example method includes determining a plurality of image matching distances for a captured object depicted in a video frame, where each image matching distance being indicative of a quality of a match between the captured object and a respective object match result. The example method further includes including, in a candidate pool, an indication of the object match results having image matching distances in a candidate region, discarding the object match results having image matching distances in a non-candidate region, and analyzing the object match results with image matching distances in a potential candidate region to include, in the candidate pool, indications of select object match results with image matching distances in the potential candidate region. Similar and related example methods and example apparatuses are also provided.

Abstract: An exemplary method includes receiving stroke information for a partially written East Asian character, the East Asian character representable by one or more radicals; based on the stroke information, selecting a radical on a prefix tree wherein the prefix tree branches to East Asian characters as end states; identifying one or more East Asian characters as end states that correspond to the selected radical for the partially written East Asian character; and receiving user input to verify that one of the identified one or more East Asian characters is the end state for the partially written East Asian character. In such a method, the selection of a radical can occur using radical-based hidden Markov models. Various other exemplary methods, devices, systems, etc., are also disclosed.

Abstract: Iconic images for a given object or object category may be identified in a set of candidate images by using a learned probabilistic composition model to divide each candidate image into a most probable rectangular object region and a background region, ranking the candidate images according to the maximal composition score of each image, removing non-discriminative images from the candidate images, clustering highest-ranked candidate images to form clusters, wherein each cluster includes images having similar object regions according to a feature match score, selecting a representative image from each cluster as an iconic image of the object category, and causing display of the iconic image. The composition model may be a Naïve Bayes model that computes composition scores based on appearance cues such as hue, saturation, focus, and texture. Iconic images depict an object or category as a relatively large object centered on a clean or uncluttered contrasting background.

Abstract: A method and a device for people group detection, relating to the field of image processing includes acquiring at least one corner and foreground region in video data; computing, according to said corner and foreground region, to obtain at least one cluster; constructing at least one region of people group according to said cluster. The device includes an acquisition module, a clustering module, and a construction module. Automatic people group detection is realized that is independent of the location detection of people and can be applied to any scene including complicated ones, and thus user demands can be better satisfied.

Abstract: Automated localization of a valid area of a blood smear and, thus, localization requiring less effort and being more objective is enabled in that a picture of the blood smear pixels are classified at least into first pixels, which represent blood cells, and second pixels, which do not represent the blood cells, and the valid area is then found on the basis of a local frequency of pixel clusters of at least Amin first pixels, Amin being a minimum threshold for a number of first pixels of a pixel cluster, and a local average size of the pixel clusters for laterally distributed areas of the blood smear.

Abstract: An automated system and a method for extracting a region of interest from a digital image are disclosed. The method includes identifying a subset of training images from a larger set of training images, each training image in the set having a respective identified region of interest. The subset is identified based on a measure of similarity between the digital image and the images in the set of training images. At least one region of interest is extracted from the digital image based on an analysis of the identified regions of interest in the subset of training images.

Abstract: An object detection method and system for detecting an object in an image utilizing an adaptive image scanning strategy is disclosed herein. An initial rough shift can be determined based on the size of a scanning window and the image can be scanned continuously for several detections of similar sizes using the rough shift. The scanning window can be classified with respect to a cascade of homogenous classification functions covering one or more features of the object. The size and scanning direction of the scanning window can be adaptively changed depending on the probability of the object occurrence in accordance with scan acceleration. The object can be detected by an object detector and can be localized with higher precision and accuracy.

Abstract: The Target Separation Algorithms (TSAs) are used to improve the results of Automated Target Recognition (ATR). The task of the TSAs is to separate two or more closely spaced targets in Regions of Interest (ROIs), to separate targets from objects like trees, buildings, etc., in a ROI, or to separate targets from clutter and shadows. The outputs of the TSA separations are inputs to ATR, which identify the type of target based on a template database. TSA may include eight algorithms. These algorithms may use average signal magnitude, support vector machines, rotating lines, and topological grids for target separation in ROI. TSA algorithms can be applied together or separately in different combinations depending on case complexity, required accuracy, and time of computation.

Abstract: An image processing apparatus includes a dividing unit, a first extracting unit, a quantizing unit, a generating unit and an image output unit. The dividing unit divides an object image into regions. The first extracting unit extracts image features of the regions generated by the dividing unit. The quantizing unit quantizes the image features extracted by the first extracting unit. The generating unit generates an expected value of an occurrence probability of each topic variable indicating similar images from the image features quantized by the quantizing unit, using a correlation between the image features quantized by the quantizing unit and the topic variables. The image output unit outputs an image of a defective portion in the object image, using the expected values of the occurrence probabilities of the topic variables generated by the generating unit.

Abstract: A method and apparatus for processing images. Clusters of first features identified in a first image are identified. Each cluster in the clusters comprises a first group of features from the first features. A transformation for registering each cluster in the clusters with a corresponding cluster comprising a second group of features from second features identified in a second image is identified using an initial correspondence between the first features in the first image and the second features in the second image. A set of clusters from the clusters of the first features is identified using the transformation identified for each cluster. A final transformation for registering the first image with the second image is identified using the set of clusters.

Abstract: The present invention is a system and method for estimating the age of people based on their facial images. It addresses the difficulty of annotating the age of a person from facial image by utilizing relative age (such as older than, or younger than) and face-based class similarity (gender, ethnicity or appearance-based cluster) of sampled pair-wise facial images. It involves a unique method for the pair-wise face training and a learning machine (or multiple learning machines) which output the relative age along with the face-based class similarity, of the pairwise facial images. At the testing stage, the given input face image is paired with some number of reference images to be fed to the trained machines. The age of the input face is determined by comparing the estimated relative ages of the pairwise facial images to the ages of reference face images.

Abstract: One embodiment is a method for selecting and grouping key points extracted by applying a feature detector on a scene being analyzed. The method includes grouping the extracted key points into clusters that enforce a geometric relation between members of a cluster, scoring and sorting the clusters, identifying and discarding clusters that are comprised of points which represent the background noise of the image, and sub-sampling the remaining clusters to provide a smaller number of key points for the scene.

Abstract: An apparatus for determining a fake image includes an image-acquiring block for acquiring an image captured by and input from a camera; and a background-learning block for learning a background of the image to create a learning background. Further, the apparatus for determining the fake image includes a face extracting-block for extracting a face region of a person to be authenticated when an input image for authentication is transmitted from the camera; and an inter-background comparing block for comparing a present background of an input image with the learning background. Furthermore, the apparatus for determining the fake image includes a motion information-comparing block for extracting motion information in the face region and the present background to compare the same with each other; and a fake image-determining block for determining whether the input image is faked using the compared results of the motion information and the backgrounds.

Abstract: A level set tree feature detection machine is disclosed along with a method for detecting a level set tree feature. At least one pixilated image is provided. An electronic model is generated of the pixilated images. Maximal meaningful nodes for the pixilated images are determined.