Abstract: The present invention relates to a patient interface identification system for identifying a patient interface that is suited for a face (16) of a user (18), comprising: a receiving unit (12) for receiving a test picture (14) including the face (16) of the user (18); a database (22) for storing reference picture including faces of other users, wherein each reference picture is referenced to a patient interface advice; a processing unit (24) for comparing the received test picture (14) with at least a subset of said reference pictures stored in the database (22), wherein comparing said test picture (14) with said subset of reference pictures includes a comparison of image based features of the user's face (16) and the other users' faces; and a user interface (26) for communicating a patient interface advice including information related to a patient interface that is suited for the face (16) of the user (18), which patient interface advice is based on the comparison of said test picture (14) with the subset of

Abstract: Methods are described for presenting in an user interface information regarding the subject faces that will appear in upcoming images. In general, many of the images available to display will be comprised of images containing subject faces. Based on a subject affinity score between the viewer and the subjects, an image affinity is computed. Based on the image affinity scores, images are selected for presentation on the display. As images are displayed, the system analyzes one or more upcoming images to determine information to display. As each image is displayed, subject information comprising the subject's face is presented in an area of the display adjacent to the current image.

Abstract: The present invention relates to a template (10) and a system (50) for collecting data of a face of a subject. The system (50) comprises at least the template (10) and a camera (52). The template (10) comprises at least one computer-detectable element and allows to take a single image of a face of a subject which is positioned in an opening of the template and to derive subject dimensions of the face of the subject based on this single image. The present invention relates also to according methods.

Abstract: Methods, systems, and apparatus, including computer programs encoded on a computer storage medium, for augmenting an interactive session with images. In one aspect, a method includes generating a first linear arrangement of images captured during an interactive session. The images of the first linear arrangement of images can be arranged in order based on a sequence in which the images were captured. The first linear arrangement of images is provided for display. Selection data specifying a selection of an image of the first linear arrangement of images are received. In response to receiving the selection data, a branch point is created at the selected image. The branch point can define a branch from the selected image to a second linear arrangement of images. Additional images captured during the interactive session are received. The second linear arrangement of images is generated that includes the additional images.

Abstract: Improved decision tree training in machine learning is described, for example, for automated classification of body organs in medical images or for detection of body joint positions in depth images. In various embodiments, improved estimates of uncertainty are used when training random decision forests for machine learning tasks in order to give improved accuracy of predictions and fewer errors. In examples, bias corrected estimates of entropy or Gini index are used or non-parametric estimates of differential entropy. In examples, resulting trained random decision forests are better able to perform classification or regression tasks for a variety of applications without undue increase in computational load.

Abstract: An information processing apparatus that obtains intimacy degree information corresponding to identification information of a first person, specifies an extraction period based on the intimacy degree information, and extracts content in the extraction period.

Abstract: Surveillance systems may be found in both private and public spaces. In private spaces, they can be designed to help provide and monitor secure premises. Similarly, public spaces may also use surveillance systems to determine an allocation of public resources. A camera surveillance system according to an embodiment of the invention uses advanced image processing techniques to determine whether an object moving across a scene is a person. The camera surveillance system achieves an accurate and efficient classification by selectively processing a set of features associated with the object, such as features that define an omega shape. By selectively processing the set of features associated with the object, the methods and systems described herein reduce the computational complexity of standard image processing/object detection techniques.

Abstract: Systems, devices, and processes for classifying a digital item are described. In some examples, a first classifier determines whether a digital item, such as an electronic book (eBook), includes content of a first category that is acceptable for publication by a publisher. A second classifier determines whether the digital item includes content of a second category that is acceptable for publication by a publisher. In response to determining that the digital item includes content of the first category or content of the second category, a third classifier may determine whether the digital item includes a phrase that is indicative of content of a third category that is unacceptable for publication.

Abstract: Face recognition using multilayered discriminant analysis includes systems and methods applying an initial linear discriminate analysis to a database of face images in a more-or less conventional manner. Initial fuzzy logic then is applied to the results of the initial linear discriminate analysis to produce a subset of the database of face images. Thereafter, a subsequent linear discriminate analysis is applied to the subset of the database of face images and subsequent fuzzy logic is applied to the results of the subsequent linear discriminate analysis to produce a further subset of the subset of the database of face images. The application of the subsequent linear discriminate analysis and application of the subsequent fuzzy logic may be repeated until the further subset contains only one, or zero, face images.

Abstract: In one embodiment, a method includes receiving a digital image captured by a mobile device; and using a processor of the mobile device: generating a first representation of the digital image, the first representation being characterized by a reduced resolution; generating a first feature vector based on the first representation; comparing the first feature vector to a plurality of reference feature matrices; and classifying an object depicted in the digital image as a member of a particular object class based at least in part on the comparing.

Abstract: According to one embodiment, in response to a set of data for anomaly detection, a Bayesian belief network (BBN) model is applied to the data set, including for each of a plurality of features of the BBN model, performing an estimate using known observed values associated with remaining features to generate a posterior probability for the corresponding feature. A scoring operation is performed using a predetermined scoring algorithm on posterior probabilities of all of the features to generate a similarity score, wherein the similarity score represents a degree to which a given event represented by the data set is novel relative to historical events represented by the BBN model.

Abstract: A data classifier system of the present invention selects a plurality of classifications correlated to data groups so as to output classification axes based on hierarchical classifications and data groups. The data classifier system includes a basic category accumulation means, a classification axis candidate reduction means and a priority calculation means. The basic category accumulation means accumulates classifications serving as basic categories used for desired classifications in advance. The classification axis candidate reduction means selects a plurality of classifications from among classifications descendant from each basic category so as to create classification axis candidates, thus reducing classification axis candidates subjected to calculations based on data quantity of classifications and hierarchical distances of classifications.

Abstract: Provided is a photoelectric conversion apparatus including a plurality of pixels and a control unit, wherein each of the pixels includes a photoelectric conversion unit and a digital-signal output unit configured to output a digital signal based on the output of the photoelectric conversion unit, and the number of bits of the digital signal may be switched.

Abstract: A method includes selecting a target mobile device based on information regarding a power storage level of the particular mobile device. The method further includes transmitting program context information associated with a task of the first mobile device to a network accessible storage device. The method further includes transmitting a notification regarding the program context information to the target mobile device. The present disclosure describes a power and task (data and/or voice) handover system that enables a user to transfer task(s) from one mobile device to another mobile device using a network (wired or wireless) based handover scheme.

Abstract: An estimator training method and a pose estimating method using a depth image are disclosed, in which the estimator training method may train an estimator configured to estimate a pose of an object, based on an association between synthetic data and real data, and the pose estimating method may estimate the pose of the object using the trained estimator.

Abstract: An imaging device for capturing an image of an imaging object that is an artificial food mass, in which a light-transmissive microparticle is contained in a base material having a property of blocking infrared light, includes imaging means for capturing the image of the imaging object from one side; and an infrared light source that emits infrared light on the imaging object from the other side of the imaging object. The imaging means includes visible-light removing means for not receiving visible light. The imaging means captures the image of the imaging object while the infrared light source emits the infrared light on the imaging object. The device can accurately count the number of “microparticles not finely crushed or ground” by a computer or the like.

Abstract: A gradient computation unit computes a gradient of an objective function in a variable to be optimized. An added variable selection unit adds a variable corresponding to a largest absolute value of the computed gradient from among variables included in a variable set, to a nonzero variable set. A variable optimization unit optimizes a value of the variable to be optimized, for each variable included in the nonzero variable set. A deleted variable selection unit deletes a variable that, when deleted, causes a smallest increase of the objective function from among variables included in the nonzero variable set, from the nonzero variable set. An objective function evaluation unit computes a value of the objective function for the variable to be optimized.

Abstract: A computer-implemented method of enhancing images includes receiving one or more observed images, identifying wavelet bases, and determining a downsampling operator. A noise variance value is estimated and used to select a tuning parameter. A blurring kernel is estimated based on one or more system calibration parameter and used to determine a low-pass blurring filter operator. A cost function is created which generates one or more denoised super-resolution images based on the observed images and the plurality of wavelet bases. The cost function may include, for example, a sparsity inducing norm applied to the plurality of wavelet bases (with the tuning parameter applied to the sparsity inducing norm) and a constraint requiring the one or more denoised super-resolution images to be equal to a result of applying the low-pass blurring filter operator and the downsampling operator to the one or more denoised super-resolution images.

Abstract: The disclosed embodiments illustrate methods and systems for estimating a half-tone frequency of an image. The method includes combining, by one or more processors, a first binary block, obtained from a portion of the image, with one or more second binary blocks to create a third binary block. Each of the one or more second binary blocks is obtained by shifting the first binary block. The method further includes estimating, by the one or more processors, the half-tone frequency of the portion of the image, based on the first binary block and the third binary block.

Abstract: In general, in one aspect, the disclosure describes a video recording system including a user interface to enable a user to enter commands. A bookmark manager is to generate bookmarks corresponding to locations in the videos being recorded based on bookmark commands received, to assign end points for the bookmarks, and to generate a program based on selection of one or more of the recorded videos and selection of at least a subset of the bookmarks associated with the one or more recorded videos. A video record/playback manager is to control recording of the videos and the associated bookmarks and to present the program by playing the at least a subset of the associated bookmarks for the one or more of the recorded videos. Playback of each of the at least a subset of the associated bookmarks is to end at the assigned endpoint.

Abstract: An information processing apparatus that obtains intimacy degree information corresponding to identification information of a first person, specifies an extraction period based on the intimacy degree information, and extracts content in the extraction period.

Abstract: Motion of a device is sensed using image data, and a gesture corresponding to the sensed motion of the device is recognized. Functionality of the device corresponding to the recognized gesture is determined and invoked.

Abstract: Techniques for grouping images are disclosed. In some situations, the techniques include identifying at least one event-based image group among a plurality of images based on an event that is associated with each identified image, receiving a selection of one or more objects in a first image of the identified event-based image group, identifying other images in the identified event-based image group that each include at least one of the selected one or more objects, and associating the identified images with the first image. In one instance, the selected objects include individuals captured in the image.

Abstract: A method, system, and machine-readable medium for classifying an image element as one of a plurality of categories, including assigning the image element based on a ratio between an unoccluded perimeter of the image element and an occluded perimeter of the image element and coding the image element according to a coding scheme associated with the category to which the image element is classified. Exemplary applications include image compression, where categories include image foreground and background layers.

Abstract: Provided are a color evaluation apparatus and the like capable of evaluating the appropriateness of a color scheme in an image to be evaluated. A color evaluation apparatus 101 includes a division unit 102 that identifies a partial region of an input image, an acquisition unit 103 that acquires color information for identifying a color contained in the partial region and a first character string contained in the partial region, an extraction unit 104 that extracts a second character string which is associated in advance with the color information, and an evaluation unit 105 that evaluates appropriateness of the color information according to a result of comparing the first character string and the second character string.

Abstract: A system for contextualizing machine indeterminable information based on machine determinable information may include a memory, an interface, and a processor. The memory may store an electronic document image which may include information determinable by a machine and information indeterminable by a machine. The processor may be operative to receive, via the interface, the electronic document image. The processor may determine the machine determinable information of the electronic document image and may identify the machine indeterminable information of the electronic document image. The processor may contextualize the machine indeterminable information based on the machine determinable information. The processor may present the contextualized machine indeterminable information to the user to facilitate interpretation thereof. In response thereto, the processor may receive, via the interface, data representative of a user determination associated with the machine indeterminable information.

Abstract: Embodiments of the invention provide a system and method that is able to automatically provide a starting point for 2D to 3D image registration, without relying on human recognition of features shown in the 2D image. This is achieved by pre-processing the 3D data to obtain synthetically generated 2D images of those parts of the 3D data volume which will be used for registration purposes. Many different synthetically generated 2D images of the or each part of the 3D volume are produced, each from a different possible viewing direction. Each of these synthetic images is then subject to a feature extraction process to extract characterizing feature data of the registration feature shown in the images. Once the feature extraction has been undertaken for each image, when registration is to be performed the real-time 2D image is processed by applying each of the sets of extracted features thereto, to try and identify which set best matches the registration features in the 2D image.

Abstract: Techniques for comparing documents may be provided. For example, a comparison between layouts of the documents may be performed. The comparison may include segmenting the documents into blocks, where an arrangement of blocks of a document represents a layout of the document. Once segmented, similarity metrics, such as distances, between blocks of one document and blocks of the other document may be computed. The similarity metrics may be used to match the blocks between the documents. Further, the similarity metrics between the matched blocks may be added to determine an overall similarity metric between the documents. This overall similarity metric may indicate how similar the documents may be.

Abstract: In one implementation, a method includes detecting, using a processor, user input through a camera lens. The method further includes determining, using the processor, that an identity of a user, selected from identities of at least two users, is associated with the user input. The method also includes tracking, using the processor, a local interaction between the at least two users based on at least the identity, the user input, and stored rules that govern the local interaction. The tracking can include determining whether the user has complied with the stored rules that govern the local interaction. Furthermore, the local interaction can include a multiplayer game.

Abstract: A processing system can include a processor that includes circuitry. The circuitry can be configured to: receive far-end and near-end audio signals; detect silence events and voice activities from the audio signals; determine whether an audio event in the audio signals is an interference event or a speaker event based on the detected silence events and voice activities, and further based on localized acoustic source data and faces or motion detected from an image; and generate a mute or unmute indication based on whether the audio event is the interference event or the speaker event. The system can include a near-end microphone array to output the near-end audio signals, one or more far-end microphones to output the far-end audio signals, and one or more cameras to capture the image of the environment.

Abstract: Method and device are described for customizing the content selection to present on a display device based on identifying the viewer of the device. In one embodiment, the present disclosure relates to selecting from among a group of digital images, those images that are most likely to be of interest to the viewer. In general, many of the images available to the display device will be comprised of images containing subject faces. Using the relationship information to predict subject affinity, the display device computes an image affinity for each image by accumulating the individual subject affinity predictions between the viewer and each subject identified in each image. The image affinities are used to select images for presentation on the display device.

Abstract: A method includes receiving an image of a face to match with images of known faces, extracting blocks multiple blocks from the received image, calculating local binary pattern histograms for each block, generating matching scores for each block against block of the images of known faces, determining a top number, N, of matching scores less than the number of blocks, and matching the received image to an image of a known face as a function of the top number of matching scores.

Abstract: Annotating and classifying an image based on a user context includes determining a location data of an object captured in an image, determining an attribute data of the object, obtaining sensor data from sensors that are associated with the location data based on the attribute data, determining a recommended user context from one or more predefined user contexts based on a comparison of the location data, the attribute data, and the sensor data with location data, attribute data, and sensor data of one or more images associated with the one or more predefined user contexts, determining a recommended class of the captured image based on the recommended user context, selecting one or more annotation data from the location data, the attribute data, and the sensor data based on the recommended class or the recommended user context, and annotating the image with the one or more annotation data.

Abstract: A method for identifying, by at least one processor, at least one feature in a raster image based on a set of extraction parameters, and generating, by the at least one processor, a feature path file conforming to a vector format, the feature path file represents a plurality of instances of the at least one feature in the raster image. A system and computer program product are also disclosed.

Abstract: A method (100) and system (300) is described for processing video data comprising a plurality of images. The method and apparatus is for obtaining for labeling of a plurality of objects or regions in an image of a sequence of images followed by label propagation to other images in the sequence based on an inference step and a model.

Abstract: An image prior as a shared basis mixture model is described. In one or more implementations, a plurality of image patches are generated from one or more images. A shared basis mixture model is learned to model an image patch distribution of the plurality of image patches from the one or more images as part of a Gaussian mixture model. An image may then be reconstructed using the shared basis mixture model as an image prior.

Abstract: An information processing apparatus includes: a storage unit which stores person relationship information representing relationships between people as a subject in a storage medium; an acquisition unit which acquires image data generated by imaging people as a subject; a detection unit which detects each person in an image; a specification unit which specifies each person detected from the image by the detection unit; and a determination unit which determines the relationship between multiple people detected from the image. When at least one person from among the people detected from the image is specified and another person is unable to be specified, the specification unit may specify the at least one other person on the basis of the relationship between the multiple people and the person relationship information.

Abstract: A system for extracting and monitoring media tags within video content includes at least one server in communication with a plurality of content sources, the server receiving video content from the content sources, a recorder saving the video content, a detector receiving at least one frame of the video content, the detector detecting one or more unknown text within the frame and creating one or more images, each image associated with one of the one or more unknown text, the detector generating metadata associated with the one or more unknown text appearing in the frame, and an optical character recognition engine scanning the one or more images and converting the one or more images into one or more known text. The server further determines that the one or more known text is a media tag.

Abstract: An exemplar dictionary is built from exemplars of digital content for determining predictor blocks for encoding and decoding digital content. The exemplar dictionary organizes the exemplars as clusters of similar exemplars. Each cluster is mapped to a label. Machine learning techniques are used to generate a prediction model for predicting a label for an exemplar. The prediction model can be a hashing function that generates a hash key corresponding to the label for an exemplar. The prediction model learns from a training set based on the mapping from clusters to labels. A new mapping is obtained that improves a measure of association between clusters and labels. The new mapping is used to generate a new prediction model. This process is repeated in order to iteratively refine the machine learning modes generated.

Abstract: Techniques are disclosed for analyzing a scene depicted in an input stream of video frames captured by a video camera. In one embodiment, e.g., a machine learning engine may include statistical engines for generating topological feature maps based on observations and a detection module for detecting feature anomalies. The statistical engines may include adaptive resonance theory (ART) networks which cluster observed position-feature characteristics. The statistical engines may further reinforce, decay, merge, and remove clusters. The detection module may calculate a rareness value relative to recurring observations and data in the ART networks. Further, the sensitivity of detection may be adjusted according to the relative importance of recently observed anomalies.

Abstract: An imaging apparatus includes an imaging unit that generates a pair of pieces of image data mutually having a parallax by capturing a subject, an image processing unit that performs special effect processing, which is capable of producing a visual effect by combining a plurality of pieces of image processing, on a pair of images corresponding to the pair of pieces of image data, and a region setting unit that sets a region where the image processing unit performs the special effect processing on the pair of images.

Abstract: Provided is an image display device provided with an image display unit for displaying a still image or a moving image, an image capturing unit for capturing the image in a direction in which the image display unit displays the image on the image display unit, and a face detection unit for performing, at predetermined intervals, face detection processing for detecting a face included in the image captured by the image capturing unit, wherein the predetermined intervals are variable according to whether or not the face of a user is included in the image captured by the image capturing unit, and when the position of the detected face does not change for a predetermined period of time in the face detection processing, the face detection unit does not detect the face as the face of the user.

Abstract: This invention relates to an information processing apparatus which evaluates diagnosis based on the tissue sample image of a tissue. The information processing apparatus inputs a plurality of first regions selected as diagnosis targets from a tissue sample image obtained by capturing a tissue, a plurality of second regions selected as diagnosis targets from the tissue sample image, and pieces of position information of the respective regions selected on the tissue sample image. The information processing apparatus calculates a similarity between the plurality of first regions and the plurality of second regions based on correlations considering the distances between the selected regions on the tissue sample image. This arrangement can evaluate whether ROIs selected by a pathologist or apparatus include an important region of interest.

Abstract: Machines, systems and methods for enhanced optical character recognition are provided. In one embodiment, the method comprises identifying a sample character in a textual context to be optically recognized; comparing the sample character with a template character, wherein the sample character is scaled into a first grid and the template character is scaled into a second grid; identifying one or more pixels in the sample character within the first grid and one or more pixels in the template character in the second grid, wherein the one or more pixels are identified as belonging to a foreground category in the textual content, a foreground pixel having at least N gradients corresponding to edges of the foreground pixel that are juxtaposed to a neighbor pixel, wherein a contour foreground pixel has at least one gradient that is neighbored by a background pixel in the textual context.

Abstract: Personalized tag ranking of images, including identifying within a reference image collection any images that are similar to an input image, identifying within a source image collection any images that have associated tags that are similar to a set of input tags associated with the input image, identifying among the images identified in the reference image collection any images that are similar to the images identified in the source image collection, and calculating a weight for each of a plurality of tag pairs, where each of the tags in each of the tag pairs is associated with a different subset of the images in the reference image collection identified as being similar to the images identified in the source image collection, and ranking the input tags of the input image in accordance with a predefined ranking function as applied to the tag pair weights.

Abstract: A method and apparatus for matching key pixels of images and a method and apparatus for matching images are disclosed. The method for matching key pixels of images includes: determining, for a key pixel to be matched of a first image, a first eigenvector, in a set of eigenvectors of a second image, matching an eigenvector of the key pixel to be matched; determining a second eigenvector, in a set of eigenvectors of the first image, matching the first eigenvector; and determining the key pixel to be matched and a key pixel corresponding to the first eigenvector as a pair of matching pixels when a coordinate vector of the key pixel to be matched is the same as a coordinate vector of a key pixel corresponding to the second eigenvector.

Abstract: A system and method for adaptive face recognition includes at least one electronic processor having a central processing unit. At least one database having a plurality of pixilated face images of known subjects of interest is associated with the processor. At least one test image of a new subject of interest is configured for input into the electronic processor. A classification processing tool is associated with the electronic processor. The classification processing tool is configured to build a dictionary and provide a classification match of the test image with one of the plurality of pixilated face images of known subjects of interest. At least one device is associated with the processor and configured to output the classification match in a tangible medium.

Abstract: There is provided an image processing apparatus that includes a feature data calculating unit, a distribution map generating unit, and a display control unit. The feature data calculating unit calculates feature data of each image contained in a group of sequential images that are taken by an image taking apparatus. The distribution map generating unit includes a representative vector calculating unit and a representative vector arrangement determining unit, and generates a distribution map that represents an overall trend of the group of sequential images. The representative vector calculating unit calculates a predetermined number of representative vectors that represent a plurality of images contained in the group of sequential images. The representative vector arrangement determining unit determines arrangement of the calculated representative vectors on the distribution map. The display control unit displays the distribution map on a display unit.

Abstract: The present disclosure provides an image processing method, system and electronic device. The method comprises: obtaining a first image; applying a first process to the first image to obtain a second image having a number of pixels smaller than a number of pixels in the first image; applying a second process to the second image to obtain a third image having an image quality higher than that of the second image; sending, upon detecting a first operation by a user, the first image to a server, such that the server applies a third process to the first image to obtain a fourth image having an image quality higher than that of the first image, the third process and the second process belonging to a same type of image process; and receiving the fourth image. The present invention avoids unnecessary waste of data traffic and saves the consumed time.

Abstract: Methods, systems, and apparatus are provided for determining location information for images. In one aspect, a method includes obtaining landmark location data from content depicted in an image and corresponding confidence scores. Also, the method includes obtaining caption location data from user input and corresponding confidence scores, and obtaining metadata location data from data provided by an image capturing device. Further, the method includes identifying location pairs from the landmark, caption, and metadata location data, and generating, for each location pair, a geographic consistency score. Additionally, the method includes selecting a location pair based on the geographic consistency scores, and selecting an image location for the image from the selected location pair. Moreover, the method includes determining an image location score based on a confidence score for one of the locations in the selected location pair, and associating the image location and image location score with the image.