Abstract: A method of identifying a distracting element in an image (e.g., 1100), is disclosed. A visual attention map (e.g., 1120) is determined for the image (1100), the visual attention map (1120) representing one or more regions of the image, at least one of the regions corresponding to at least a portion of a subject of the image. A salient region map (e.g., 1110) is determined for the image (1100), the salient region map comprising a distribution of visual attraction values defining one or more further regions of the image (1100), the one or more further regions being categorized as salient. An intersection between the visual attention map (1120) and the salient region map (1110) is determined to identify a distracting element in the image (1100). The distracting element corresponds to at least one of the salient regions.

Abstract: An image processor reads an image from an original, divides the image into a plurality of blocks, and performs a determination process on each block. Through the determination process, a block is classified as a first color block or second color block. The image processor classifies the original as a color image when a number of first color blocks reach a prescribed number before the determination processes for all of the plurality of blocks have been completed. The image processor classifies the original as the color image when a number of first color blocks determined through the determination processes for all of the plurality of blocks is fewer than the prescribed number and a color ratio is greater than a prescribed ratio. The color ratio is the sum of the number of the first color blocks and the number of the second color blocks to the plurality of blocks.

Abstract: Classifying pixels in a digital image includes receiving a primary image from a primary image sensor. The primary image includes a plurality of primary pixels. Depth information from a depth sensor is also received. The depth information and the primary image are cooperatively used to identify whether a primary pixel images a foreground subject or a background subject.

Abstract: Embodiments herein provide computer-implemented techniques for allowing a user computing device to extract financial card information using optical character recognition (“OCR”). Extracting financial card information may be improved by applying various classifiers and other transformations to the image data. For example, applying a linear classifier to the image to determine digit locations before applying the OCR algorithm allows the user computing device to use less processing capacity to extract accurate card data. The OCR application may train a classifier to use the wear patterns of a card to improve OCR algorithm performance. The OCR application may apply a linear classifier and then a nonlinear classifier to improve the performance and the accuracy of the OCR algorithm. The OCR application uses the known digit patterns used by typical credit and debit cards to improve the accuracy of the OCR algorithm.

Abstract: A computer readable medium stores a program causing a computer to execute a process for image processing. The process includes: calculating, on the basis of image feature information of a plurality of image areas each set with a classification information item, a probability distribution of the image feature information for each classification information item; acquiring a target image; calculating an evaluation value of each of pixels included in the target image relating to a specified classification information item, on the basis of the image feature information of an image area including the pixel and the probability distribution of the image feature information calculated for the specified classification information item; and extracting, from the target image, an image area relating to the specified classification information item, on the basis of the evaluation value calculated for each of the pixels included in the target image.

Abstract: An information processing apparatus displays, for each group, images that are divided into groups so that each group contains at least one of the images. The apparatus includes an image-data storing unit that stores image data of the images, a group-attribute-information storing unit that stores attribute information of the groups, a display controlling unit that controls processing for displaying the images for each group, a search-key extracting unit that extracts a search key when the display controlling unit issues an instruction for starting the processing for displaying the images for each group, and a searching unit that searches for the groups associated with the extracted search key. The display controlling unit controls display of a library of the groups so that the groups associated with the search key and found by the searching unit are displayed at a top side in the library.

Abstract: In some embodiments, a server, system, and method for automatically creating a photo-based project based on photo analysis and image metadata is disclosed. The method includes the steps of: receiving a plurality of images from a user-device, reading embedded metadata from the plurality of images, and storing said plurality of images in a data repository; performing photo analysis on the plurality of images in the data repository to determine a visual content and relevant metadata in the images; customizing the photo-based project automatically by performing one or more automatic customization actions based on the visual content in and the relevant metadata in the plurality of images; placing the plurality of images automatically in one or more particular page layouts of the photo-based project based on the customization performed; and generating a printed product comprising the plurality of images based on the customization performed.

Abstract: A method for vehicle clear path detection using a camera includes imaging a ground area in front of the vehicle with the camera to produce a ground image and analyzing the ground image to formulate a clear path free of objects limiting travel of the vehicle.

Abstract: A robotic surgical system includes a master controller with an input handle and robotic manipulator assemblies including a surgical end effector and an endoscopic camera. The input handle is translatable to provide a position and rotatable to provide an orientation. A control system couples the master controller to the first and second manipulator assemblies. The control system moves the surgical end effector in response to the position and orientation of the input handle. The control system moves the input handle to orient the input handle to correspond to an orientation of the surgical end effector from a viewpoint of the endoscopic camera during the repositioning of at least one of the input handle position, the end effector, or the endoscopic camera. The control system may move the surgical end effector only in a first mode and orients the input handle only in a second mode.

Abstract: An object identification system calculates boundaries between real objects from images of the real objects, and calculates first indicators which correspond to each angles of a first angle section divided into a first angle gap and which varies every boundary between the calculated real objects. The object identification system extracts a virtual object having an outline firstly meet with a radiating line corresponding to each map angle of the divided into a second angle gap, and generate a set of second indicators corresponding to each map angle. The object identification system matches the first indicators into second indicators having a repeat ratio substantially equal to a repeat ratio of the first indicators in an angle section, and extracts virtual objects matched with each of the previewed real objects.

Abstract: Aspects of the present invention include systems and methods for segmentation and recognition of action primitives. In embodiments, a framework, referred to as the Continuous Linear Dynamic System (CLDS), comprises two sets of Linear Dynamic System (LDS) models, one to model the dynamics of individual primitive actions and the other to model the transitions between actions. In embodiments, the inference process estimates the best decomposition of the whole sequence into continuous alternating between the two set of models, using an approximate Viterbi algorithm. In this way, both action type and action boundary may be accurately recognized.

Abstract: A method for recognizing heart diseases in a cardiac echo video of a heart with an unknown disease using a spatio-temporal disease model derived from a training echo video, comprising the steps of: generating a plurality of training models for heart diseases, wherein the cardiac echo videos are each derived from a known viewpoint and the disease of the heart is known; analyzing the video of the heart with the unknown disease by fitting a model of shape and motion for each frame and combining the results across the frames; and, reporting the disease using a classification method for choosing among the diseases of interest.

Abstract: An image processing apparatus comprises a first composition processing unit configured to compose a first image generated by a first image capturing unit and a second image generated by a second image capturing unit and generate a third image; and a detection unit configured to detect an area of the object from the third image.

Abstract: An illustrative mobile device includes a data storage configured to at least temporarily store visual information and at least one processor that is configured to determine whether to request visual information processing from a network with which the mobile device may communicate. The processor is configured to determine a mobile device condition and a network condition. The processor determines a type of feature from the visual information to use for classification based on the determined mobile device and network conditions. The processor is configured to classify the visual information based on the determined type of feature and determine a confidence indicator based on the classification. The processor determines whether to request visual information processing from the network based on the determined confidence indicator.

Abstract: Disclosed are a system and a method for recognizing a disguised face using a Gabor feature and a support vector machine (SVM) classifier according to the present invention. The system for recognizing a disguised face includes: a graph generation means to generate a single standard face graph from a plurality of facial image samples; a support vector machine (SVM) learning means to determine an optimal classification plane for discriminating a disguised face from the plurality of facial image samples and disguised facial image samples; and a facial recognition means to determine whether an input facial image is disguised using the standard face graph and the optimal classification plane when the facial image to be recognized is input.

Abstract: Methods, systems, and articles of manufacture for annotating of an image are disclosed. These include scoring the image using a plurality of trained classifiers, wherein each of the trained classifiers corresponds to at least one of a plurality of image groups clustered based upon image similarity, and wherein each image group is associated with a set of weighted labels; selecting one or more of the image groups based upon the scoring; aggregating one or more sets of weighted labels associated with the selected one or more image groups; and annotating the image using the aggregated one or more sets of weighted labels.

Abstract: A method (and system) of determining a local binary pattern in an image includes selecting an orientation. For each pixel in the image, the method further includes determining a binary decision for each such pixel relative to one neighboring pixel of the orientation, selecting a new orientation, and repeating the determination of the binary decision for each pixel in the image relative to one neighboring pixel of the newly selected orientation.

Abstract: A digital image of the object is captured and the object is recognized from plurality of objects in a database. An information address corresponding to the object is then used to access information and initiate communication pertinent to the object.

Abstract: The present disclosure relates to a method for improving the perception of an image. The method may include subjecting an original image to a series of independent processes, each producing a pixel calculated using a respective reference kernel. The reference kernels each may comprise pixels from the original image.

Abstract: Methods, systems, and apparatus, including computer programs encoded on a computer storage medium, for classifying images. In one aspect, a method includes receiving training samples for a particular data dimension. Each training sample specifies a training value for the data dimension and a measure of relevance between the training sample and a phrase. A value range is determined for the data dimension. The value range is segmented into two or more segments. A predictive model is trained for each segment. The predictive model for each segment is trained to predict an output based on an input value that is within the segment. A classification sample specifying an input value is received. A classification output is computed based on the input value, the predictive model for the segment in which the input value is included, and the predictive model for an adjacent segment.

Abstract: A system for segregating handwritten information from typographic information on a document may include a memory, an interface, and a processor. The memory stores an electronic document image of a document where the electronic document image includes pixels and each pixel has a characteristic. The processor may receive, via the interface, the electronic document image and may identify first, second and third most frequently occurring characteristics of the pixels of the electronic document image. The pixels having the first most frequently occurring characteristic represent a background of the document. The processor may determine the typographic information of the document as represented by pixels having the second most frequently occurring characteristic. The processor may determine the handwritten information of the document as represented by pixels having the third most frequently occurring characteristic.

Abstract: A representation framework is determined in a face recognition method for a first collection of facial images including at least principle component analysis (PCA) features. A representation of said first collection is stored using the representation framework. A modified representation framework is determined based on statistical properties of original facial image samples of a second collection of facial images and the stored representation of the first collection. The first and second collections are combined without using original facial image samples. A representation of the combined image collection (super-collection) is stored using the modified representation framework.

Abstract: An image recognition device in accordance with the inventive concept may include an input vector extraction part extracting an input vector from an input image; a compression vector conversion part converting the input vector into a compression vector using a projection vector; a training parameter generation part receiving a training vector to generate a training parameter using a projection vector obtained through a folding operation of the training vector; and an image classification part classifying the compression vector using the training vector to output image recognition data.

Abstract: A method for generating a depth map for a 2D image and video includes receiving the 2D image and video; defining a plurality of object classes; analyzing content of the received 2D image and video; calculating probabilities that the received 2D image belongs to the object classes; and determining a final depth map based on a result of the analyzed content and the calculated probabilities for the object classes.

Abstract: An image recognition device that improves the accuracy of generic object recognition compared with conventional technologies by reducing the influence of the position, size, background clutter and the like of an object that is targeted to be recognized in the input image by the generic object recognition. The image recognition device performs a generic object recognition and includes: a segmenting unit configured to segment an input image into a plurality of regions in accordance with meanings extracted from content of the input image; a generating unit configured to compute feature data for each of the plurality of regions and generate feature data of the input image reflecting the computed feature data; and a checking unit configured to check whether or not a recognition-target object is present in the input image in accordance with the feature data of the input image.

Abstract: One or more devices may receive multiple images; determine one or more classifications for each of the multiple images; generate a confidence score for each classification of the one or more classifications for each of the multiple images. The confidence score may include a value between two numbers and may identify the likelihood that that a particular classification, of the one or more classifications, correctly corresponds to a particular image, of the multiple images. The confidence score may be based on information, associated with a user, and pixel-based classification information. The one or more devices may sort the multiple images by the one or more classifications and by corresponding confidence scores to form sorted multiple images; and provide the sorted multiple images.

Abstract: Embodiments generally relate to summarizing a photo album in a social network system. In one embodiment, a method includes grouping photos into a plurality of groups of photos, and selecting a plurality of representative photos, where each representative photo represents a respective group from the plurality of groups, where the selecting is based on a quality score of each of the photos, and where each quality score is based on different types of attributes. The method also includes enabling the plurality of representative photos to be shared.

Abstract: There is provided an image processing apparatus including a zero class detecting unit that detects a zero class in which an appearance frequency of a pixel value is zero from among a plurality of classes into which pixel values of an image are classified according to pixel value magnitude, and a non-zero class converting unit that converts the zero class into a non-zero class in which the appearance frequency of the pixel value is one or more, without updating a total number of the classes, by updating a range of the zero class detected by the zero class detecting unit. The present disclosure can be applied to an image processing apparatus.

Abstract: Embodiments include methods and systems for context-adaptive pixel processing based, in part, on a respective weighting-value for each pixel or a group of pixels. The weighting-values provide an indication as to which pixels are more pertinent to pixel processing computations. Computational resources and effort can be focused on pixels with higher weights, which are generally more pertinent for certain pixel processing determinations.

Abstract: Image fragments are formed in regions corresponding to circles searched from an input image. In a cascade of homogeneous classifiers, each classifier classifies input vectors corresponding to the image fragments into a face type and a non-face type. This procedure is performed on all images included in an image pyramid and the coordinates of a face detected based on the results of the procedures on all images.

Abstract: A system and method to detect similarities between images. The system and method allow comparisons between a query image and one or more catalog images in a manner that is resilient to scanning, scaling, rotating, cropping and other distortions of the query image. The system includes an image processing module that determines and/or calculates principle features of a catalog image and constructs a feature vector using one or more of the principle features. The system also includes a matching module that matches a query image to one or more catalog images. The system finds matches based on a distance measure of features present in the query image and features present in the catalog images.

Abstract: A system and method are provided to identify and extract data from data forms by identifying data containment locations on the form, classifying the data containment locations to identify data containment locations of interest, and performing a match between recognition results and a predefined set of known labels or data formats to classify and return a data containment label, coordinates and the recognition value of interest.

Abstract: The present invention relates to a method and a corresponding apparatus for detecting coding artifacts in an image. The proposed apparatus comprises an edge position detector that detects an edge position of an edge in said image, a border position detector that detects a border position of a border between a texture area and a flat area in said image, and an artifact position defining unit that defines the area between said edge position and said border position as artifact area potentially comprising coding artifacts.

Abstract: A challenge to be met is to make it possible to accurately ascertain a behavior history of a person in various camera environments. Person characteristic data extracted from a plurality of cameras are stored in a person characteristic database. A retrieval request receiving section receives an identifier for identifying a person to be retrieved as a retrieval key. A characteristic retrieval section performs retrieval of persons matching the retrieval key from the person characteristic database in descending order of similarity. A retrieval result grouping section classifies the results of retrieval into units assumed to belong to the same environment. A retrieval result display section displays results of grouping. Since retrieval results are displayed in the form of a list on each unit assumed to belong to the same environment, the person to be retrieved can simply be ascertained in various camera environments despite a limited number of displays provided.

Abstract: A method and system for automatic lung segmentation in magnetic resonance imaging (MRI) images and videos is disclosed. A plurality of predetermined key landmarks of a lung are detected in an MRI image. The key landmarks may be detected using discriminative joint contexts representing combinations of multiple key landmarks. A lung boundary is segmented in the MRI image based on the detected key landmarks. The landmark detection and the lung boundary segmentation can be repeated in each frame of an MRI video.

Abstract: A method for fine-grained image classification on an image includes automatically segmenting one or more objects of interest prior to classification; and combining segmented and original image features before performing final classification.

Abstract: Technology is described for determining and using invariant features for computer vision. A local orientation may be determined for each depth pixel in a subset of the depth pixels in a depth map. The local orientation may an in-plane orientation, an out-out-plane orientation or both. A local coordinate system is determined for each of the depth pixels in the subset based on the local orientation of the corresponding depth pixel. A feature region is defined relative to the local coordinate system for each of the depth pixels in the subset. The feature region for each of the depth pixels in the subset is transformed from the local coordinate system to an image coordinate system of the depth map. The transformed feature regions are used to process the depth map.

Abstract: An apparatus and method are provided for recognizing an emotion of an individual based on Action Units. The method includes receiving an input AU string including one or more AUs that represents a facial expression of an individual from an AU detector; matching the input AU string with each of a plurality of AU strings, wherein each of the plurality of AU strings includes a set of highly discriminative AUs, each representing an emotion; identifying an AU string from the plurality of AU strings that best matches the input AU string; and outputting an emotion label corresponding to the best matching AU string that indicates the emotion of the individual.

Abstract: A method for determining noise levels in a subband of an image. The method comprises receiving the subband of the image, defining block regions in at least two space domains of the subband, for each defined block region, identifying first wavelet coefficients associated with coordinate values in the at least two space domains in the defined block region, computing a correlation matrix between identified wavelet coefficients to determine the correlation between first wavelet coefficients according to the at least one color domain, computing second wavelet coefficients, the computation of second wavelet coefficients being based on the correlation matrix and the first wavelet coefficients, computing at least one noise level, the noise level computation being based on at least one second wavelet coefficient and providing the at least one noise level.

Abstract: An image segmentation method includes generating a hierarchy of regions by unsupervised segmentation of an input image. Each region is described with a respective region feature vector representative of the region. Hierarchical structures are identified, each including a parent region and its respective child regions in the hierarchy. Each hierarchical structure is described with a respective hierarchical feature vector that is based on the region feature vectors of the respective parent and child regions. The hierarchical structures are classified according to a set of predefined classes with a hierarchical classifier component that is trained with hierarchical feature vectors of hierarchical structures of training images. The training images have semantic regions labeled according to the set of predefined classes. The input image is segmented into a plurality of semantic regions based on the classification of the hierarchical structures and optionally also on classification of the individual regions.

Abstract: A nearest-neighbor-based distance metric learning process includes applying an exponential-based loss function to provide a smooth objective; and determining an objective and a gradient of both hinge-based and exponential-based loss function in a quadratic time of the number of instances using a computer.

Abstract: Techniques are presented for analyzing audio-video segments, usually from multiple sources. A combined similarity measure is determined from text similarities and video similarities. The text and video similarities measure similarity between audio-video scenes for text and video, respectively. The combined similarity measure is then used to determine similar scenes in the audio-video segments. When the audio-video segments are from multiple audio-video sources, the similar scenes are common scenes in the audio-video segments. Similarities may be converted to or measured by distance. Distance matrices may be determined by using the similarity matrices. The text and video distance matrices are normalized before the combined similarity matrix is determined. Clustering is performed using distance values determined from the combined similarity matrix.

Abstract: An apparatus and method to find a specified number of corners and/or interest points in an image is presented. In some embodiments, a method to find a specified number of corners in a digital image comprises receiving a digital image containing a plurality of candidate corners; directly calculating a threshold score (S) for a center pixel, for each of the plurality of candidate corners, to form a plurality of scores; sorting, by the plurality of scores, the plurality of candidate corners to form a sorted list; and selecting corner locations sequentially from the sorted list based on the certain number of corners. The methods described may be implemented using any combination of hardware, software and firmware.

Abstract: Methods, systems and apparatus for assigning labels to images. In general, in one aspect, a method includes determining, for an image, a first set of labels, each label being determined to be indicative of subject matter of the image based on content feature values of the image, for each label in the first set of labels, determining a second set of labels, each label in the second set of labels determined to be semantically related to the label in the first set of labels, assigning a score to each label in the second sets of labels, and based on the scores assigned to each label in the second sets of labels, assigning one or more of the labels in the second sets of labels to the image.

Abstract: A system and method for generating an ordered set of suggested profile images. The profile image application includes a scorer, a recognition engine, a trend analyzer, a suggestion module and a user interface engine. The scorer scores user images based on metadata, such as the number of people tagged in the image and the recency of the image. The recognition engine identifies people and objects in the image. The trend analyzer identifies trends. The suggestion module generates the ordered set of suggested profile images based at least in part on the score. The user interface engine generates a user interface that includes the ordered set of suggested profile images.

Abstract: Methods and systems for intelligently cropping images, including receiving, over a computer network, a source image, and then associating a first identifier tag with a first object in the source image. A cropped image is generated from the source image wherein the cropping is based on the first object. The system and method then notifying a first user that the first identifier tag is associated with the first object in the cropped image, wherein the notification includes the cropped image.

Abstract: A system includes a content evaluation device is configured to receive reproduced media content and compare the reproduced media content to reference media content to determine a quality of the reproduced media content relative to the reference media content. The content evaluation device is configured to apply an entropy factor to the determined quality to model human perception of the reproduced media content. A method of determining the entropy factor includes converting the reference media content or the reproduced media content to a grayscale image, counting a number of unique luminance values in the grayscale image, determining the total number of possible luminance values, and defining the entropy factor to be the number of total pixels compared relative to the maximum number of pixels represented by any single luminance value multiplied by the number of possible luminance values.

Abstract: A system and method are provided for model-based coronary artery calcium (CAC) scoring. A model image of a heart region is aligned with an image of a patient's heart region in order to more easily identify the coronary arteries and other relevant anatomical features in the image. Once the images are aligned, relevant calcium plaques are identified by their presence within a coronary artery, and the relevant plaques are then labeled by the specific coronary artery in which they are located. The coronary arteries with the labeled plaques are scored individually based on their size and X-ray attenuation, and an overall score based on all of the relevant plaques is then computed, which is related to the patient's risk for coronary artery disease.

Abstract: The present invention may provide a method for image-based identification. The method may include providing a digital photo of an unidentified item; transmitting, over a network, the digital photo to an identification service; in response to transmitting the digital photo, receiving, over the network, item information from the identification service, wherein the item information includes textual identification information about the item; and displaying the textual identification information.

Abstract: The image signature extraction device includes an extraction unit and a generation unit. The extraction unit extracts region features from respective sub-regions in an image in accordance with a plurality of pairs of sub-regions in the image, the pairs of sub-regions including at least one pair of sub-regions in which both a combination of shapes of two sub-regions of the pair and a relative position between the two sub-regions of the pair differ from those of at least one of other pairs of sub-regions, and being classified into a plurality of types based on a combination of shapes of two sub-regions and a relative position between the two sub-regions of each of the pairs. The generation unit generates an image signature to be used for identifying the image based on the extracted region features of the respective sub-regions.