Abstract: A method and system for real time processing of a sequence of video frames. A current frame in the sequence and at least one frame in the sequence occurring prior to the current frame is analyzed. Each frame includes a two-dimensional array of pixels. The sequence of video frames is received in synchronization with a recording of the video frames in real time. The analyzing includes performing a background subtraction on the at least one frame, which determines a background image and a static region mask associated with a static region consisting of a contiguous distribution of pixels in the current frame. The static region mask identifies each pixel in the static region upon the static region mask being superimposed on the current frame. A determination is made that a persistence requirement, both a non-persistence duration requirement and a persistence duration requirement, or a combination thereof have been satisfied.

Abstract: An image processing apparatus performs sharpening processing on each of a plurality of pieces of left-eye image data, and synthesizes them in a unit of predetermined group to generate left-eye intermediate image data (1). The image processing apparatus then performs sharpening processing on each of a plurality of pieces of left-eye intermediate image data (1) generated by the synthesizing processing and synthesizes them in a unit of predetermined group to generate left-eye intermediate image data (2).

Abstract: Provided are a shoe image retrieval apparatus and method using a matching pair, which can accurately retrieve image information corresponding to an inputted image from the database and provide the retrieved image information, by normalizing a correspondence relation in consideration of geometric image transformation about the matching pair and allowing a similar image to be retrieved by applying the normalized correspondence relation. It is possible to detect optimum geometric image transformation from a matching pair between the inputted shoe image and the image stored in the database and simultaneously retrieve a plurality of objects in the inputted shoe image based on the detected geometric image transformation, thereby providing an efficient shoe retrieval service.

Abstract: According to one method, the method occurs at a data file analyzer. The method includes identifying at least one document identifier associated with a first document in a portable document format (PDF) file. The method further includes determining, using the at least one document identifier, a reference point identifier for identifying a reference point in the first document, an offset value for indicating a location of a first detection area in the first document, and size information for indicating a size of the first detection area in the first document. The method also includes identifying, using a reference point identifier, the reference point in the first document. The method further includes identifying, using the offset value and the size information, the first detection area in the first document and extracting, by processing binary data of the PDF file, data within the first detection area of the first document.

Abstract: A method and system for real time processing of a sequence of video frames. A current frame in the sequence and at least one frame in the sequence occurring prior to the current frame is analyzed. The sequence of video frames is received in synchronization with a recording of the video frames in real time. The analyzing includes performing a background subtraction on the at least one frame, which determines a background image and a static region mask associated with a static region consisting of a contiguous distribution of pixels in the current frame. The static region mask identifies each pixel in the static region upon the static region mask being superimposed on the current frame. A status of a static object is determined as either an abandoned status if the static object is an abandoned object or a removed status if the static object is a removed object.

Abstract: A method and system for real time processing of a sequence of video frames. A current frame in the sequence and at least one frame in the sequence occurring prior to the current frame is analyzed. The sequence of video frames is received in synchronization with a recording of the video frames in real time. The analyzing includes performing a background subtraction on the at least one frame, which determines a background image and a static region mask associated with a static region consisting of a contiguous distribution of pixels in the current frame, which includes executing a mixture of 3 to 5 Gaussians algorithm coupled together in a linear combination by Gaussian weight coefficients to generate the background model, a foreground image, and the static region. The static region mask identifies each pixel in the static region upon the static region mask being superimposed on the current frame.

Abstract: Systems and methods for image organization are provided. An computing device in accordance with embodiments of the present disclosure includes a processor configured to receive an image set comprising a plurality of images, compare a portion of each image in the image set with a verified cue library including a plurality of visual cues that correspond to different geographic place tags, and display a recommendation panel including a recommended place tag corresponding to a visual cue that matches the portion.

Abstract: Methods, apparatus, systems and articles of manufacture to perform block-based static region detection for video processing are disclosed. Disclosed example video processing methods include segmenting pixels in a first frame of a video sequence into a first plurality of pixel blocks. Such example methods can also include processing the first plurality of pixel blocks and a second plurality of pixel blocks corresponding to a prior second frame of the video sequence to create, based on a first criterion, a map identifying one or more static pixel blocks in the first plurality of pixel blocks. Such example methods can further include identifying, based on the map, a static region in the first frame of the video sequence.

Abstract: The disclosure includes a system and method for indexing synthetically modified images of a high quality image. An image recognition application receives images of a product, crops background regions from the images, scales the image based on a minimum value among width and height of the image and generates multiple image sizes, blurs the images, brightens the image and indexes the images as being associated with the product. The images can be of box-shaped packages that include four or six images or cylindrical packages that include, for example, eight images of the packages. The images can be indexed in a k-dimensional tree for faster retrieval.

Abstract: A method, apparatus and computer program product are provided to facilitate scene segmentation from focal stack images. The method may include receiving a set of focal stack images, calculating a focal measure for each of a plurality of pixels of the set of focal stack images, and grouping each of a plurality of pixels for which the focal measure was calculated into a plurality of super pixels. The method may also include calculating a focal measure for each of the plurality of super pixels, segmenting a respective focal stack image based on the focal measure of each of the plurality of super pixels, calculating a color probability for each of the plurality of super pixels, and segmenting each focal stack image based on color probability of each of the plurality of super pixels.

Abstract: Systems and methods for document tracking using elastic graph-based hierarchical analysis are disclosed. According to one embodiment, a method may include at least one computer processor identifying a sector for the document; the at least one computer processor retrieving a customization library for the document based on the sector; the at least one computer processor analyzing a structure of the document using the customization library, whereby a plurality of markers in first the document are identified; and the at least one computer processor generating an elastic graph for the document based on the plurality of markers.

Abstract: An image compression method and fast storage device accessing and pixel decompression is achieved by applying variable bit rate to reduce the data amount of each image frame. Several thresholds are predetermined depending on the availability of the bandwidth of the storage device and the image resolution to decide the compression ratio of each image frame. Starting address of each compressed image frame is saved in predetermined location of the storage device for quick random accessing any compressed frame of image.

Abstract: A method including digitally processing a first image of a scene from a first perspective, to identify a first obscured portion of the scene at an imaging plane that is obscured by a forward object in the scene; digitally processing a second image of the scene from a second perspective, to identify a second obscured portion of the scene at the imaging plane that is obscured by the forward object in the scene; and outputting, if the first obscured portion of the scene and the second obscured portion of the scene are overlapping at the imaging plane, an indication that the first image and the second image cannot be processed successfully to produce a third composite image of the scene without the forward object.

Abstract: Computer-readable media stores instructions that perform operations including receiving a first electronic document; determining a first information gain value associated with a first line that divides the first electronic document into a first portion and a second portion; determining a second information gain value associated with a second line that divides the first electronic document into a third portion and a fourth portion; and determining which of the first information gain value and second information gain value is greater. Information gain values are determined by calculating a difference between an entropy value associated with a line and an entropy value associated with an electronic document. Entropy values associated lines or electronic documents are determined based at least in part on document objects in the portions created by a line or an electronic document.

Abstract: An image processing device capable of generating foreground object data by using a captured image includes a depth data generator configured to generate depth data of the captured image; an amplitude data generator configured to generate amplitude data of the captured image; a foreground object detector configured to perform a first detection operation for detecting the foreground object based on the generated depth data and first reference background data, and to perform a second detection operation for detecting the foreground object based on the generated amplitude data and second reference background data; and a foreground object data generator configured to generate the foreground object data based on a result of the first detection operation and a result of the second detection operation.

Abstract: An information processing device includes: an outline extraction unit extracting an outline of a subject from a picked-up image of the subject; a characteristic amount extraction unit extracting a characteristic amount, by extracting sample points from points making up the outline, for each of the sample points; an estimation unit estimating a posture of a high degree of matching as a posture of the subject by calculating a degree of the characteristic amount extracted in the characteristic amount extraction unit being matched with each of a plurality of characteristic amounts that are prepared in advance and represent predetermined postures different from each other; and a determination unit determining accuracy of estimation by the estimation unit using a matching cost when the estimation unit carries out the estimation.

Abstract: This disclosure relates to a method and apparatus for implementing a trapping operation on a digital image during image processing and prorating the size of trap color filter with respect to local irregularity in shape of any target object. Some examples of the present disclosure calculate a plurality of prorated trapping parameters to be applied to portions of an object in a printing process, the calculation being based on repeated generation and application of a 2D Gaussian mask to a binarized object to identify disappeared portions of the object. The calculated plurality of prorated trapping parameters may be applied to the object during the printing process.

Abstract: Stereoscopic target region filling techniques are described. Techniques are described in which stereo consistency is promoted between target regions, such as by sharing information during computation. Techniques are also described in which target regions of respective disparity maps are completed to promote consistency between the disparity maps. This estimated disparity may then be used as a guide to completion of a missing texture in the target region. Techniques are further described in which cross-image searching and matching is employed by leveraging a plurality of images. This may including giving preference to matches with cross-image consistency to promote consistency, thereby enforcing stereo consistency between stereo images when applicable.

Abstract: The present invention uses invisible junctions which are a set of local features unique to every page of the electronic document to match the captured image to a part of an electronic document. The present invention includes: an image capture device, a feature extraction and recognition system and database. When an electronic document is printed, the feature extraction and recognition system captures an image of the document page. The features in the captured image are then extracted, indexed and stored in the database. Given a query image, the features in the query image are extracted and compared against those stored in the database to identify the query image. The feature extraction and recognition system of the present invention is integrated into a multifunction peripheral. This allows the feature extraction and recognition system to be used in conjunction with other modules to provide security and annotation applications.

Abstract: An image processing device and a method performed by a computer, the image processing device comprising: a processing unit configured to operate as an image acquisition unit configured to acquire an image; a similarity map generator configured to calculate, with a region constructed with one or a plurality of pixels in the image as a constituent unit, a first similarity map based on a first algorithm, the first similarity map representing a degree of similarity between the region and a marginal region of the image, and calculate a second similarity map based on a second algorithm, the second similarity map representing a degree of similarity between the region and the marginal region of the image; and a saliency map generator configured to integrate the first similarity map and the second similarity map to generate a saliency map.

Abstract: Techniques for detecting and recognizing text may be provided. For example, an image may be analyzed to detect and recognize text therein. The analysis may involve detecting text components in the image. For example, multiple color spaces and multiple-stage filtering may be applied to detect the text components. Further, the analysis may involve extracting text lines based on the text components. For example, global information about the text components can be analyzed to generate best-fitting text lines. The analysis may also involve pruning and splitting the text lines to generate bounding boxes around groups of text components. Text recognition may be applied to the bounding boxes to recognize text therein.

Abstract: In one or more embodiments described herein, there is provided a method of training an apparatus. The method trains the apparatus to automatically detect features of interest in an image. An image is received, the image being of at least one object for inspection, each image comprising a plurality of pixels. The image is segmented into a plurality of superpixels, each superpixel comprising a plurality of pixels which each have similar image data attributes to one another. The superpixels are classified into at least two classes in response to user input identifying at least one feature of interest in one or more of the super-pixels. From a library of image data attributes, a subset of image data attributes is determined that provides preferential discrimination between the at least two classes. The apparatus is then trained using said determined subset of image data attributes to thereby enable the apparatus to classify super-pixels of an image into the at least two classes.

Abstract: An information processing apparatus for converting image data created from an optically read manuscript to character data is provided. The information processing apparatus includes a data converting unit configured to convert the image data of a printed character printed beforehand on the manuscript and an added character added after the printed character has been printed to the character data; a character data distinguishing unit configured to distinguish, of the converted character data, between printed character data converted from the image data corresponding to the printed character and added character data converted from the image data corresponding to the added character; an edit information accepting unit configured to accept added character data edit information; and a character data edit unit configured to edit, according to the accepted added character data edit information, the distinguished added character data.

Abstract: A method for identifying facial features comprises following steps: An image tracing step is performed to receive video data of a plurality of face images and to obtain a real-time background image from the video data by a video tracing technique. A data calculating step is performed to calculate a video data difference between a current face image and the real-time background image. A process setting step is performed to set an iteration number according to the video data difference. A coordinate requesting step is performed to obtain facial feature coordinates of a previous face image, the previous one of the current face image, serving as initial facial feature coordinates. A localization step is performed to obtain current facial feature coordinates of the current image by conducting an iterative calculation according to the iteration number and based on the initial facial feature coordinates.

Abstract: An image processing device includes an image sequence acquisition section that acquires an input image sequence that includes first to N-th images, and a processing section that performs an image summarization process that deletes some of the first to Nth images to generate a summary image sequence, the processing section selecting an s-th (s is an integer that satisfies 0?s?N+1) image to be a provisional summary image, selecting a t-th (t is an integer that satisfies 0?t?s?1) image to be a provisional preceding summary image, selecting a u-th (u is an integer that satisfies t<u<s) image to be a determination target image, calculating a summarization interval evaluation value G(t, s) based on deformation information about the provisional summary image and the determination target image, and deformation information about the provisional preceding summary image and the determination target image, and performing the image summarization process.

Abstract: The system and method of the invention combines target image intensity into a maximum likelihood estimate (MLE) framework as in STAPLE to take advantage of both intensity-based segmentation and statistical label fusion based on atlas consensus and performance level, abbreviated iSTAPLE. The MLE framework is then solved using a modified expectation-maximization algorithm to simultaneously estimate the intensity profiles of structures of interest as well as the true segmentation and atlas performance level. The iSTAPLE greatly extends the use of atlases such that the target image need not have the same image contrast and intensity range as the atlas images.

Abstract: A method including segmenting an image into different segments, where the segmenting is based at least partially upon an estimate of blur of areas of the image; and changing the segmenting of two or more of the sections based, at least partially, upon color in the image.

Abstract: An embodiment provides a computer-implemented system and method for providing visual suggestions for cluster classification. One or more clusters comprising uncoded documents from a set are obtained. A different set of reference documents that are each classified with a code is designated. A cluster center in one of the clusters is identified. The cluster center is compared to one or more of the reference documents. Those of the reference documents that are similar to the cluster are identified based on the comparison. The classification codes of each of the similar reference documents are visually represented as a suggestion for assigning one of the classification codes to the cluster.

Abstract: Embodiments of the present application relate to an image index generation method, system, a device, and a computer program product. An image index generation method is provided. The method includes selecting an image included in an image library for which an image index is to be generated, determining at least one target region included in the image, extracting visual features from the determined at least one target region, determining a similarity value of the selected image and image included in the image library based on the extracted visual features, determining image categories to which the images belong to based on the determined similarity values among the images, and assigning category identifiers to the images in accordance with an identifier assignment method, the identifier assignment method assigns the same category identifiers to images belonging to the same image category, and different category identifiers to images belonging to different image categories.

Abstract: A document authentication method determines the authenticity of a target hardcopy document, which purports to be a true copy of an original hardcopy document. The method compares a binarized image of the target document with a binarized image of the original document which has been stored in a storage device. The image of the original document is generated by binarizing a scanned grayscale image of the original document. Halftone and non-halftone text areas in the grayscale image area separated, and the two types of text are separately binarized. The non-halftone text areas are then down-sampled. During authenticating, a scanned grayscale image of the target document is binarized by separating halftone and non-halftone text areas and binarizing them separately, and then down-sampling the non-halftone text areas. The binarized images of the target document and the original document are compared to determine the authenticity of the target document.

Abstract: The description relates to sentence autocaptioning of images. One example can include a set of information modules and a set of sentence generation modules. The set of information modules can include individual information modules configured to operate on an image or metadata associated with the image to produce image information. The set of sentence generation modules can include individual sentence generation modules configured to operate on the image information to produce a sentence caption for the image.

Abstract: An apparatus and user interface (155) for aiding in navigating and modifying delineations (117a-c) in or associated with 2D sub-volumes (110a-c) of a 3D or higher dimensional image dataset (100). States and position of the sub-volumes visualized. Both, states and position can be changed by using the functionalities of the user interface generated (155) by said apparatus. The apparatus can be used in medical image post-processing system.

Abstract: This invention provides a system, method and computer-readable medium for detecting and localizing organs and other regions of interest in medical image data provided by a medical imaging procedure using gradient template information with respect to an example of the imaged organ and cross-correlation techniques to generate object detection information. In an embodiment, the detection and localization process/processor receives a plurality of gradient templates and employers a template with the closest matching cross-correlation to the gradient of the organ in the medical image.

Abstract: A web development, application development, or other tool can be enhanced by configuring the tool to support an overlay for defining a plurality of regions (i.e. slices) simultaneously. Embodiments include providing, via a computing apparatus, a graphical user interface comprising an overlay over the area of a visual element, the graphical user interface configured to define from one to nine adjustable slices, with each slice corresponding to a respective region or component of the visual element. The method can comprise associating a default repetition behavior with each slice based on its relative position in the overlay and receiving input via the overly and adjusting a characteristic of at least one slice, the adjusted characteristic comprising a size or position of the slice. The default and/or adjusted characteristics can be used to generate HTML, CSS, and/or other code for providing the desired scaling behavior for the visual component.

Abstract: Embodiments described herein use depth images to extract user behavior, wherein each depth image specifies that a plurality of pixels correspond to a user. In certain embodiments, information indicative of an angle and/or curvature of a user's body is extracted from a depth image. This can be accomplished by fitting a curve to a portion of a plurality of pixels (of the depth image) that correspond to the user, and determining the information indicative of the angle and/or curvature of the user's body based on the fitted curve. An application is then updated based on the information indicative of the angle and/or curvature of the user's body. In certain embodiments, one or more average extremity positions of a user, which can also be referred to as average positions of extremity blobs, are extracted from a depth image. An application is then updated based on the average positions of extremity blobs.

Abstract: When using a graph cut process for binary labeling, labeling unit selects N (>3) pixels in image data in such a manner to represent a predetermined shape in the image, minimize the high-order energy of the Nth order or greater in which the pixel values of the N pixels are variables, and performs labeling.

Abstract: Certain embodiments provide a computer system for determining a registration mapping between a novel medical image and a reference medical image, the computer system comprising: a storage system adapted to store data representing the novel medical image and the reference medical image and variance data for a plurality of different locations in the reference medical image representing a statistical variation for corresponding locations identified in a plurality of training medical images; and a processor unit operable to execute machine readable instructions to determine a registration mapping between the novel medical image and the reference medical image in a manner that takes account of the variance data for the plurality of different locations in the reference medical image.

Abstract: Hybrid image projection systems and methods can superimpose image components of an input image. An input image can be divided into smaller regions and at least one parameter of each region can be determined. The input image can be decomposed based on the parameter of each region into multiple, less correlated, orthogonal or quasi-orthogonal image components. Each projector can display respective image components so that the images projected may be optically superimposed on a screen. The superposition of orthogonal or quasi-orthogonal image components can result in superposition of images in an existing multi-projector image systems being more insensitive to inter-projector image misalignment. Superimposing orthogonal or quasi-orthogonal images can be used to avoid visible image degradation, and provide more robust image quality in a multiple projector system implementation.

Abstract: According to an aspect of the present invention, an image processing method for extracting a pixel having a specific feature includes: extracting pixels representing an object, to which the pixel having the specific feature belongs, from a given input image based on an image feature other than color; extracting principal colors from the pixels; selecting, from a plurality of pre-trained color distribution models deposited in a repository, a color distribution model closest in distance metric, which indicates distance relative to the extracted principal colors, to the extracted principal colors by performing a search through the repository using the extracted principal colors; and segmenting the input image by categorizing pixels in the input image using the selected color distribution model.

Abstract: According to one aspect, a method of previewing multimedia data, including selecting a first graphical representation in association with a multimedia object, displaying the first graphical representation, receiving an input in relation to the first graphical representation, in response to the input, determining whether to change the first graphical representation, and if so then selecting a second graphical representation from the multimedia object in a randomized manner, and displaying the second graphical representation.

Abstract: Techniques are described to employ image recognition techniques to content. In an implementation, one or more images are identified in content using a signature derived from the one or more images. Metadata associated with the content is then supplemented based on the identified one or more images.

Abstract: The present invention provides a method and an apparatus for detecting a traffic monitoring video. The method comprises: determining a background reference model; determining a target area image in the traffic monitoring video according to the background reference model; updating the background reference model by using the target area image; summating all target points in detection area of each frame of image in the traffic monitoring video according to the updated background reference model to obtain a total area of all the target points; segmenting the frame with the biggest total area to obtain a target area at the best position; and extracting vehicle information from the target area at the best position. By using the present invention, the accuracy of a detection result in a complex environment may be improved.

Abstract: An image region extraction device for extracting a target region on the basis of a designated region with high precision. An image region extraction device (100) extracts a target region from an image on the basis of a designated region and is provided with: a spatial change learning unit (180) for acquiring, for each section of the image, a pixel value changing pattern which is a characteristic of the spatial changes in a pixel value component, and a distance changing pattern which is a characteristic of the spatial changes in a distance component extending from a reference position to a photographic object; and a region dividing unit (210) for extracting a target region on the basis of the similarities between the pixel value changing pattern and the distance changing pattern among the designated region and each section of the image.

Abstract: A method for providing a content based on a user's preference(s) includes analyzing meta-data information of a pre-stored content, determining at least one preference based on the analyzed meta-data information, transmitting the at least one preference to a content-providing server; searching, at the content-providing server, for at least one content corresponding to the at least one preference, extracting general information of at least one content found to correspond to the at least one preference and transmit the general information to the portable terminal.

Abstract: An image processing apparatus is provided. The apparatus includes: a processor configured to process an image according to a preset process in response to receiving the image; and a controller configured to control the processor in order to detect a figure of a human within a video frame based on a feature vector data value according to histograms of oriented gradients (HOG) algorithm of the video frame of the image input to the processor, wherein the controller divides the video frame into a foreground corresponding to a region which includes a moving object and a background corresponding to a region which excludes the foreground, removes the background, converts a target region having a preset area including at least a part of the foreground without the background into a binary image, and derives the feature vector data value from the binary image using a lookup table.

Abstract: A panel view module receives a comic comprising one or more pages, which comprise one or more panels. The panel view module may identify candidate comic panels and determine confidence levels for the candidate comic panels. The panel view may also generate a panel view for the comic based on the confidence levels for the candidate comic panels.

Abstract: An information processing apparatus includes a network creating unit that creates a network in which respective characters of plural character recognition results are represented as nodes, and in which nodes of adjacent character images are connected with a link, a first determining unit that determines a first candidate boundary in the network, a second determining unit that determines a second candidate boundary different from the first candidate boundary in the network, and an extracting unit that extracts, as to-be-searched objects, plural candidate character strings from a set of candidate character strings each formed of nodes between the first candidate boundary and the second candidate boundary.

Abstract: Methods for removing vertical and horizontal lines from a document image. The horizontal line removal method includes: for a column of black pixels at each horizontal position along the line, removing them if their maximum stroke width is less than the median value of maximum stroke widths in a small window centered at that horizontal position; Remove connected components remaining in the horizontal line bounding box that do not extend significantly above or below the bounding box boundaries; and Perform closing operation to join broken pieces of character strokes caused by underline removal. This method preserves character strokes while removing underlines. The vertical line removal method includes: for vertical lines that have large height to width ratio, remove parts of such lines that are not at intersection of with horizontal or near-horizontal lines; remove all remaining connected components that touch neither left nor right boundary of the bounding box.

Abstract: Embodiments are directed towards determining within a digital camera whether a pixel belongs to a foreground or background segment within a given image by evaluating a ratio of derivative and deviation metrics in an area around each pixel in the image, or ratios of derivative metrics across a plurality of images. For each pixel within the image, a block of pixels are examined to determine an aggregate relative derivative (ARD) in the block. The ARD is compared to a threshold value to determine whether the pixel is to be assigned in the foreground segment or the background segment. In one embodiment, a single image is used to determine the ARD and the pixel segmentation for that image. Multiple images may also be used to obtain ratios of a numerator of the ARD, useable to determine an extent of the foreground.

Abstract: A method for removing false foreground image content in a foreground detection process performed on a video sequence includes, for each current frame, comparing a feature value of each current pixel against a feature value of a corresponding pixel in a background model. The each current pixel is classified as belonging to one of a candidate foreground image and a background based on the comparing. A first classification image representing the candidate foreground image is generated using the current pixels classified as belonging to the candidate foreground image. The each pixel in the first classification image is classified as belonging to one of a foreground image and a false foreground image using a previously trained classifier. A modified classification image is generated for representing the foreground image using the pixels classified as belonging to the foreground image while the pixels classified as belonging to the false foreground image are removed.