Abstract: An image processing method includes a segmentation step that segments an input image into a plurality of regions by using an automatic segmentation algorithm, and a computation step that calculates a saliency value of one region of the plurality of segmented regions by using a weighted sum of color differences between the one region and all other regions. Accordingly, it is possible to automatically analyze visual saliency regions in an image, and a result of analysis can be used in application areas including significant object segmentation, object recognition, adaptive image compression, content-aware image resizing, and image retrieval.

Abstract: A method and system for adaptive discriminant learning and measurement fusion for image based catheter tracking is disclosed. An adaptive discriminant model is trained online based on a tracked object, such as a pigtail catheter tip, in at least one previous frame of a fluoroscopic image sequence. The object is tracked in the current frame of the fluoroscopic image sequence based at least on the adaptive discriminant model trained online. The object may be tracked in the current frame based on a fusion of three types of measurement models including the adaptive discriminant model trained online, an object detection model trained offline, and an online appearance model.

Abstract: A method and system for segmentation and removal of pulmonary arteries, pulmonary veins, and a left atrial appendage from 3D medical image data, such as 3D computed tomography (CT) volumes, is disclosed. A global shape model is segmented for each of pulmonary arteries, pulmonary veins, and a left atrial appendage in a 3D volume. The segmented global shape model for each of the pulmonary arteries, pulmonary veins, and left atrial appendage is locally refined based in local voxel intensities in the 3D volume, resulting in a respective mask for each structure. The mask is used to remove voxels belonging to the pulmonary arteries, pulmonary veins, and left atrial appendage from the 3D volume in order to better visualize coronary arteries and bypass arteries.

Abstract: In embodiments of the present invention improved capabilities are described for producing background separated product images for print and on-line display. An image formation system provides lighting of a product to facilitate acquiring images that can be automatically processed to generate high resolution item-only images free of quality defects and imaging artifacts. Image processing programs accurately detect an outline of an item in a set of digital images taken using the image formation system and automatically store processed images in an image library. The images in the library may be repurposed for print, sales display, transmission to a user, on-line customer support, and the like. A user display configured with an adaptable user interface facilitates user interaction with images in the library.

Abstract: A camera system (10) is provided for generating an image presegmented into regions (106a-b) of interest and of no interest, having an evaluation unit (20) which is designed to divide the raw image into part regions (106a-b) to calculate a contrast value for each part region (106a-b) and to decide with reference to the contrast value whether the respective part region (106a-b) is a region of interest (106a) or a region of no interest (106b). In this respect, the evaluation unit (20) has a preprocessing unit (22) which is implemented on an FPGA, which respectively accesses the pixels of a part region (106a-b) and generates summed values (a), b) for the respective part region (106a-b) and has a structure recognition unit (24) which calculates the contrast value of the part region (106a-b) from its summed values (a, b) without accessing pixels of the part region (106a-b).

Abstract: Video frames of a baseball game are analyzed to determine a track for the participants in the game and to update a digital record of the game. The merging of participants in a video frame is resolved by associating the participants' tracks before and/or after the merging with a most likely participant role, such as a player, coach or umpire role. The role of one merged participant can be used to deduce the role of the other merged participant. In this way, the digital record can be completed even for the merged period. The role of a participant can be based, e.g., on the location of the participant relative to a base, a coach's box region, a pitcher's mound, a dugout, or a fielding position, or by determining that a participant is running along a path to a base or performing some other movement.

Abstract: This invention is a method for rectifying an input digital image including warped textual information. The method includes analyzing the input digital image to locate a plurality of local features, at least some of the local features including textual features. A sparse set of local image regions are located corresponding to reliable combinations of spatially-consecutive local features, and corresponding local orientations are determined. A global deformation function is formed by interpolating between the determined local orientations and is used to form a rectified image.

Abstract: A computer implemented method for modifying a digital image comprising identifying two or more individual regions in the digital image that each include a human face, and digitally defining at least one combined region that includes the two or more individual regions wherein at least one border of the at least one combined region is collinear with a border of one of the individual regions.

Abstract: An embodiment of the invention provides a method for sharing digital images on an image-sharing application, wherein a digital image is received from a user, the digital image including a first access setting defined by the user. A user-defined select region is identified on the digital image with a processor, wherein the select region includes a second access setting. Access to the digital image is permitted with an access controller based on the first access setting; and, access to the select region is permitted with the access controller based on the second access setting. In at least one embodiment, the digital image is displayed only to a first group of individuals based on the first access setting; and, the select region is displayed only to a second group of individuals based on the second access setting.

Abstract: A system and method uses an image manipulating application to define in an object image a plurality of discrete cells. Predefined image information is substituted for image information in selected ones of the plurality of discrete cells to form a translated version of the object image. The translated version of the object image may then be provided to an image recognition capable search engine to obtain search results.

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

Abstract: A method and system for identifying existence and occurrence of a contour. The contour presence can be identified by taking a second derivative of a color space (e.g., L*, a*, and b*) value of a rendered image derived utilizing an ICC profile that models behavior of a MFD as a smoothness metric. A moving average filter can be applied to minimize an extraneous peak and trough in the second derivative that can be contributed to noise. The contour can be detected if a filtered second derivative lies outside a given range. The location of the contour can be identified by matching up an input value with corresponding input value of the image. A probability of the contour being visible in a rendered output can be then determined by separately analyzing the color space values. The occurrence and location of contour can be displayed on a user interface to quickly and clearly identify the contour in the image without making physical prints and with minimal human interaction and expenditure.

Abstract: A device is disclosed for determining and visualizing the perfusion of the myocardial muscle with the aid of static CCTA images. In at least one embodiment, the device includes a segmentation unit for segmenting the coronary blood vessels and the left myocardial muscle from a CCTA image of the heart; a first simulation unit for simulating the blood flow through the coronary blood vessels; and a second simulation unit by which the local perfusion of the myocardial muscle is determined on the basis of the ascertained blood flow into different regions of the myocardial muscle. The perfusion of the different regions of the myocardial muscle is visualized in a schematized image on a visualization unit. By virtue of the proposed device it is possible to dispense with further imaging examinations after the performance of a CCTA scan, thereby relieving the pressure both on the part of the physician and on the part of the patient.

Abstract: A method (100) and system (300) is described for processing video data comprising a plurality of images. The method (100) comprising obtaining (104, 106), for each of the plurality of images, a segmentation in a plurality of regions and a set of keypoints, and tracking (108) at least one region between a first image and a subsequent image resulting in a matched region in the subsequent image taking into account a matching between keypoints in the first image and the subsequent image. The latter results in accurate tracking of regions. Furthermore the method may optionally also perform label propagation taking into account keypoint tracking.

Abstract: First and second images are captured at first and second focal lengths, the second focal length being longer than the first focal length. Element sets are defined with a first element of the first image and a corresponding second element of the second image. Element sets are identified as background if the second element thereof is more in-focus than or as in-focus as the first element. Background elements are subtracted from further analysis. Comparisons are based on relative focus, e.g. whether image elements are more or less in-focus. Measurement of absolute focus is not necessary, nor is measurement of absolute focus change; images need not be in-focus. More than two images, multiple element sets, and/or multiple categories and relative focus relationships also may be used.

Abstract: In embodiments of image layers navigation, a canvas interface displays image segments of an image in different layers of the image. An image layers application is implemented to receive a position input of a canvas viewer control that encompasses one or more of the image segments of the image, and then determine the layers of the image that correspond to the image segments encompassed by the canvas viewer control. The position input of the canvas viewer control is effective to select the layers of the image that correspond to the one or more image segments encompassed by the canvas viewer control. Thumbnail images are then displayed that each represent one of the layers encompassed by the canvas viewer control, where each of the layers represented by a thumbnail image are displayed to include the image segments associated with a respective layer of the image.

Abstract: First and second images are captured at first and second focal lengths, the second focal length being longer than the first focal length. Element sets are defined with a first element of the first image and a corresponding second element of the second image. Element sets are identified as background if the second element thereof is more in-focus than or as in-focus as the first element. Background elements are subtracted from further analysis. Comparisons are based on relative focus, e.g. whether image elements are more or less in-focus. Measurement of absolute focus is not necessary, nor is measurement of absolute focus change; images need not be in-focus. More than two images, multiple element sets, and/or multiple categories and relative focus relationships also may be used.

Abstract: An apparatus and method for video fingerprinting are provided. The method includes, for each frame of a video sequence including a plurality of frames, removing a portion of the frame, dividing a remaining portion of the frame into blocks, dividing each block into sub-blocks, computing a block level feature as a mean of pixels in each sub-block within the block, concatenating all block level features in the frame, and concatenating features of all frames in the video sequence.

Abstract: Embodiments of the present invention provide techniques for retrieving and displaying multimedia information. According to an embodiment of the present invention, a graphical user interface (GUI) is provided that displays multimedia information that may be stored in a multimedia document. According to the teachings of the present invention, the GUI enables a user to navigate through multimedia information stored in a multimedia document. The GUI provides both a focused and a contextual view of the contents of the multimedia document.

Abstract: A method for separating foreground and background contents in a document image is provided. The method first computes a pixel-wise map of maximal local features (e.g., local variance, local contrast, etc.), which is binarized to generate a mask for potential foreground. In order to utilize color information effectively, the local feature map is computed using all color channels of the image. Then the background image is obtained by inpainting the mask regions from the non-mask regions of the original document image. Adaptive thresholding is applied to the difference between the original document image and the background image to obtain the binary foreground image. Post-processing of the binary foreground image can further remove undesirable elements. Finally, a more accurate background image can be obtained by inpainting the original document image using the binary foreground image as a mask.

Abstract: There are provided methods and systems for use in performing feature sensitive captioning of media content. In one implementation, such a method includes detecting an aesthetically determinative feature of a media content unit selected by a user, and determining a captioning aesthetic for a caption of the media content unit based at least in part on the aesthetically determinative feature. The captioning aesthetic may include a background aesthetic and a text aesthetic. The captioning aesthetic may be utilized by a feature sensitive captioning application to produce a feature sensitive caption for the media content unit.

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

Abstract: Embodiments of the present disclosure include methods, apparatuses, and systems for identifying regions to be filtered during processing of an image. A map generator is configured to receive pixels of an image and to determine a map for the image. The map indicates a number of islands within blocks of pixels of the image, where individual ones of the islands include either a single dark pixel, or two or more contiguous dark pixels, bordered by light pixels and/or one or more edges of the blocks of pixels. An index generator sets, based at least on the number of islands within the individual ones of the blocks of pixels that correspond to regions of the scanned image, filter indices for the regions of the scanned image. An image filter component, based on the filter indices, filters the regions of the scanned image.

Abstract: In the image processing apparatus, image data is divided into large blocks of a prescribed size and the large blocks are subdivided into small blocks by the dividing unit. The number of isolated points in each large block is then calculated by the large block isolated point calculation unit, and the number of isolated points in each small block is then calculated by the small block isolated point calculation units. It is then determined by the halftone-dot region determination unit whether or not the large block is a halftone-dot region. This determination considers both the number of isolated points in the large block and the number of isolated points in each small block.

Abstract: According to one embodiment, a system stores a plurality of contents in a storage medium, each content includes handwritten data including stroke data corresponding to strokes which are handwritten, image data corresponding to the strokes, and retrieval information for retrieving the handwritten data. The system provides, upon receiving a retrieve request including a character string from a terminal, to the terminal either the handwritten data in the content corresponding to first retrieval information, the first retrieval information corresponding to the character string from among retrieval information of the plurality of contents, or the image data in the content corresponding to the first retrieval information.

Abstract: A reference character is generated by combining part objects prepared for each site. At least one candidate character object is generated by changing at least one part object among the part objects used in the reference character object. The reference character object and the candidate character object are displayed by a display device, and an input for selection from a user is accepted. Next, a site for which different part objects are used between the selected character object and the reference character object is determined. A new character object is generated by changing the part object used for the determined site with priority. The selected character object is displayed as the reference character, and the newly generated character is displayed as the candidate character.

Abstract: An image processing device of the present invention acquires the positional information of a boundary line for a case where a first image is segmented into a foreground and a background by a segmentation processing section that segments an image into a foreground and a background, and controls the segmentation processing section to segment a second image having a predetermined relationship with the first image by use of the positional information of the acquired boundary line.

Abstract: A method for error correction for segmented three dimensional image data. The method includes receiving segmented three dimensional image data, the segmented three dimensional image data being divided into a plurality of slices; correcting at least one contour of the segmented three dimensional image data on at least one slice according to a command from a user to form a corrected contour; and automatically interpolating a correction represented by the corrected contour to a plurality of slices of the segmented three dimensional image data.

Abstract: Techniques for segmenting an object are provided. The techniques include capturing an image of an object, dividing the image into one or more blocks, computing a confidence value for each of the one or more blocks, and eliminating one or more blocks from consideration based on the confidence value for each of the one or more blocks.

Abstract: A method for representing a video sequence including a time sequence of input video frames, the input video frames including some common scene content that is common to all of the input video frames and some dynamic scene content that changes between at least some of the input video frames. Affine transform are determined to align the common scene content in the input video frames. A common video frame including the common scene content is determined by forming a sparse combination of a first basis functions. A dynamic video frame is determined for each input video frame by forming a sparse combination of a second basis functions, wherein the dynamic video frames can be combined with the respective affine transforms and the common video frame to provide reconstructed video frames.

Abstract: The present invention converts an image into a transparency, or “foreground image”, on which the readability of text and other detail is preserved after compositing with a background, while maintaining color information of broad areas of the image.

Abstract: Disclosed is a method for identifying lawn grass which includes capturing an image of the terrain in front of a mower, segmenting the image into neighborhoods, calculating at least two image statistics for each of the neighborhoods, generating a binary representation of each image statistic. The binary representation of each image statistic is generated by comparing the calculated image statistic values to predetermined image statistic values for grass. The method further includes weighting each of the binary representations of each image statistic, and summing corresponding neighborhoods for all image statistics. A binary threshold is applied to each of the summed neighborhoods to generate a binary map representing grass containing areas and non-grass containing areas.

Abstract: An apparatus, computer-readable medium, and computer-implemented method for identifying, classifying, and utilizing object information in one or more image includes receiving an image including a plurality of objects, segmenting the image to identify one or more objects in the plurality of objects, analyzing the one or more objects to determine one or more morphological metrics associated with each of the one or more objects, determining the connectivity of the one or more objects to each other based at least in part on a graphical analysis of the one or more objects, and mapping the connectivity of the one or more objects to the morphological metrics associated with the one or more objects.

Abstract: A method for estimating signal-dependent noise includes defining a plurality of pixel groups from among the image pixels. The method further includes computing, for one or more signal levels of the image, a difference value between two pixel groups, whereby a respective one or more difference values are computed collectively. The method determines an estimated noise response of the image as a function of the one or more computed difference values.

Abstract: An image processing device, method and program in which a feature point derivation unit derives a plurality of characteristic points in an input moving image. A tracking subject feature point setting unit sets a feature point within a tracking subject, from the characteristic points. A background feature point setting unit sets a group of background feature points from the characteristic points. The background feature points are not located within the tracking subject. A motion detection unit detects movement over time of the background feature points. A clip area setting unit sets a size and a position of a clip area of an image to be employed which includes the feature point within the tracking subject, on the basis of the movement of the feature point within the tracking subject and the movement of the background feature points, when the motion detection unit detects movement of the background feature points.

Abstract: A method for determining a scene boundary location dividing a first scene and a second scene in an input video sequence. The scene boundary location is determined responsive to a merit function value, which is a function of the candidate scene boundary location. The merit function value for a particular candidate scene boundary location is determined by representing the dynamic scene content for the input video frames before and after candidate scene boundary using sparse combinations of a set of basis functions, wherein the sparse combinations of the basis functions are determined by finding a sparse vector of weighting coefficients for each of the basis functions. The weighting coefficients determined for each of the input video frames are combined to determine the merit function value. The candidate scene boundary providing the smallest merit function value is designated to be the scene boundary location.

Abstract: Various embodiments of the present invention relate to a method, system and computer program product for detecting and recognizing text in the images captured by cameras and scanners. First, a series of image-processing techniques is applied to detect text regions in the image. Subsequently, the detected text regions pass through different processing stages that reduce blurring and the negative effects of variable lighting. This results in the creation of multiple images that are versions of the same text region. Some of these multiple versions are sent to a character-recognition system. The resulting texts from each of the versions of the image sent to the character-recognition system are then combined to a single result, wherein the single result is detected text.

Abstract: An image processing apparatus includes a receiving unit that receives an image; a separating unit that separates a first area from the received image; an extracting unit that extracts a second area of a color having a predetermined relationship in the separated first area; an acquiring unit that acquires the characteristic relating to the shape of the extracted second area; a first determining unit that determines whether or not the second area is plain, on the basis of the acquired characteristic; and a second determining unit that determines, as the property of the first area, whether the first area is a continuous-tone area, a plain area, or a composite area including a continuous-tone area and a plain area, on the basis of the ratio of the second area determined to be plain to the separated first area.

Abstract: An apparatus for detecting an error in a contour of a lesion includes an extracting unit configured to extract a contour of a lesion in each of a plurality of two-dimensional image frames that form a three-dimensional image, and an error determining unit configured to determine a presence or an absence of an error in a contour of a lesion in a target image frame of the two-dimensional image frames based on estimation information about the lesion in the target image frame and/or an energy value that corresponds to the contour of the lesion in the target image frame.

Abstract: A system and method of assigning diacritics in an electronic image using optical character recognition (OCR) is disclosed. In one example, the method comprises analyzing, by a computer system, the electronic image to generate a plurality of bounding blocks associated with text lines within the electronic image. The method further comprises establishing a plurality of bounding boxes for diacritics and base text with the electronic image. The method also comprises determining a distance from a diacritic to a nearest base text character and a nearest text line. The method also comprises evaluating a base box distance and the nearest text line distance to assign the diacritic to a correct text line in the electronic image.

Abstract: An image capture application captures a sequence of images via a digital camera. The sequence of images may have undesirable levels of blurriness due to the motion of objects in the field of view of the digital camera or due to movement of the digital camera itself. A deblur engine within the image capture application generates image segments within one of the captured images, where a given image segment includes pixel values that move coherently between different images in the sequence. The deblur engine then deblurs each image segment based on the coherent motion of each different image segment and combines the resultant, deblurred image segments into a deblurred image. Advantageously, blurriness caused by the combined effects of moving objects and camera motion may be reduced, thereby improving the ability of a digital camera to provide high-quality images.

Abstract: A method and apparatus are provided for segmenting an object in an image. The method includes obtaining a first image including the object; receiving an input signal including information about a predetermined position in the first image; selecting at least one pixel included in the first image, based on the position information; generating a second image by dividing the first image into several areas, using the selected at least one pixel; and segmenting the object in the first image by using the first image and the second image.

Abstract: A content application determines images of an article for extraction. The content application identifies an initial image associated with a content of the article. A caption and a credit line associated with the initial image is detected and the initial image is extracted along with the caption and the credit line. A second image of the article associated with a video is also detected and extracted along with the video. In addition, the content application extracts a slideshow detected within the article.

Abstract: A method is described for determining eye location on a frontal face digital image in order to validate the frontal face as such and determine points of reference. The method consists of the following steps: obtain a frontal face digital image that is W pixels wide and H pixels high in grayscale, where the top left vertex of the digital image is considered to be the reference source; detect each eye, starting from a search subimage of the frontal face digital image, delivering approximate coordinates if both eyes have been detected, or an arbitrary predetermined value to indicate no eye detection; locate the iris of each eye, if both eyes have been detected, starting from the approximate coordinates, validating the frontal face digital image by delivering eye positions; or, validate the frontal face digital image if one or both eyes have not been detected by submitting a search subimage defined by an area resulting from centering a square of area L in the original image, where L=0.

Abstract: A system and method to capture an image of an oncoming target vehicle and localize the windshield of the target vehicle. Upon capturing an image, it is then analyzed to detect certain features of the target vehicle. Based on geometrical relationships of the detected features, the area of the image containing the windshield of the vehicle can then be identified and localized for downstream processing.

Abstract: A method for processing an image to generate a signature which is characteristic of a pattern within said image. The method comprising receiving an image; overlaying a window at multiple locations on said image to define a plurality of sub-images within said image, with each sub-image each having a plurality of pixels having a luminance level; determining a luminance value for each said sub-image, wherein said luminance value is derived from said luminance levels of said plurality of pixels; and combining said luminance values for each of said sub-images to form said signature. Said combining is such that said signature is independent of the location of each sub-image. A method of creating a database of images using said method of generating signatures is also described.

Abstract: An electronic device and an image processing method in the electronic device are provided. The electronic device includes a display unit configured to display an image; and a controller configured to correct an outline according to a drawing input with a correction scheme on the image and to crop the image within the corrected outline according to the corrected outline.

Abstract: A method of analyzing a medical image, where the medical image comprises one or more than one region of interest, and where the method comprises a) providing the medical image comprising a set of actual image values; b) rescaling the actual image values to produce corresponding rescaled image values and to produce a rescaled image from the rescaled image values; c) deriving a histogram of the rescaled image values; d) using the histogram to derive an adaptive segmentation threshold; e) using the adaptive segmentation threshold to recursively split the rescaled image; f) terminating the recursive splitting of the sub(sub) images using one or more than one predetermined criteria; and g) identifying one sub(sub) image in the terminated Hierarchical Region Splitting Tree which comprises the region of interest.

Abstract: A video is segmented to produce volumetric video regions. Descriptors are created for the video regions. A region graph is created for the video, where the region graph has weighted edges incident to video regions and the weight of an edge is calculated responsive to the descriptors of the video regions incident to the edge. The region graph is segmented responsive to the weights of the edges incident to the video regions to produce a new region graph having new volumetric video regions comprised of merged video regions of the first region graph. The descriptions of the region graphs are stored in a data storage.

Abstract: Methods and apparatus are disclosed to automatically detect vertebrae boundaries in a spine image. A method to detect a vertebra in a spine image is described, the method comprising generating a rectangle approximation of a reference vertebra. The method also including identifying a mask similar to the rectangle approximation and labeling a mask region in the mask. The method also including comparing the mask region to the rectangle approximation and detecting a vertebra in the spine image based on the comparison.