Abstract: An embodiment of the invention provides a method and apparatus for registering two medical images with one another. A first medical image including a representation of a biological organ of a subject or for a population is obtained and the surface of the organ is identified in the first medical image. The identified surface is then used to construct a 3D geometric surface model of the organ. The geometric model is used to derive a motion model that incorporates information on the physical material properties of the organ and external forces that cause the organ to move and deform. A second medical image including a representation of the organ of the subject (or another subject, in the case that the first medical image is an atlas image) is obtained and an alignment is determined between a first surface normal vector field for the organ surface, derived from the geometric model, and a second surface normal vector field for the organ surface, derived by filtering the second medical image.

Abstract: A method, an apparatus and a computer program for transferring scan geometry between a first region and a second region, similar to the first region includes identifying the first and second regions in an overview image, followed by determining of the first scan geometry corresponding to the first region. Then, the first scan geometry is transferred into the second scan geometry corresponding to the second region using information on geometrical correspondence between the first and second regions. The transferring includes establishing corresponding mappings between similar regions and their respective scan geometries.

Abstract: Systems for processing digital check image files include an image classification module programmed to review a plurality of attributes associated with a digital check image file including at least one check image, and to categorize the digital check image file into at least one category of a plurality of categories, and a decision module programmed to decide how to process the digital check image file based on the category.

Abstract: The present invention relates to automated document processing and more particularly, to methods and systems for document image capture and processing using mobile devices. In accordance with various embodiments, methods and systems for document image capture on a mobile communication device are provided such that the image is optimized and enhanced for data extraction from the document as depicted. These methods and systems may comprise capturing an image of a document using a mobile communication device; transmitting the image to a server; and processing the image to create a bi-tonal image of the document for data extraction. Additionally, these methods and systems may comprise capturing a first image of a document using the mobile communication device; automatically detecting the document within the image; geometrically correcting the image; binarizing the image; correcting the orientation of the image; correcting the size of the image; and outputting the resulting image of the document.

Abstract: A system for determining at least one characteristic of wood furnish from an upstream source. The system includes: an inclined panel comprising a transparent window having a top surface for the wood furnish to slide down; a lighting means adjacent the transparent window for lighting the wood furnish visible through a bottom surface of the window; an image capturing means adjacent the transparent window for capturing an image of the wood furnish visible through the bottom surface of the window; and a processing means in communication with the image capturing means for deriving from the captured images the at least one characteristic of the wood furnish.

Abstract: The present invention provides a model image acquisition support apparatus, a model image acquisition support method, and a model image acquisition support program that can easily and swiftly obtain an optimum model image for an image processing apparatus that performs matching processing based on a model image set in advance with respect to a measurement image that is obtained by imaging an object. A plurality of model image candidates, serving as candidates for model image, are extracted from a reference image obtained by imaging an object which can be a model. Matching processing with the plurality of extracted model images is executed on measurement images actually obtained by a visual sensor, so that trial results are obtained. A trial result is generated upon evaluating each of the trial results of the matching processing with the model image. An optimum model image is determined based on the evaluation result.

Abstract: A visual inspection method and apparatus detecting a defect with the use of a detected signal obtained by illuminating one of a light and an electron beam onto a substrate to be inspected. The visual inspection method and apparatus includes calculation of an image feature based on an image of the detected defect, calculation of a coordinate feature based on position information of the detected defect, and outputting of real defect information by performing false alarm judgment by processing with respect to one of the image feature and the coordinate feature.

Abstract: An apparatus for the detection of a geometrical position of plastics material containers, for example, plastics material pre-forms, having a base member and a thread region may include an image-recording device, which records a locally resolved image of the plastics material container. The image-recording device is arranged in such a way that it observes the plastics material container substantially along its longitudinal direction. The apparatus includes an illumination device, which illuminates at least one region of the plastics material container observed by the image-recording device, and an evaluation device, which on the basis of an image recorded by the image-recording device determines a rotary setting of the plastics material container with respect to its longitudinal direction.

Abstract: Methods of monitoring critical dimensions in a semiconductor fabrication process include capturing at least one image of a first structure that has an effect on the polarization state of light reflected therefrom. For at least some of the first structure images, a value is calculated indicative of intensity of light reflected from the first structure. A critical dimension of the first structure is obtained and correlated with the calculated value. At least one image of a subsequent structure is captured. A determination is made, based at least in part on the calculated value, of a critical dimension of the subsequent structure.

Abstract: A method is provided for imaging a workpiece by capturing successive frames of an elongate stationary field of view transverse to a workpiece transit path of a robot, while the workpiece is transported by the robot. The robot transit path is illuminated with an elongate illumination pattern transverse to the transit path to obtain a workpiece image of successive frames. Motion-induced image distortion is prevented or reduced adjusting the camera frame rate in real time in proportion to changes in robot velocity profile of the workpiece along the transit path.

Abstract: Embodiments include methods, systems, and/or devices that may be used to image, obtain three-dimensional information from a scence, and/or locate multiple small particles and/or objects in three dimensions. A point spread function (PSF) with a predefined three dimensional shape may be implemented to obtain high Fisher information in 3D. The PSF may be generated via a phase mask, an amplitude mask, a hologram, or a diffractive optical element. The small particles may be imaged using the 3D PSF. The images may be used to find the precise location of the object using an estimation algorithm such as maximum likelihood estimation (MLE), expectation maximization, or Bayesian methods, for example. Calibration measurements can be used to improve the theoretical model of the optical system. Fiduciary particles/targets can also be used to compensate for drift and other type of movement of the sample relative to the detector.

Abstract: According to one embodiment, a three-dimensional object determining apparatus includes: a detecting unit configured to detect a plurality of feature points of an object included in an image data that is acquired; a pattern normalizing unit configured to generate a normalized pattern that is normalized by a three-dimensional model from the image data using the plurality of feature points; an estimating unit configured to estimate an illumination direction in which light is emitted to the object in the image data from the three-dimensional model and the normalized pattern; and a determining unit configured to determine whether or not the object in the image data is a three-dimensional object on the basis of the illumination direction.

Abstract: According to an aspect of the invention, an image processing apparatus includes a generating unit, a calculating unit, a receiving unit, and a changing unit. The generating unit generates a plurality of histograms of images with respect to each color based on an input image. The calculating unit calculates a plurality of first image densities of the images from the histograms. The receiving unit receives a content of image quality adjustment performed on the input image. The changing unit changes one of the histograms based on the content of the image quality adjustment. The one of the histogram corresponds to one of the images on which the image quality adjustment is performed. The calculating unit calculates a second image density corresponding to the one the images based on the one of the histogram changed by the changing unit.

Abstract: An image processing apparatus extracts an area for each color from an illustration area, specifies an area that is in contact with the boundary of the illustration area, extracts a color around the illustration area, determines whether or not the extracted color around the illustration area is the same as the color of the specified area, and processes vector data that represents an area that has been determined as having the same color.

Abstract: A method, apparatus and program product are presented for detecting an image. Ring contour images are created by blurring the image, posterizing the blurred image at a plurality of levels and creating the ring contour images from each of the posterized images. Convex hull images are created by creating a plurality of corner images from corners within the image located by at least two different corner algorithms, finding a bounding rectangle that encompasses the ring contour images, cropping the corner images using the bounding rectangle, applying a threshold to the cropped corner images, and creating the convex hull images by generating a convex hull from the corners in each of the cropped corner images. A plurality of triangles is created by fitting a triangle with an orientation to the ring contour images and the convex hull images. Finally the orientation of the triangle is determined from the plurality of triangles.

Abstract: A corresponding image processing method is provided. The corresponding image processing method includes a first step for searching for a corresponding point of a corresponding image; a second step for performing radiometric calibration such that a camera response function of the corresponding image has a linear function; a third step for compensating for a color of the corresponding image by calculating a color conversion matrix; and a fourth step for measuring similarity of the corresponding image.

Abstract: The invention facilitates adaptive compression of multi-level images, such as captured digital images of a whiteboard, etc., encoding a bitstream comprising a color image component and a black-and-white image component. Either or both of a color and a black-and-white image can be output to a user based on user desires, receiving device capabilities, etc.

Abstract: A hue bar, radio buttons, and slide bars are laid out on an adjustment field of a dropout color setting screen. Hue which is continuously changed is displayed on the hue bar in a band form. The radio buttons correspond to specified color numbers so as to switch specification of a plurality of target colors. Sensitivity and intensity are set on the slide bars. Further, when the radio buttons are switched, a slider corresponding to the switched radio button, that is, the specified color number is switched to be in an active display such that a hue range is capable of being set and sliders corresponding to other specified color numbers are switched to be in a non-active display so that setting of the hue range is accepted. Further, settings of the sensitivity and intensity are accepted so as to be subordinate to the accepted hue range.

Abstract: A natural input image is upscaled, first by interpolation. Second, edges in the interpolated image are sharpened by a lion-parametric patch transform. The result is decomposed into an edge layer and a detail layer. Only pixels in the detail layer enhanced, and the enhanced detail layer is merged with the edge layer to produce a high resolution version of the input image.

Abstract: An image sensor apparatus is disclosed. The image sensor apparatus includes an image sensor for generating pixel data corresponding to a scene under a scene illuminant and a processor. The processor includes an illuminant estimation module for receiving a subset of the pixel data associated with a subset of a color space and finding a chromaticity trend in the pixel data subset to estimate the scene illuminant. A white balance and color correction module in the processor applies white balance and color correction coefficients to the pixel data according to the estimated scene illuminant.

Abstract: There is provided an image processing device which transforms an image with a bit depth of N into an upper layer with a bit depth of M and a remaining lower layer, including a histogram unit that generates histogram indicating occurrence frequency of each pixel value of an image with a bit depth of N, a table unit that generates a table listing pixel values of which occurrence frequency in the histogram generated by the histogram unit is equal to or more than one, a reordering unit that reorders an arrangement of values in the histogram using the table generated by the table unit, an update unit that updates the table generated by the table unit and the histogram reordered by the reordering unit; and an index image unit that generates an index image with a bit depth of N using the updated table and the updated histogram.

Abstract: A region extraction apparatus includes an image acquisition device that acquires an image, a temporary initial region specifying device that specifies a plurality of temporary initial regions in the acquired image, a separation calculation device that calculates a separation that is an indicator indicating how much pixel values of all pixels of an inside of a specified temporary initial region and pixel values of all pixels of an outside of the specified temporary region are different from each other, on each temporary initial region, an initial region specifying device that specifies a temporary initial region having a highest calculated separation as an initial region, and a region extraction device that performs a region extraction on a basis of the specified initial region.

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: The technology is directed to determining a class associated with an image. In some examples, a method determines the class associated with an image. The method can include determining a segmentation score for an image segment based on a comparison of the image segment and a region of an image. The region of the image can be associated with the image segment. The method further includes determining a confidence score for the image segment based on the segmentation score and a classification score. The classification score can be indicative of a similarity between the image segment and at least one class. The method further includes determining a class associated with the image based on the confidence score. The method further includes outputting the class associated with the image.

Abstract: Various embodiments of the invention provide systems and methods for extracting information from digital documents, including physical documents that have been converted to digital documents. For example, some embodiments are configured to extract information from a field in a digital document by identifying a block of tokens before (i.e., a prior block) and a block of tokens after (i.e., a post block) the field from which the information is to be extracted, where both the prior block and post block are known to be associated with the field type of the field (e.g., name, address, phone number, etc.).

Abstract: Aspects of the present invention relate to systems and methods for locating text in a digital image. According to a first aspect of the present invention, a multi-stage filtering technique may be used to progressively refine a set of candidate text components associated with a digital image. A first, refined set of candidate text components may be formed by filtering an initial set of candidate text components based on component properties. Text lines may reconstructed from the first, refined set of candidate text components. The first, refined set of candidate text components may be further filtered based on text-line properties measured on the reconstructed text lines.

Abstract: An image processing apparatus determines an attribute of a block image based on the attribute of the block image determined based on a color distribution characteristic amount of the block image and the attribute of the block image determined based on an edge characteristic amount of the block image.

Abstract: Systems and methods for sonar image feature extraction, which fit a parameterized statistical model to sonar image data to extract features that describe image textures for follow-on pattern classification tasks. The systems and methods estimate the parameters of an assumed statistical model from the pixel values in the sonar images. The parameters of the distribution can then be used as features in a discriminant classifier to perform tasks such as texture segmentation or environmental characterization. The systems and methods divide a sonar image into separate overlapping cells. The ACF parameters of each cell are sequentially estimated using various methods. Based on the ACF parameters obtained, each cell is assigned a label via a pattern classification algorithm. The labeled image can be used in target recognition, environmental characterization and texture segmentation.

Abstract: Character recognition is described. In one embodiment, it may use matched sequences rather than character shape to determine a computer-legible result.

Abstract: Shape recognition is performed based on determining whether one or more ink strokes is not part of a shape or a partial shape. Ink strokes are divided into segments and the segments analyzed employing a relative angular distance histogram. The histogram analysis yields stable, incremental, and discriminating featurization results. Neural networks may also be employed along with the histogram analysis to determine complete shapes from partial shape entries and autocomplete suggestions provided to users for conversion of the shape into a known object.

Abstract: The outlines of specific subjects becoming unnaturally deformed is prevented, while reducing the amount of calculations. A reference image setting section sets a reference image which is to become a reference from among a plurality of images. A specific subject detecting section detects a specific subject from within the reference image. A feature point extracting section extracts a plurality of feature points from within the reference image such that the average density of the feature points become higher in the vicinity of the outline of the specific subject. A corresponding point obtaining means corresponding point obtaining section obtains corresponding points within the other images that correspond to the extracted feature points. A coordinate converting section converts the coordinates of the positions of each pixel within the reference image and/or the other images such that the positions of the feature points and the positions of the corresponding points match.

Abstract: An image registration system for aligning first and second images. The novel system includes a first system for extracting a region of interest (ROI) from each image and a second system for coarsely aligning the regions of interest. The first system determines the size and location of the ROI based on the number of features contained within the region. The size of the ROI is enlarged until a number of features contained in the ROI is larger than a predetermined lower bound or until the size is greater than a predetermined upper bound. The second system computes a cross-correlation on the regions of interest using a plurality of transforms to find a coarse alignment transform having a highest correlation. The image registration system may also include a third system for performing sub-pixel alignment on the regions of interest.

Abstract: The feature selection device includes a feature extraction unit that extracts M types of features from each of a plurality of original images and each of a plurality of altered images obtained by applying an alteration process to the plurality of original images; and a feature selection unit that handles an original image and an altered image of the original image as identical images and handles altered images of the same original image as identical images, while handles other images as different images, and with use of discrimination capability which is a degree of discriminating different images and robustness which is a degree that a value of a feature does not vary due to the alteration process applied to an image as evaluation criteria, evaluates the M types of features extracted from the respective images, and selects a collection of N types of features, the N types being smaller in number than that of the M types, from the M types of features as features for discriminating images.

Abstract: Methods, articles of manufacture, and apparatus to count people in an image are disclosed. An example method includes capturing an image of a body region in a first frame; and when a second frame different from the first frame includes the image of the body region, incrementing a first count of persons in the second frame.

Abstract: A method of recognizing features in a 3D environment includes using a sensor that collects a plurality of sensed data points, populating a strip histogram grid having a plurality of strips, each strip having a dx dimension and a dy dimension, by assigning each sensed data point to a strip in the strip histogram grid that has x, y and z dimensions that encompass the spatial coordinate information of the respective assigned sensed data point, and estimating the local ground plane for a strip in the strip histogram grid by using information on each sensed data point assigned to that strip and surrounding strips in the strip histogram grid. Further methods include extracting smooth surfaces, building segmentation, top down segmentation and bottom up segmentation.

Abstract: An image processing apparatus includes a line information reception unit, a prediction determination unit, a feature amount calculation unit and a line determination unit. The line information reception unit receives a set of information indicating (i) information on an image having a possibility of being line and (ii) line element being a rectangular pixel lump constituting a line. The prediction determination unit determines whether or not a target line element matches a predicted value based on the received information. The predicted value indicates line element which is predicted when the target line element constitutes a line. The feature amount calculation unit calculates feature amount of the image when the prediction determination unit determines the target line element does not match the predicted value. The line determination unit determines whether or not the image is a line based on the calculated feature amount.

Abstract: An apparatus for detecting specific human body parts in an image includes: a texture energy analysis unit for analyzing energy distribution in the image and generating texture energy maps; a candidate region-of-interest extraction unit for extracting candidate regions-of-interest for the specific body parts on a given texture energy map by applying a threshold to the given texture energy map, the given texture energy map being selected among the texture energy maps; a candidate mask application unit for performing convolution between candidate masks for the specific body parts and the candidate regions-of-interest and selecting candidate body parts based on results of the convolution; and a body part detection unit for detecting the specific body parts on the image by performing verification on the candidate body parts. The verification is performed by using machine-learning models for the specific body parts.

Abstract: A computer implemented method is disclosed. The method includes obtaining a first and second images for comparison, globally registering the first and second images, calculating for pairs of a first patch of the first image and second patch of the second image a similarity measure which is a product of luminance and contrast components and a normalized structure component, each component taking a value between 0 and 1 and determining similarity of the images based on the calculated similarity measure. Relating computer program product and data processing system are also disclosed.

Abstract: A system and method for detecting changes by comparing images which cover the same physical area but are collected at different times, the system comprising: at least one input for inputting an image of a target area; the image of the target area having signatures representing outstanding features; at least one processor operating to divide the image of a target area into a plurality of target subimages; at least one memory comprising reference data comprising reference subimages taken at or near the target area at various times, the at least one processor operating to determine a sparse image representation from the reference data; the sparse image representation of the target data being a linear combination of reference data from corresponding reference subimages stored in the at least one memory; the at least one processor operating to compare the target image to the sparse image representation and to match signatures from the target image to the sparse image representation to register the images and perfo

Abstract: An image and supplementary information of the image, such as a photographing point and time, are input by an image input section and are stored in an image data storage section. Character recognition in the image is performed by a character recognition section, and the recognition result is stored in a character recognition result storage section. An analysis section extracts object character information relevant to an object from the image, the supplementary information, and the character recognition result on the basis of the analysis conditions input in a designation section to thereby analyze an object, and the analysis result is output to a result output section. Accordingly, a change in the object can be analyzed by analyzing a change in character patterns indicating the identical object.

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

Abstract: Provided are a virtualization server for presentation virtualization and a method thereof. The virtualization server includes: a virtual layer management unit which generates a virtual screen for a user terminal; a service operation unit which executes a service requested from the user terminal, and displays a result of the executed service on the virtual screen; a screen division processing unit which divides the virtual screen into a plurality of sub-blocks; and an image data encoding unit which classifies the plurality of sub-blocks into image sub-blocks and text sub-blocks and encodes the image sub-blocks by a first encoding scheme and encodes the text sub-blocks by a second encoding scheme.

Abstract: An image coding method includes: dividing a picture into tiles; coding the tiles to generate pieces of coded data each of which corresponds to a different one of the tiles; and generating a bitstream including the pieces of coded data. The coding of the tiles includes: generating a first code string by coding a first tile which is one of the tiles, without referring to coding information used in coding another one of the tiles; and adding a bit string after the first code string to make a bit length of first coded data which is one of the pieces of coded data, a multiple of a predetermined N bits, N being an integer greater than or equal to 2.

Abstract: Adaptive entropy encoding and decoding which utilizes Set Partitioning within Generalized Hierarchical Trees (SPRIGHT) and a method of designing trees utilizing directionality. After decorrelation and quantization a tree structure is selected from multiple candidates, based on geometric relationships within the image block, for coding the coefficients toward improving zero-clustering of coefficients. Trees for the SPRIGHT encoding are created in response to finding frequency position of each coefficient and scaling frequency position followed by use of octave-band partitioning of coefficient patterns into squares and L-shapes, and the L-shapes are iteratively partitioned into squares. The tree comprises leaf nodes containing coefficients associated with each non-leaf node. The number of zero clustered coefficients can be increased, thus decreasing the number of nodes coded into the encoded image output.

Abstract: A method, medium, and apparatus processing depth information of a depth image. The apparatus adaptively presenting information on depth information includes a section determination unit determining which one of plural sections respective depth values for pixels of the 3D image fall within, with the plural sections being defined by a measured limit distance for the 3D image being parsed into the plural sections based on distance based depth resolution information, and an adaptive quantization unit to selectively quantize and represent each depth value based on a respective predefined quantization setting of the one section.

Abstract: A motion blur control device uses inter-frame movement computation means to compute an inter-frame movement direction and an inter-frame movement amount from plural frame images acquired at a specific time interval. Motion blur correction means then generates a corrected frame image by correcting motion blur in a specific frame image in plural frame images based on the blur amount set within a range not exceeding the inter-frame movement amount and based on the inter-frame movement direction. Evaluation means evaluates the corrected frame image using a motion blur evaluation function. The motion blur control device controls the blur amount such that the motion blur evaluation function satisfies a specific condition.

Abstract: A display control apparatus includes a synthesizing unit for synthesizing multiple pieces of image data to generate synthesized image data; an image quality adjustment unit for carrying out image quality adjustment for the synthesized image data output from the synthesizing unit; a format discrimination unit for discriminating a format of each of the multiple pieces of image data; a determination unit for determining referenced image data for the image quality adjustment from the multiple pieces of image data based on discrimination results from the format discrimination unit; and a control unit for controlling the image quality adjustment unit so as to carry out the image quality adjustment for the synthesized image data using a parameter suitable for image quality adjustment of the referenced image data for the image quality adjustment determined by the determination unit.

Abstract: Methods, apparatuses and systems providing pixel correction values for a captured image, where the correction values are determined based on a piecewise-quadratic correction function in a first direction. The parameters for the piecewise-quadratic correction function in the first direction are calculated based on a plurality of piecewise-quadratic correction functions in a second direction. The correction values may be positional gain adjustment values.

Abstract: A video encoder may use an adaptive Wiener filter inside the core video encoding loop to improve coding efficiency. In one embodiment, the Wiener filter may be on the input to a motion estimation unit and, in another embodiment, it may be on the output of a motion compensation unit. The taps for the Wiener filter may be determined based on characteristics of at least a region of pixel intensities within a picture. Thus, the filtering may be adaptive in that it varies based on the type of video being processed.

Abstract: Disclosed herein is a movement-adaptive noise reduction apparatus, including a memory, a mixing control section, a movement component extraction section, a low-pass filter section, and a movement decision control section. In the apparatus, the movement decision control section and the low-pass filter section receive, from the outside, information regarding the gain value upon an amplification process to which the image signal is subjected before inputted to the mixing control section to control at least one of the threshold value and the filter characteristic in response to the information.