Abstract: An interventional roadmap method with optimization of the mask face is proposed. At least two empty images and at least two fill images are recorded in a mask phase A with a matrix-type array of pixels and stored. The empty and fill images are processed such that the gray values of each pixel of the x-ray images from mask phase A are arranged in ascending order. A mask image is computed from the processed empty and fill images such that the smallest gray values are averaged and from which the mask image will be formed. At least one current x-ray image is recorded and subtracted from the mask image to create roadmap images.

Abstract: Techniques for face verification are described. Local binary pattern (LBP) features and boosting classifiers are used to verify faces in images. A boosted multi-task learning algorithm is used for face verification in images. Finally, boosted face verification is used to verify faces in videos.

Abstract: A dynamic image compression method for human face detection includes the following steps. An original image is acquired. The image is divided into a plurality of blocks. A first brightness and a plurality of gradient values of each block are calculated. A second brightness of each block is calculated according to a brightness transformation function and the first brightness. A reconstruction image is generated according to the second brightness and the plurality of gradient values of each block. Human face detection is performed according to the reconstruction image. Therefore, gradient values within an original square are. When the human face detection process is performed through gradient direction information, a success rate of detection is greatly increased.

Abstract: Digital image data including discrete photographic images of a variety of different subjects, times, and so forth, are collected and analyzed to identify specific features in the photographs. In an embodiment of the invention, distinctive markers are distributed to aid in the identification of particular subject matter. Facial recognition may also be employed. The digital image data is maintained in a database and quarried in response to search requests. The search requests include criteria specifying any feature category or other identifying information, such as date, time, and location that each photograph was taken, associated with each photograph. Candidate images are provided for review by requesters, who may select desired images for purchase or downloading.

Abstract: Capsule type endoscopes generate large amounts of in-vivo image data that requires review and analysis by a doctor or clinician. By not reviewing the images gathered from healthy tissue, and only focusing on images indicating potential abnormalities, the time it takes to review the data can be greatly reduced. By correlating the tissue images with a characteristic known to indicate a potential abnormality, only the suspect images need to be reviewed.

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

Abstract: The present invention provides a medical diagnosis support device which enables a user to acquire the most appropriate information to support medical diagnosis without causing the user so much trouble.

Abstract: A method for computing a color-coded analysis image of an examination area of an examination object from a temporal sequence of fluoroscopic images of the examination area comprising a vascular system containing arteries and/or veins is provided. An acquisition time instant has been assigned to each of the fluoroscopic images representing a given distribution of a material embolizing some of the vascular system. The fluoroscopic image spatially corresponds to an analysis image pixel by pixel. A computer receives the fluoroscopic images with a color attribute assigned to each pixel of the analysis image at an image point and a time instant. If a pixel differs from a pixel at a preceding time instant, the color attribute assumes a color attribute of the time instant and the difference. If a pixel corresponds to a background color of the analysis image, the color attribute assumes a background color.

Abstract: A system for providing interstitial photodynamic and/or photothermal therapy on a region of tissue in a body, comprising at least one light source adapted to deliver a therapeutic light to the region of tissue, such that the light source is interstitially inserted into the tissue for interaction with a photosensitizer agent and/or for providing a controlled thermal environment of the tissue; and a unit for determining an optimized number of the light sources and individual position of each of the light sources in the region of tissue as well as individual control parameters for each of the light sources.

Abstract: A method and system is provided for performing cosmetic analysis of a subject. Assessment data of observable characteristics of each of a plurality of defined body areas of a subject is converted to weighted data for each of the plurality of defined body areas. This weighted data is analysed to generate cosmetic analysis data. This cosmetic analysis data can include an apparent age of the subject. The cosmetic analysis data is then provided to a user such as a cosmetic surgeon, beauty therapist or the subject themself. The system and method can be further adapted to perform treatment diagnosis for the subject based on the cosmetic analysis data.

Abstract: A determination method for reinitialization of a temporal sequence of fluoroscopic images of an examination region of an examination object is provided. The examination region comprises a vascular system including arteries and/or veins. An acquisition time is assigned to each of the images representing a given distribution of a substance in the examination region at the acquisition time. A computer receives the temporal sequence of the images, determines an evaluation image corresponding spatially on a pixel-by-pixel basis to the images, and calculates a differential value between a pixel of the evaluation image at a time and a pixel at a preceding time during a time characteristic of the sequence. A reinitialization of the temporal sequence of the images is performed at a specific time and thereafter the determination method is started over and/or repeated. The specific time is determined as a function of at least one previously calculated differential value.

Abstract: An apparatus includes a first magnetic resonance (MR) coil element configured to output a first set of MR data at a first output frequency and a first mixer coupled to the first MR coil element. The first mixer is configured to receive the first set of MR data from the first MR coil element and frequency translate the first set of MR data to a first offset frequency different from the first output frequency by a first offset value. The apparatus also includes a digitizer coupled to the first mixer and configured to convert the frequency-translated first set of MR data into a set of digital data and a transmission line coupled to the first mixer and to the digitizer, the transmission line configured to transmit the frequency-translated first set of MR data from the MR coil element to the digitizer without a balun coupled to the transmission line.

Abstract: A method of generating an image data set, describing an object, as the object moves in a scanning space, comprises: a) performing a plurality of scans of the scanning space each scan being arranged to generate a set of samples, each sample including a sample value of at least one parameter associated with a respective point in the scanning space, the plurality of scans generating sample sets relating to a plurality of different parameters; b) determining a mapping for each of the samples from the scanning space into an object space which is fixed relative to the object; and c) determining object space values for each of the parameters at each of a plurality of points in the object space.

Abstract: This invention relates to computer-assisted diagnostics and classification of prostate cancer. Specifically, the invention relates to segmentation of the prostate boundary on MRI images, cancer detection using multimodal multi-protocol MR data; and their integration for a computer-aided diagnosis and classification system for prostate cancer.

Abstract: Disclosed herein are methods and devices for repairing articular surfaces in a knee joint. The articular surface repairs are customizable or highly selectable for each patient and geared toward providing optimal fit and function. Kits are also provided to enable customized repairs to be performed.

Abstract: A method is disclosed for recording and processing measurement data from a hybrid imaging device including a first partial device for a first imaging modality and a second partial device for emission tomography.

Abstract: An X-ray inspecting apparatus capable of high-speed inspection of a prescribed inspection area of an object of inspection is provided. The X-ray inspecting apparatus includes: a scanning X-ray source for outputting X-ray; an X-ray detector driving unit on which a plurality of X-ray detectors are mounted, and capable of driving the plurality of X-ray detectors independently; and an image acquisition control mechanism controlling acquisition of image data by X-ray detector driving unit and X-ray detectors. A scanning X-ray source emits X-ray while moving the X-ray focal point of the X-ray source to each of X-ray emission originating positions set for each X-ray detector such that the X-ray passes through a prescribed inspection area of an object of inspection and enters each X-ray detector. Image pick-up by some of the X-ray detectors and movement of other X-ray detectors to an image pick-up position are executed in parallel and alternately.

Abstract: An image processing apparatus for performing tone conversion on an image imaged by an X-ray imaging system extracts a reference region that is to serve as a reference for the image, and, if there is a change in the image, performs tone conversion so as to suppress variation in contrast resulting from the change in the image in the extracted reference region, and so as to reflect variation in the contrast in the remaining region.

Abstract: A method and an X-ray image acquisition system for the acquisition of X-ray images of a region of interest of an examination object from a multiplicity of angles of view for an 3-D image reconstruction are provided. The X-ray image acquisition system comprises an X-ray focus and an X-ray detector, which can be separately positioned and oriented relative to each other. The X-ray focus is moved along a combination of straight line segments and/or arc segments for the acquisition of X-ray images. The X-ray detector is oriented relative to the X-ray focus and moved in such a way that the region of interest is projected completely onto the X-ray detector upon each image acquisition.

Abstract: Methods, systems and computer program products for normalizing histology slide images are provided. A color vector for pixels of the histology slide images is determined. An intensity profile of a stain for the pixels of the histology slide images is normalized. Normalized image data of the histology slide images is provided including the color vector and the normalized intensity profile of a stain for the pixels of the histology slide images.

Abstract: Systems and methods are described for performing image analysis. A computer-implemented method for analyzing images may include quantitatively analyzing image data to identify image objects relative to a background portion of the image according to predefined object criteria, the image data including a plurality of image objects that represent objects in a sample distributed across a substrate. The identified image objects are further clustered into groups or colonies of the identified image objects according to predetermined clustering criteria.

Abstract: A computer-implemented method is provided of identifying an optical character recognition (OCR) font to assist an operator in setting up a bank remittance coupon application. The computer-implemented method comprises electronically on a processor reading an OCR font in a zone of the bank remittance coupon, electronically on a processor comparing the read OCR font with an OCR font stored in a look-up table to determine if the read OCR font meets predetermined criteria, and storing the read OCR font into a configuration file to setup at least a portion of the bank remittance coupon application when the read OCR font meets the predetermined criteria.

Abstract: Embodiments of the present invention determine the surface profile of certain classes of work surface. More specifically, embodiments of the invention measure the three-dimensional locus of points that define the “virtual” continuous surface fitted to the ends of the walls of a cellular core.

Abstract: The present disclosure includes a system for inspecting a manufactured composite component. In some embodiments, the system includes an inspection assembly having master camera assembly and a slave camera assembly. The master camera assembly and the slave camera assembly each include a machine vision camera and a lighting system. The lighting assembly may include back lights and spot lights. In some embodiments, the master camera and the slave camera are each connected to a telecentric lens. The composite component is inspected by moving it through the inspection assembly, taking images, and processing the images to measure features on the component.

Abstract: Methods for generating a standard reference die for use in a die to standard reference die inspection and methods for inspecting a wafer are provided. One computer-implemented method for generating a standard reference die for use in a die to standard reference die inspection includes acquiring output of an inspection system for a centrally located die on a wafer and one or more dies located on the wafer. The method also includes combining the output for the centrally located die and the one or more dies based on within die positions of the output. In addition, the method includes generating the standard reference die based on results of the combining step.

Abstract: A color image of an inspection object is taken by an imaging means capable of taking a color image to obtain color information of an RGB color space. A gray-scale image of a color component of the RGB color space or another color space is generated, and the inspection object is detected by a pattern recognition technique. Alternatively, a binary image is generated from the generated gray-scale image, and the inspection object is detected by performing pattern recognition on the binary image. Color data of a pixel occupied by the detected inspection object is compared with color data of a non-defective inspection object which is previously prepared to judge whether or not the inspection object is defective. In addition, this judgment result is reflected in another manufacturing step through a network and product quality is improved.

Abstract: A location and orientation in an environment is determined by first acquiring a real omni-directional image of an unknown skyline in the environment. A set of virtual omni-directional images of known skylines are synthesized from a 3D model of the environment, wherein each virtual omni-directional image is associated with a known location and orientation. The real omni-directional image with each virtual omni-directional images to determine a best matching virtual omni-directional image with the associated known location and orientation.

Abstract: The present invention relates to a method and a system for rectifying images. An original stereo image pair is obtained, and the epipolar lines corresponding to the original stereo image pair are parallelized to obtain a first transformed stereo image pair. Epipolar lines corresponding to the first transformed stereo image pair are collinearized to obtain a second transformed stereo image pair. The present invention parallelizes and collinearizes the epipolar lines corresponding to the stereo image pair after the images are rectified.

Abstract: An information processing apparatus includes the following elements. A learning unit is configured to perform Adaptive Boosting Error Correcting Output Coding learning using image feature values of a plurality of sample images each being assigned a class label to generate a multi-class classifier configured to output a multi-dimensional score vector corresponding to an input image. A registration unit is configured to input a register image to the multi-class classifier, and to register a multi-dimensional score vector corresponding to the input register image in association with identification information about the register image. A determination unit is configured to input an identification image to be identified to the multi-class classifier, and to determine a similarity between a multi-dimensional score vector corresponding to the input identification image and the registered multi-dimensional score vector corresponding to the register image.

Abstract: A method and system for automatically training a document imaging classification and extraction system that switches between a manual mode and an automatic mode based on constant monitoring. A specialized sub-system monitors and records a user interaction with the classification system during the initial manual mode and, in parallel, develops and tests a user configuration with respect to an automated processing engine. The system is capable of being shifted to the automatic mode if a desired acceptability threshold is attained and the document can then be processed automatically. Furthermore, a user can interact with the classification system if the automatic mode fails. Information concerning exception handling can be entered into a training database for continual refinement of the classification and extraction system.

Abstract: In an exemplary embodiment of the present invention, an automated, computerized method is provided for processing an image. According to a feature of the present invention, the method comprises the steps of providing an image file depicting an image, in a computer memory, identifying information in the image file relevant to a logical deduction regarding material and illumination aspects of an image and selected from information relevant to spatio-spectral aspects of an image and constituents of color; defining a constraint as a function of the information; and utilizing the constraint in an image segregation operation.

Abstract: A video detection system and method compares a queried video segment to one or more stored video samples. Each of the queried video segments and stored video samples can be represented by respective digital image sets. A first and second comparison comprises comparing a set of low and high resolution temporal and spatial statistical moments in a COLOR9 space, and eliminating file digital image sets that do not match the queried digital image set. A third comparison generates a set of matching files by comparing a set of wavelet transform coefficients in a COLOR9 space. RGB bit-wise registration and comparison of one or more subframes of specific frames in the queried digital image set to a corresponding set of matching file subframes determines queried subframe changes. In the event of a change in a queried subframe, the changed subframe is added to the set of matching file subframes.

Abstract: When compressing continuous tone bit map image data, the image compression section of the image compressing apparatus segments the continuous tone bit map image data into bit map image data for lossy compression, index image data for lossless compression and bit map image data for lossless compression based on pixel identification information data. The lossy compression section of the image compression section performs lossy compression process according to the JPEG method for the bit map image data for lossy compression, and the first lossless compression section thereof performs lossless compression process according to the JBIG method for the index image data for lossless compression. Furthermore, the second lossless compression section thereof performs lossless compression process according to the JPEG-LS method for the bit map image data for lossless compression.

Abstract: A method for providing improved foreground/background separation in a digital image of a scene is disclosed. The method comprises providing a first map comprising one or more regions provisionally defined as one of foreground or background within the digital image; and providing a subject profile corresponding to a region of interest of the digital image. The provisionally defined regions are compared with the subject profile to determine if any of the regions intersect with the profile region. The definition of one or more of the regions in the map is changed based on the comparison.

Abstract: The present invention is a digital image manipulation system for automatically cropping acquired digital images, including a memory device configured to store at least one acquired digital image, a crop analysis segmentation subsystem configured to divide at least one image into a set of similarly colored regions, a classification subsystem configured to classify each region into one of a set of possible classes which include subject background and distraction at a minimum, an optimization search configured to search possible crop boundaries and a selection module configured to automatically select a highest rated crop boundary determined from the search and based on an optimization criterion that is derived from results of the crop analysis segmentation and classification subsystems.

Abstract: An image processing apparatus includes a region analysis unit configured to generate a quantized region by integrating regions that are included in an input multivalued image and have similar colors and to determine an attribute of a connected component included in the generated quantized region, and a character portion filling unit configured to determine a color used for filling a connected component that has been determined by the region analysis unit to have a character attribute and to execute processing for filling the connected component that has been determined to have the character attribute. In the image processing apparatus, the character portion filling unit is configured to change a method for determining the color used for filling based on the quantized region existing adjacent to the connected component determined to have the character attribute.

Abstract: A method for guiding a user with a suitable composition includes detecting scene information from an input image, recognizing a scene of the input image by using the detected scene information, extracting composition information corresponding to the recognized scene, and displaying the extracted composition information. Accordingly, an apparatus for guiding a user with a suitable composition and a digital photographing apparatus using the method displays a composition suitable for a current scene by automatically recognizing the current scene, so that the user photographs the current scene quickly and easily.

Abstract: The present invention aims at suppressing a noise in a low luminance part and a high luminance part and, at the same time, realizing a high contrast of the parts, and realizing high contrast of a characterizing part of the image as well. The image signal processing is provided with: a first area input-output characteristics control unit which controls change of input-output characteristics for every arbitrary areas, associated with a value of an input luminance signal; a second area input-output characteristics control unit which controls change of input-output characteristics for every arbitrary areas, associated with an output of the first area input-output characteristics control unit; and a chrominance input-output characteristics control unit which controls change of the input-output characteristics of an input chrominance signal, utilizing the output of the first area input-output characteristics control unit and the output of the second area input-output characteristics control unit.

Abstract: A method for tone mapping high dynamic range images for display on low dynamic range displays wherein high dynamic range images are first accessed. The high dynamic range images are divided the into different regions such that each region is represented by a matrix, where each element of the matrix is a weight or probability of a pixel value. An exposure of each region is determined or calculated by estimating an anchor point in each region such that most pixels in each region are mapped to mid grey and the anchor points are adjusted to a key of the images to preserve overall brightness. The regions are then placed or mapped to zones and exposure values are applied to the regions responsive to the weight or probability. The regions are fused together to obtain a final tone mapped image.

Abstract: Disclosed are techniques and systems to provide a scanned image in which a portion of the image is overlaid with OCR generated text corresponding to the text of the original scanned document.

Abstract: In an image conversion method, a value which reflects the mutual relationship between the classes of pixel patterns each formed from a pixel classified as one of a plurality of classes and peripheral pixels is set as a converted value corresponding to each of the plurality of classes, a pixel of interest is sequentially selected from the input image, and a pixel pattern formed from the selected pixel of interest and a predetermined number of pixels around it is classified as one of the plurality of classes in accordance with a neighboring pattern obtained based on the relationship between the value of the pixel of interest and the values of peripheral pixels located at predetermined relative positions with respect to the pixel of interest. The value of the pixel of interest is converted into a converted value set for a class to which the pixel of interest has been classified.

Abstract: A method of segmenting regions of an image wherein a number of partitions are determined based on a range of an image histogram in a logarithmic luminance domain. Regions are defined by the partitions. A mean value of each region is calculated by K-means clustering wherein the clustering is initialized, data is assigned and centroids are updated. Anchor points are determined based on the centroids and a weight of each pixel is computed based on the anchor points.

Abstract: Techniques are disclosed for correcting the exposure of a digital image. An exposure predictor may be generated based on a set of images for which ground truth data are known. After identifying an optimal set of features, the exposure of the digital image may be corrected by extracting values of the selected optimal features from the image, using the predictor to predict a desired exposure correction for the image, and correcting the exposure of the image by the predicted desired amount. Exposure correction is based on a model that relates intensity of light in the world to the RGB digits of the digital image. The model comprises a gamma function that models the response of a typical monitor and a S-shaped curve that compresses the large dynamic range of the world to the small dynamic range of the RGB digit space.

Abstract: An image processing apparatus according to the present invention, comprises a histogram creation unit creates a histogram from an input image, a detection unit detects a gradation level of interest from the histogram, a gradation correction parameter generation unit generates a gradation correction parameter to improve a gradation characteristic in a gradation range around the gradation level of interest, and a correction unit corrects the gradation of the image using the gradation correction parameter, wherein the detection unit detects, as the gradation level of interest, a gradation level of which frequency is a peak value equal to or more than a predetermined threshold, and which has variation width of frequencies in a predetermined range including this gradation level to be smaller than a predetermined width in the histogram.

Abstract: The present invention discloses a method of estimating human pose comprising: modeling a human body as a tree structure; optimizing said tree structure through importance proposal probabilities and part priorities; performing foreground detection to create image region observation; and performing image segmentation to provide image edge observations.

Abstract: An image processing apparatus includes a division unit configured to divide an image into a plurality of areas, a calculation unit configured to calculate a feature amount for each division area, an area category determination unit configured to determine for each division area at least a night scene category or an under-exposure category based on the calculated feature amount, an entire category determination unit configured to determine a category of the entire image based on the result of category determination, and a processing unit configured to perform correction processing on the image based on the result of category determination by the entire category determination unit.

Abstract: A statistical system and method for generating patterns and performing online handwriting recognition based on those patterns. A plurality of predetermined patterns may be generated by performing feature extraction operations on one or more character samples utilizing a Gabor filter. An online handwritten character may be acquired. The online handwritten character may be pre-processed. One or more feature extraction operations, utilizing a Gabor filter, may be performed on the online handwritten character to produce a feature vector. One or more patterns may be generated, using a statistical algorithm, for the online handwritten character, based on the feature vector. The online handwritten character may be statistically classified based on a comparison between the one or more patterns generated for the online handwritten character and the plurality of predetermined patterns.

Abstract: Techniques are disclosed for detecting new events in a video stream that yield improved detection efficiency in real time. For example, a method determines whether a given event is a new event in a video stream. The video stream includes a plurality of events. A first step extracts a first set of features (e.g., text features) from the given event. The first set of features is computationally less expensive to process as compared to a second set of features (e.g., image features) associated with the given event. A second step computes one or more first dissimilarity values between the given event and one or more previous events in the video stream using only the first set of features when one or more first dissimilarity criteria exist. A third step determines whether the given event is a new event based on the one or more computed first dissimilarity values.

Abstract: An automated method of generating sets of image processing instructions that identifies a region of picture elements for processing and a region of picture elements to be produced is described. The method receives a first set of image processing instructions for performing a transform operation, and, for the first set of image processing instructions, produces a second set of image processing instructions that identify a region of picture elements for processing from an input image and a third set of image processing instructions that identify a region of picture elements to be produced in an output image. The method associates the second and third sets of image processing instructions with the first set of image processing instructions, the association allowing the execution of the second and third sets of image processing instructions at run-time to facilitate the execution of the first set of image processing instructions.

Abstract: An image processing apparatus including a detector to detect a face in an image is provided. The image processing apparatus sets a size of the face to be detected, changes a detection condition for face detection in accordance with the size of the face set, applies the detection condition changed to the detector, and detects the face from the image by use of the detector to which the detection condition is applied.