Abstract: A method for following hand movements in an image flow, includes receiving an image flow in real time, locating in each image in the received image flow a hand contour delimiting an image zone of the hand, extracting the postural characteristics from the image zone of the hand located in each image, and determining the hand movements in the image flow from the postural characteristics extracted from each image. The extraction of the postural characteristics of the hand in each image includes locating in the image zone of the hand the center of the palm of the hand by searching for a pixel of the image zone of the hand the furthest from the hand contour.

Abstract: An imaging apparatus is disclosed. The imaging apparatus includes: an imaging unit for imaging a subject to obtain image data; a display unit for displaying the obtained image data; a subject specifying unit for specifying the subject in the image data; a tracking frame displaying unit for displaying on the display unit a tracking frame surrounding the subject specified by the subject specifying unit; a subject tracking unit for tracking the subject surrounded by the tracking frame displaying unit; an imaging condition controlling unit for controlling an imaging condition for the subject within the tracking frame; and a subject recognizing unit for recognizing whether or not the subject within the tracking frame is the subject specified by the subject specifying unit. The subject recognizing unit repeats the recognition during the tracking by the subject tracking unit.

Abstract: There is provided a monitoring system including an image capture module for capturing an image, an object detecting unit for detecting an object from the image, a monitoring range setting unit for setting a monitoring range in a side of the object on the image, a determining unit for determining the existence of a light source within the monitoring range, and an adjusting unit for adjusting one of an exposure amount of the image capture and a luminance of a pixel output from the image capture when the determining unit determines the existence of the light source.

Abstract: A system and method of recording digitally stored surveillance images comprises dividing a series of continuous digital picture image frames according to timing intervals; storing a reference image in a frame buffer of a motion analyzer; detecting a motion difference between a captured image and the reference image; attributing a motion code and time stamp on the captured image; and recording the captured image when the motion code and time stamp match a predetermined threshold.

Abstract: In the context of a site analysis report showing paths between nodes, color is used to indicate a direction of traffic that follows a particular node-to-node path. Different colors are assigned to different nodes in a site analysis report. Paths are color-coded according to their destination nodes, so as to provide a distinctive visual identification of a traffic flow direction. Node connection direction can be reinforced by static or moving arrows.

Abstract: The invention relates to a method, which comprises the capturing of image data representing a physical object using an electronic device. First visual objects are determined in the image data. Second objects are determined among the first visual objects. Position information is determined for the second visual objects within the physical object. Third visual object are obtained based on the position information from object data storage. The third visual objects are matched to the first visual objects and differences between third visual objects and the first visual object are indicated to a user.

Abstract: A patient identification system based on a portable data terminal including a biometric data capture device for capturing biometric scan data from a person and creating a biometric template for the person. A reference biometric template is prepared based oil a biometric scan of patient. Software is provided on the portable data terminal to compare the biometric template captured by the portable data terminal to the reference biometric template and indicate a whether the person corresponds to the patient described by the reference biometric template.

Abstract: The present invention provides a registration device which can improve the authentication accuracy. The registration device includes a detection means for detecting fluctuation information that fluctuates according to an illumination intensity in an image-pickup element, a filter means for performing the spatial filter processing for an image signal output from the image-pickup element using a filter coefficient which is made to correspond to the fluctuation information detected by the detection means, and extracting a living organism identification subject contained in the image signal, and a registration means for generating registration data from the image signal that is spatially filtered by the filter means, and storing thus generated registration data in a storage medium.

Abstract: A method and apparatus for designing an iris biometrics system that operates in minimally constrained settings. The image acquisition system has fewer constraints on subjects than traditional methods by extending standoff distance and capture volume. The method receives design parameters and provides derived quantities that are useful in designing an image acquisition system having a specific set of performance requirements. Exemplary scenarios of minimally constrained settings are provided, such as a high volume security checkpoint, an office, an aircraft boarding bridge, a wide corridor, and an automobile.

Abstract: The face detection device detects a human face image in an image. The face detection device includes a face determining unit, a control unit, a display unit, and a receiving unit. The face determining unit performs a face determination process in which the face determining unit determines whether the image includes a human face image indicative of at least a part of a human face. The control unit performs a base process by controlling the face determining unit to perform the face determination process at least one time. The display unit displays a result of the base process. When the receiving unit receives an instruction, the control unit performs an additional process by controlling the face determining unit to perform the face determination process at least one time on the same image with a higher accuracy than the face determination process in the base process.

Abstract: Disclosed is a method of extracting ridge and valley lines from three-dimensional point data, the method including the steps of: receiving undefined point data obtained from a three-dimensional scanning system; estimating a normal vector by principal component analysis so as to calculate a normal vector with regard to each received point; and on the basis of such information, creating a moving least squares (MLS) surface of points approximation with regard to each received point. Then, Delaunay edge is created by a Voronoi diagram with regard to each point from the created MLS surface of points; and ridge (or valley) points are extracted by measuring zero-crossing on each Delaunay edge. Ridges and valleys as lines are created by connecting the extracted ridge points in a principal curvature direction. The extraction of ridge and valley lines is used as a pre-processing step for creating three-dimensional points into mesh data, and is advantageous for identifying general model features.

Abstract: In a multi-modality method for representing functional and morphological exposures of an extremity of patients exhibiting arthritis/arthrosis, and corresponding computer software, images obtained with different imaging modalities are supplied to a computer and displayed at the computer with a default line model of the extremity superimposed on each of the images. A user interacts with the computer to modify the line model as necessary, so that each of the images has a modified line model associated therewith. The images obtained from the different imaging modalities are then superimposed and registered with each other by conforming the respective modified line models with each other. One of the images can be composed of a number of sub-images, obtained at respective joints in the extremity. These individual images of the joint can be fused with the image of the complete extremity, so that in a display of such a fused image, the individual joint images can be selected and displayed.

Abstract: The present invention provides a universal and centralized image (e.g., medical, bio-molecular, etc.) processing system platform. The invention permits sharing both computation and visualization across a single universal platform, thus allowing for sharing of computing resources and visualization of images on a variety of imaging (client) devices without high-performance graphical display cards. In a typical embodiment a (e.g., medical) image 2D linear registration algorithm is implemented on a Cell Broadband Engine processor, which has nine processor cores on a chip and has a 4-way SIMD unit for each core.

Abstract: The present invention uses a common, hybrid system platform to provide a generalized medical image processing system that can handle the existing medical image application as it is and route the compute intensive medical image processing to a multi0core processor/processing system. The invention allows the processing platform to be shared among healthcare system such as mammography, X-ray, CT Scan MRI, two-photon, laser microscopy, digital pathology, etc. It also allows the processing platform to deliver medical images to a variety of client devices, such as a desktop computer or a handheld device, through the network without high-performance graphical display capabilities because the rendering of the medical images is performed on the Cell BE based platform of the invention.

Abstract: Systems and methods for high-throughput radiation biodosimetry are disclosed herein.

Abstract: A method and an apparatus are disclosed for registering at least three different image data records for an object. In at least one embodiment, the method involves first of all determining for each image data record the anatomical region which is covered by the image data record. Next, degrees of overlap in these anatomical regions are calculated. These degrees of overlap are taken as a basis for determining the image data record as a master image data record which, in total, has a maximum overlap with the other image data records, ignoring degrees of overlap which are below a prescribable lower threshold. The other image data records are then registered merely with the master image data record. Thus, they are automatically also indirectly registered with one another. At least one embodiment of the present method and the associated apparatus reduce the waiting time for the user who wishes to visualize a plurality of the image data records simultaneously next to one another or superimposed on one another.

Abstract: An image-constituting element group corresponding to bone areas is selected from among a plurality of image-constituting elements that make up a three-dimensional image model, and CT values originally associated only with the selected image-constituting element group are replaced by values resulting from multiplying the original values by 1/4. As a result, a distribution curve 34A denoting a frequency distribution of bone is shifted to a region of CT values that are lower than those of a distribution curve 33 denoting a frequency distribution of blood vessels. An observation image is then constructed by maximum intensity projection on the basis of three-dimensional image data after such signal value replacement.

Abstract: Methods and systems for enhancing an image exhibiting speckle noise are provided. An image exhibiting the speckle noise is received and a coefficient of variation is estimated in a part of the received image. Either a detail tuning parameter or a smooth tuning parameter are selected based on the estimated coefficient of variation. A maximum likelihood (ML) filter is configured with the selected tuning parameter and the configured ML filter is applied to the part of the received image.

Abstract: Methods, systems and computer program products for managing frequency domain optical coherence tomography (FDOCT) image resolution. A spectrum used to acquire an image of a subject is calibrated and default dispersion correction parameters are set. Default dispersion management parameters associated with a region of the image of the subject are also set. The image of the subject is acquires after setting the default dispersion correction parameters and the default dispersion management parameters. A quality of the acquired image is compared to a quality metric for the acquired image. The dispersion correction parameters are adjusted if the quality of the acquired image does not meet or exceed the quality metric for the acquired image. The acquired image is reprocesses based on the adjusted dispersion correction parameters.

Abstract: An image processing apparatus includes a storing section which stores data of a digital image, a rotation processing section which generates a plurality of rotated digital images having different rotation angles from the digital image, an image processing section which generates a plurality of image-processed digital images from the rotated digital images, a reverse processing section which generates a plurality of reversed digital images from the image-processed digital images, and a combining section which combines the reversed digital images into one digital image.

Abstract: Ultrasound systems and methods are described to measure changes in cardiac chamber volumes and organ wall areas, thicknesses, volumes and masses between the cardiac chambers using computer readable media employing image processing algorithms applied to 3D data sets acquired at systole and diastole. The systems for cardiac imaging includes an ultrasound transceiver configured to sense the mitral valve of a heart by Doppler ultrasound, an electrocardiograph connected with a patient and synchronized with the transceiver to acquire ultrasound-based 3D data sets during systole and diastole at a transceiver location determined by Doppler ultrasound affected by the mitral valve, and a computer readable medium configurable to process ultrasound imaging information from the 3D data sets communicated from the transceiver.

Abstract: A method for image acquisition is disclosed. In an embodiment, the method includes acquiring, by a first imaging method, first image data of an object to be examined; acquiring, by a second imaging method, second image data of the object to be examined; generating an image file, the file format of which allows different logical layers of image data to be stored, in such a manner that the image file generated contains the acquired first image data in a first logical layer in the intended layer format and the acquired second image data in a second logical layer.

Abstract: A method and system for locating an opaque region, such as a heart region in a chest X-ray radiograph is disclosed. In order to segment a heart region in a chest X-ray radiograph, a heart region boundary is generated based on lung boundaries in the chest X-ray radiograph and an average heart region model. A location of the lower boundary of the heart region in the chest X-ray radiograph is then determined. Left and right portions of the heart region boundary are independently registered to corresponding portions of the lung boundaries, and upper and lower portions of the heart region boundary are adjusted based on the left and right portions in order to form a smooth contour.

Abstract: There is described a system and a method for analyzing spots in a micro-array, the spots containing targeted specimen, the method comprising the steps of: providing a slide with a micro-array of the spots thereon; illuminating at least one of the spots; directing the light onto the at least one spot; collecting light emitted from the at least one spot; forming an image of the at least one spot using the collected light; and analyzing the image to distinguish at least one unit of the targeted specimen located within the at least one spot from any undesired material. The analysis results are aimed at the detection, classification and quantification of optically resolvable specimen such as micro-organisms or cells.

Abstract: A scintillation evaluation method for quantitatively evaluating scintillation, the method comprising: obtaining an image data that includes at least an interference pattern of scintillation; increasing the contrast of the interference pattern; and determining the amount of variation of brightness in the image data, the amount of the variation corresponding to the interference pattern whose contrast has been increased.

Abstract: Inspection of objects such as semiconductor wafers may proceed on a cell-to-cell or die-to-die basis. An image of a wafer may be obtained and the cells or dies shown therein can be inspected using any combination of appropriate die-to-die or cell-to-cell inspection methods. For example, one or more areas may be designated for cell-to-cell inspection. For each cell type, a reference image can be generated by obtaining an image of the area and displacing the image by an amount equal to the repetition vector for that cell type in opposite directions. The displaced images and the original image can be combined into a single reference image. The original image can then be compared to the reference image. In some embodiments, the displaced images are also compared to the reference image to statistically determine the presence or absence of defects.

Abstract: A system and method for identifying objects using a robotic system are disclosed. Briefly described, one embodiment is a method that captures a first image of at least one object with an image capture device that is moveable with respect to the object, processes the first captured image to determine a first pose of at least one feature the object, determines a first hypothesis that predicts a predicted pose of the identified feature based upon the determined first pose, moves the image capture device, captures a second image of the object, processes the captured second image to identify a second pose of the feature, and compares the second pose of the object with the predicted pose of the object.

Abstract: The present invention is directed to a system and method for interactive and iterative reconstruction in a manner that helps to reduce computational requirements by generating a model from a subset of the available data, and then refining that model using additional data. Example embodiments directed to scene reconstruction, reconstruct a 3D scene from a plurality of 2D images of that scene by first generating a model of the 3D scene from a subset a of the 2D images. The model can then be refined using specific characteristics of each image in the subset that are calculated using the other images in the subset. The model is further refined using images not in the original subset.

Abstract: A method and apparatus for high-resolution 3D imaging ladar system which can penetrate foliage and camouflage to sample fragments of concealed surfaces of interest is disclosed. Samples collected while the ladar moves can be integrated into a coherent object shape. In one embodiment, a system and method for automatic data-driven registration of ladar frames, comprises a coarse search stage, a pairwise fine registration stage using an iterated closest points algorithm, and a multi-view registration strategy. After alignment and aggregation, it is often difficult for human observers to find, assess and recognize objects from a point cloud display. Basic display manipulations, surface fitting techniques, and clutter suppression to enhance visual exploitation of 3D imaging ladar data may be utilized.

Abstract: Cameras are installed at the front, right, left, and back side of a vehicle, and two feature points are located at each of the common field of view areas between the front-right cameras, front-left cameras, back-right cameras, and back-left cameras. A camera calibration device includes a parameter extraction unit for extracting transformation parameters for projecting each camera's captured image on the ground and synthesizing them. After transformation parameters for the left and right cameras are obtained by a perspective projection transformation, transformation parameters for the front and back cameras are obtained by a planar projective transformation so as to accommodate transformation parameters for the front and back cameras with the transformation parameters for the left and right cameras.

Abstract: Pattern model parameters are updated using update equations based on competing patterns that are identical to a reference pattern except for one segment at a time that is replaced with a competing segment. This allows pattern recognition parameters to be tuned one segment at a time, rather than have to try to model distinguishing features of the correct pattern model as a whole, according to an illustrative embodiment. A reference pattern and competing patterns are divided into pattern segments. A set of training patterns are generated by replacing one of the pattern segments in the reference pattern with a corresponding competing pattern segment. For each of the training patterns, a pattern recognition model is applied to evaluate a relative degree of correspondence of the reference pattern with the pattern signal compared to a degree of correspondence of the training patterns with the pattern signal.

Abstract: Provided are an apparatus and method for generating an image using a multi-channel filter. More particularly, provided are an apparatus and method for generating an image using a multi-channel filter, wherein images input into a plurality of image sensors are allowed to pass through different filters, each of which includes a plurality of channels, and segmented images passed through the filters are combined to produce a desired image. The apparatus includes a filter unit including a plurality of filters having different patterns with respect to a plurality of image channels and filtering images input into the filters, an image sensing unit including a plurality of image sensors sensing images filtered through the plurality of the filters, an interpolation unit calculating image channel values of pixels of the sensed images, and an image combination unit assigning the calculated image channel values to corresponding pixel positions to generate a single desired image.

Abstract: A method and apparatus for translating color to grayscale images, wherein at least some pixels of the color image having the same color are mapped to different grays in the grayscale image depending on the spatial surround of each pixel. Further, the method and apparatus may include applying a high pass filter to at least one chrominance component of a color image to generate at least one high pass filtered chrominance component, and adjusting a luminance component of the color image based upon the at least one high pass filtered chrominance component.

Abstract: An apparatus for detecting a cut change based on a similarity between a first image and a second image, includes a unit for generating one of a luminance histogram and a color histogram of each of the first image and the second image, a unit for generating a spatial correlation image representing a correlation between spatial layouts of the first image and the second image, a unit for calculating a histogram similarity representing a similarity between the histogram of the first image and the histogram of the second image, a unit for calculating a spatial correlation image similarity representing a similarity between the spatial correlation image of the first image and the spatial correlation image of the second image, and a unit for determining whether a border between the first image and the second image is a cut change based on the histogram similarity and the spatial correlation image similarity.

Abstract: A classifying of an input image into a business graphic image or a photo image, such as in image calibration of the image. A system classifying an input image into at least one of a business graphic image and a photo image includes a color space transform unit transforming the input image into components of a lightness-saturation color space, a lightness analysis unit calculating a lightness frequency distribution of lightness components among the transformed components, a saturation analysis unit calculating an average of saturation components among the transformed components, and an image classification unit comparing an estimation function using the calculated lightness frequency distribution and the average of the saturation components and a threshold value so as to classify the input image.

Abstract: An aim of the invention is to achieve an image processing method that performs color information correction of an image more naturally with a simple configuration. The image processing method of the invention is an image processing method that performs color information correction of image data that have been input, and includes an information calculation step (S11), a characteristic calculation step (S12), a color information correction step (S13), and an output step (S14). The information calculation step (S11) calculates the color information of the image data. The characteristic calculation step (S12) calculates the visual characteristic information in accordance with the color information. The color information correction step (S13) corrects the color information based on the visual characteristic information that is calculated in the characteristic calculation step (S12).

Abstract: A method of processing digital images to reduce the effects of color bleeding. Chrominance components for pixels in a working window are determined and weights are assigned to the pixels in the working window. A chrominance correction for a center pixel in the working window is generated based on the chrominance components and the assigned weights. Fuzzy variables and thresholds may be applied to generate the assigned weights and the chrominance correction.

Abstract: Embodiments of the present invention comprise systems and methods for detecting glyph pixels in a rasterized image.

Abstract: Embodiments of the present invention comprise systems and methods for characterization of background regions of substantially-uniform color in a digital image.

Abstract: A system and a method for communicating video data associated with content across a network are disclosed. A server partitions the content into a plurality of tiles where each tile includes a subset of the content and index data describing a relationship between a tile and one or more adjacent tiles. Each tile is then encoded as a video frame, for example each tile is encoded according to the H.264 standard. The plurality of tiles are then transmitted to a client which combines the plurality of tiles using the index data to locally recreate the content. The client associates a predetermined viewport tile with a client viewport representing the area of the content that is visible in a client display device to allow viewing of the content while tiles not associated with the client viewport are cached to expedite subsequent retrieval.

Abstract: Foreground segmentation in real world dynamic scenes, including under various lighting and shadow conditions, is disclosed. It may be used with one or multiple cameras for various automated tasks, such as classification of moving object, tracking moving objects, and event detection in various indoor or outdoor environments. Pixel to pixel subtraction is performed on each frame, followed by a feature-level based foreground segmentation to properly validate the foreground pixels. In this step, for each pixel in the image, a neighborhood of pixels is selected, and the aggregate change in the neighborhood image is used to classify foreground and background pixels. Normalized cross correlation is then applied to the neighborhood of each pixel that was confirmed to be foreground pixel.

Abstract: When encoding each element in numeral string data, a code-string data creating unit creates code string data by assigning a code to a focused element to be encoded based on a magnitude relation between the focused element and an element adjacent to the focused element. An control unit stores primary data and the code string data as registration information in an associated manner into a storage unit. When searching for the primary data, a data extracting unit and the code-string data creating unit create code string data from image data, and a searching unit searches data stored in the storage unit based on the created code string data as search information for data having registration information that matches the search information.

Abstract: A method of filling in a form comprising using a digital pen to enter data into data entry areas of the form (64), and providing error feedback to the user (69) contemporaneously with filling in the form, said error feedback being indicative of the user entering a non-allowable entry in said data entry area.

Abstract: A method comprises using pattern recognition to determine whether a display device is being used in a first orientation or a second orientation with respect to the user.

Abstract: Methods for dimensionality reduction of large data volumes, in particular hyper-spectral data cubes, include providing a dataset ? of data points given as vectors, building a weighted graph G on ? with a weight function w?, wherein w? corresponds to a local coordinate-wise similarity between the coordinates in ?; obtaining eigenvectors of a matrix derived from graph G and weight function w?, and projecting the data points in ? onto the eigenvectors to obtain a set of projection values ?B for each data point, whereby ?B represents coordinates in a reduced space. In one embodiment, the matrix is constructed through the dividing each element of w? by a square sum of its row multiplied by a square sum of its column. In another embodiment the matrix is constructed through a random walk on graph G via a Markov transition matrix P, which is derived from w?. The reduced space coordinates are advantageously used to rapidly and efficiently perform segmentation and clustering.

Abstract: To enable efficient detection of a garbled character from only output data of an application, a character string addition unit adds, to input data to the application or other data, an ASCII character string, and a particular character string that follows the ASCII character string and is highly likely to be garbled. An application execution unit executes the application based on the input data to which the character strings are added. A response input unit inputs a response to data output by the application. A database stores output data outputted by the application. A garbled character detection unit detects a garbled character in output data based on the result of comparison between a character string following the ASCII character string in the output data from the application execution unit, the response input unit, and the database, and the particular character string added to the input data.

Abstract: A headline-region initial processing section clips a headline-region image in an image document, divides the image into individual character images, and extracts features of the individual character images. Based on the features, a candidate-character-sequence generating section selects N (N is an integer more than 1) character images as candidate characters in the order of degree of matching from a font-feature dictionary for storing features of individual character images, and generates M×N index matrix where M is the number of characters in an extracted character sequence. Based on the index matrix, a document-name generating section generates a meaningful document name according to the image document. An image-document-DB management section manages accumulated image documents using the document name.

Abstract: An imaging apparatus includes an imaging section, a subject extracting section, and an image processing section. The imaging section captures an object image and generates data of an image. The subject extracting section extracts a main subject from the image. The image processing section performs a noise addition process on the data of the image to add noise for an area where the main subject is positioned within the image.

Abstract: In an embodiment, an image is received having a first portion and one or more other portions. The one or more other portions are replaced with one or more other images. The replacing of the one or more portions results in an image including the first portion and the one or more other images. In an embodiment, the background of an image is replaced with another background. In an embodiment, the foreground is extracted by identifying the background based on an image of the background without any foreground. In an embodiment, the foreground is extracted by identifying portions of the image that have characteristics that are expected to be associated with the background and characteristics that are expected to be associated with foreground. In an embodiment any of the images can be still images. In an embodiment, any of the images are video images.

Abstract: A feature point detection unit (153) and feature amount extraction unit (154) extract a plurality of features of an object from input image data. When there are unextracted features of the plurality of features, a weight setting unit (155) sets weights for the extracted features. A facial expression determination unit (156) executes recognition processing of the object based on the features weighted by the weight setting unit (155).