Abstract: The present invention provides methods and apparatus to distinguish and/or separate an object from a background. The methods use backgrounds of known and/or advantageous texture. In an embodiment, a measure of image texture, namely the spatial frequency is used to distinguish and/or separate an object from its background. The use of image texture overcomes limitations of chroma keying used as a processing technique in photography for object-background separation. This is useful in the separation of image pixels belonging to the object of interest from image pixels belonging to the background.

Abstract: A computer aided detection method and system to assist radiologists in the reading of medical images. The method and system has particular application to the area of mammography including detection of clustered microcalcifications and densities. A microcalcification detector is provided wherein individual detections are rank ordered and classified, and one of the features for classification is derived using a multilayer perceptron. A density detector is provided including an iterative, dynamic region growing module with embedded subsystem for rank ordering and classification of a best subset of candidate masks. A post processing stage is provided where detections are analyzed in the context of a set of images for a patient.

Abstract: An input image is inputted into a pre-process circuit and a spatial filter. The pre-process circuit emphasizes a linear shadow or an edge to some extent, or reduces noises overall. Following pre-processing, the image signal is supplied to a direction detection circuit, a direction and its intensity of an area of interest are detected. These two results of the detections are correlated with peripheral areas of interest to some extent by a vector filter. An output of the vector filter is supplied to a spatial filter coefficient generation circuit, and a filter coefficient of the spatial filter is decided. The spatial filter processes the input image based on the direction of the shadow and its intensity, whereby selectively suppressing noise components of the background in real time without damaging the contrasts of a linear shadow or an edge-like shadow.

Abstract: A radiographic imaging system (100) comprises an X-ray tube (110), a sensor plate (120), and a graphics engine (130). The tube (110) and the sensor plate (120) rotate synchronously about a patient (150) and expose a stereoscopic pair of images which are transmitted to the graphics engine (130). The graphics engine (130) determines (312) the geometry of the system (100). If (314) the pair of images are toed-in relative to each other, the graphics engine (130) converts (316) the images into a parallel geometry. Likewise, the graphics engine (130) also processes (320) the images for keystone distortion, if necessary. Simply flipping the images in the stereo pair distorts the depth of objects in the stereoscopic image. Instead of simply flipping the images, it is desirable to “go behind” the screen (412A) and look at the image from the back.

Abstract: Methods and systems for fingerprinting digital data are described. In the described embodiment, Direct Sequence Spread Spectrum (DSSS) technology is utilized. Unique fingerprinting words are defined where each includes at least one spread sequence. In the described embodiment, a fingerprinting word comprises a plurality symbols, called “&Ggr; symbols.” Each &Ggr; symbol is composed of 2c-1 blocks, where c represents the number of colluders that are desired to be protected against. Each block contains d spread sequence chips. The fingerprinting words are assigned to a plurality of entities to which protected objects embedded with the fingerprinting words are to be distributed. To ascertain the identity of an entity that has altered its unique fingerprinting word, the relative weight of each block is computed in accordance with a defined function and blocks whose weights satisfy a predetermined relationship are “clipped” to a so-called working range.

Abstract: In a method for varying one or more print attributes of a print made from a digital image, a print attribute value is computed for the digital image based on a determination of the degree of importance, interest or attractiveness of the image and the resulting print attribute value is used to control a print attribute of the print made from the image. The print attribute value is derived from an emphasis or appeal value, wherein an appeal value is an assessment of each image taken by itself and the emphasis value is an assessment of each image in relation to other images in a group. In a typical embodiment, the print attribute is either the number of prints made of the image, the size of a print made from the image, or the magnification factor used for the image.

Abstract: A sensor system utilizing a Composite Hough Transform (CHT) operates on multiple corresponding broadband correlograms produced at two neighboring dual-channel sensor systems. A broadband signal source can generate one correlation trace on each of the correlograms. Since these correlation traces are produced by the same signal source, they are constrained by a set of geometric relationships. By fully exploiting this set of constraints, the CHT fuses sensor data from multiple dual-channel sensor systems for target detection and track parameter estimation. The dual-channel system can be (a) a split-array system; a linear array split into two subarrays with each subarray corresponding to one of the channels, (b) two neighboring linear arrays, or (c) two neighboring individual hydrophones. The CHT operates with two neighboring linear subarrays. One of the sensor arrays is chosen as the primary array; it is used to originate the different track hypotheses for the signal source.

Abstract: A method and system of providing segmentation of volumetric three-dimensional image data set such as MRA images. Initially, a three-dimensional MRA volume is input. An initial surface S is then generated by thresholding the input. A signed distance function v to S is then generated, where v=v(x,t) and S is the zero level set of v(·,0).

Abstract: An automatic segmentation module with an open architecture that automatically generates a contour of a target bone based on a digital image. In one embodiment, the digital image can include an extremity, such as a hand with three digits and a calibration wedge. The automatic segmentation module receives the digital image as an input, and automatically segments the target bone by utilizing an object-oriented approach. This approach extracts intermediate target objects and uses these intermediate target objects to refine or limit the search space in order to extract the final target object.

Abstract: An image authentication method by embedding digital watermarks into images, comprising: providing an original image and a watermark image; applying pseudo-random permutations to the watermark image for generating a dispersed watermark image; applying block-based permutations to the original image and the dispersed watermark image in order to form a plurality of original image blocks with each of the watermark blocks dispersed over the corresponding image block only; applying FDCT (Forward Discrete Cosine Transform) on each of the original image blocks independently so that each of the original image blocks is transformed into a DCT coefficient block that corresponds to different frequency ranges; embedding said watermark image blocks into said DCT coefficient blocks, in order to form a plurality of combined DCT coefficient blocks; applying IDCT (Inverse Discrete Cosine Transform) to the combined DCT coefficient blocks to form an embedded watermark image.

Abstract: A digital watermark inserting system for inserting digital watermark information into an input image is disclosed, that comprises a categorizing portion 103 for calculating a feature amount of the input image, categorizing the input image to a category index, a digital watermark characteristic calculating portion 104 for calculating an image deteriorating ratio and a robustness evaluation value corresponding to a digital watermark strength based on a robustness evaluation value calculation parameter and the category index, a digital watermark strength calculating portion 100 for outputting the digital watermark strength to the portion 104, deciding the optimum digital watermark strength based on digital watermark strength restriction information, and outputting the optimum digital watermark strength, and a digital watermark inserting portion 102 for converting input embedding data into digital watermark information, inserting the digital watermark information into the input image.

Abstract: A process for detection of straight-line segments in a stream of digital data that are representative of an image (m, n) in which the contour points of said image each defined by the modulus and the orientation &thgr; of their gradient in relation to a horizontal axis are identified. The stream of digital data is stored in the form of two successive lines, each of n points P(i, j), for each of the lines the n points of said line are extracted successively, and for each point Pc(i, j) extracted, the so-called current point, the three points having inferior coordinates Pa(i−1, j−1), Pb(i, j−1), Pd(i−1, j) directly neighbouring said current point are extracted, successively the value of the orientation of the current point Pc is compared with that of the neighbouring points Pa, Pb and Pd. The values of the orientations of the points Pb and Pd are compared, the result of a comparison is validated if the points are contour points and if the values of their orientation are close.

Abstract: A method and apparatus for detecting edges by which the detection of the edges of a natural image from an image obtained by mixing the graphic or text and the natural image is suppressed, to thereby stably detect edges of the graphic or the text, are disclosed. In this method, the differences in pixel value between the first pixel of sequentially input images and eight pixels adjacent to the first pixel are obtained. If all of the differences between the first pixel and the eight pixels adjacent to the first pixel are greater than a maximum threshold value or less than a minimum threshold value, the first pixel is determined to be an edge pixel. Likewise, determinations are made as to whether a second pixel, positioned adjacent the first pixel along a first dimension (for example to the left of the first pixel), is an edge pixel and whether a third pixel, positioned adjacent the first pixel along a second dimension (for example above the first pixel), is an edge pixel.

Abstract: A watermarking method and device to embed a digitized watermark into a digital image file in the spatial domain first performs error correction to enhance the robustness of the digital image. The digital image file is first processed such that capacity of each element of the digital image file is calculated. The capacity represents the highest power of element of the watermark that can be added to the related element of the digital file. Elements to which watermark elements may be added are selected and their addresses are stored. Elements of the watermark file are then inserted into the selected addresses in sequence and the watermark is modulated. After the modulation the digitized watermark is embedded into the digital file by distributing the modulated elements of the watermark into the selected addresses.

Abstract: A pattern recognition apparatus that comprises an input section, a feature extraction module, a feature transform module, a recognition section that includes a recognition dictionary, and a categorizer. The input section receives input patterns that include a pattern belonging to one of plural categories constituting a category set. The feature extraction module that expresses features of the pattern as a feature vector. The feature transform module uses transform vector matrices to transform at least part of the feature vector to generate an at least partially transformed feature vector corresponding to each of the categories. The transform vector matrices include a transform vector matrix generated in response to a rival pattern set composed of rival patterns misrecognized as belonging to plural ones of the categories. The plural ones of the categories constitute a category subset. The at least partially transformed feature vector is common to the ones of the categories constituting the category subset.

Abstract: A digital watermark inserting system for inserting digital watermark information into an input image is disclosed, that comprises a categorizing portion 103 for calculating a feature amount of the input image, categorizing the input image to a category index, a digital watermark characteristic calculating portion 104 for calculating an image deteriorating ratio and a robustness evaluation value corresponding to a digital watermark strength based on a robustness evaluation value calculation parameter and the category index, a digital watermark strength calculating portion 100 for outputting the digital watermark strength to the portion 104, deciding the optimum digital watermark strength based on digital watermark strength restriction information, and outputting the optimum digital watermark strength, and a digital watermark inserting portion 102 for converting input embedding data into digital watermark information, inserting the digital watermark information into the input image.

Abstract: A vehicle video imaging system comprises a white-light LED array for illuminating retro-reflective painted parts of a vehicle's license plate, a powerful flash with a visual spectrum cutout filter and a polarizing filter for illuminating any non-retro-reflective license plate paint and the vehicle itself. A video camera with a polarizing filter turned 90° relative to the one in front of the flash receives the illuminated image of the vehicle and its license plate. The retro-reflective paint of a license plate will return polarized light as it is received, so the white-light LED array will provide all the illumination needed by the camera to get a good high-contrast picture of the license plate. The polarizing filters will combine to block out most of the light from the flash that was returned still-polarized by the retro-reflective-paint license plate.

Abstract: An MRA image is corrected for motion artifacts using an iterative, autocorrection process in which corrections are tried and the quality of the resulting reconstructed image is measured. Corrections are made to the acquired three-dimensional data while the metric which measures image quality is applied to a two-dimensional projection image.

Abstract: A moving image data fetch section extracts frame images as well as audio information from moving image data and stores them in a frame memory. A feature amount detection section detects the change of a feature amount included in the frame images constituting the moving image data, and an image selection section selects specific frame images based on the detected image changing characteristics or audio changing characteristics. An image processing section selects a frame image having particularly great change of the image or audio data from among the selected frame images as a to-be-processed image and processes the selected image to have a predetermined expression form. A monitor, a printer or the like outputs the specific frame images selected by the image selection section and the frame image selected and processed by the image processing section as still images.

Abstract: In one aspect, the present invention is a method for scanning an object with a multi-slice CT imaging system having multiple detector rows each having an isocenter. The method includes steps of helically scanning an object with the multi-slice CT imaging system to obtain data segments including peripheral data segments, combining data from a first peripheral data segment with an opposite, second peripheral segment to form a data set for reconstruction of an image slice; and reconstructing the combined data into image slices.