Abstract: An image analyzing apparatus includes an image data memory for two-dimensionally and temporarily storing image data and is adapted for displaying an image on a CRT based on the image data temporarily stored in the image data memory and effecting a quantitative analysis. The image analyzing apparatus includes further includes a profile data producing section for producing profile data of density in a predetermined image region based on the image data temporarily stored in the image data memory and storing them in the image data memory and a region-of-interest defining section for defining a region of interest in a density profile displayed on the CRT based on the profile data.

Abstract: A method of automatic determination of preferred tone-scale parameters for digital radiographic images comprising; providing an input digital medical image and an associated tone-scale LUT (look-up table) determining the associated contrast parameter which will result in preferred equivalent contrast with the tone-scale LUT; determining the toe and shoulder parameters which will result in preferred equivalent toe and shoulder with the associated tone-scale LUT; determining the density shift parameter which will result in preferred equivalent density with the associated tone-scale LUT; and generating a preferred LUT from the results of said three determining steps.

Abstract: An SNR-adaptive method for processing a plurality of post-detection medical diagnostic ultrasonic images determines a cross-correlation parameter from corresponding multi-dimensional regions of first and second post-detection ultrasonic images, and then uses the cross-correlation parameter to suppress electronic noise in ultrasonic image processing. In some cases the multi-dimensional region of the first and second images are registered prior to cross-correlation to compensate for relative movement between the transducer and the imaged tissue between the first and second images.

Abstract: In a method and a device for transmission of S+P transform coded digitized images a mask is calculated by means of which a region of interest (ROI) can be transmitted lossless whereby the ROI can be transmitted and received lossless and still maintaining a good compression ratio for the image as a whole. This is possible since no or very few bits can be used for the remaining part of the image. The calculated mask can also be used for transmitting the coefficients needed for a lossless region of interest during any stage of the transmission.

Abstract: A control unit selects a first labeling for a color image in a small number of colors so that the labeling is performed by clustering a color palette, and selects a second labeling for a color image in a large number of colors so that the labeling is performed by an adjacency expanding method.

Abstract: Error addition section 201 generates correction data by adding correction value Emo and correction value E1 to the input data. Binary processing section 202 converts the correction data to binary data to generate output data. Binary error calculation section 203 calculates binary error E based on the correction data and output data. Propagation coefficient judgment section 204 judges propagation coefficients K1 to K4. Propagation error operation section 205 operates on binary error E and propagation coefficients K1 to K4 to calculate correction value E1 and correction value Emi. Error memory 206 temporarily stores correction value Emi, and outputs it to error addition section 201 when the pixel data to be corrected is input.

Abstract: A super-resolution image is generated from a pixel image by first performing an initial image interpolation, creating an interpolated low resolution image. The interpolated low resolution image is then partitioned into overlapping low resolution patches. The low resolution patches are then processed in a raster scan order. For each low-resolution patch, a scaled mid band patch is generated. A search vector is constructed from pixels in the scaled mid band input patch, and pixels in an overlap region of adjacent previously predicted high band patches. A nearest index vector to the search vector is located in a training database, the nearest index vector has an associated high band output patch. The high band output patch is then combined with the interpolated low resolution patch to predict pixel values for the corresponding high resolution patch of the super-resolution image.

Abstract: A method of estimating local defocus distance from a conventionally scanned image is provided. More particularly, the method of estimating defocus distance in a scanned image of a non-planar original object, such as an open book, includes scanning at least a portion of the book in order to produce scanned image data. An image feature obtainable from the scanned image data and a quantitative metric corresponding to the image feature are selected. Image feature data is extracted from the scanned image data and compared to a predetermined calibration relationship between the selected image feature and defocus distance in order to calculate a plurality of defocus distances, which are organized into a defocus distance map. The defocus distance map may be used in the subsequent correction of geometric distortions, blurring defects, and illumination variations adjacent the binding of an open book.

Abstract: This invention has as its object to provide a viewpoint detection apparatus and method, which can assure high-speed processing, high precision, and high tracking performance with a simple arrangement while suppressing adverse influences on the human body, and a stereoscopic image display apparatus using the same. The viewpoint position detection apparatus of this invention has an image sensing unit (1) and a viewpoint detection unit (2). The image sensing unit has a visible image sensing section (11) and infrared image sensing section (12). A pupil position detection processing section (24) detects the pupil position from an infrared image, and a template generation section (23) generates templates for a visible image using the pupil position obtained from the infrared image. A pattern matching discrimination section (22) executes pattern matching of a visible image.

Abstract: An object-based quad-tree mesh motion compensation method using the Greedy algorithm is provided. This method defines an object-based quad-tree mesh structure defined by extending a hierarchical grid interpolation technique, by which complicated or partial motion is more accurately displayed, so that it is suitable for an object-based technique. Also, this method provides a quad-tree block segmentation method using the Greedy algorithm by which the transmission rate-distortion performance of motion compensation is improved. The object-based quad-tree mesh motion compensation method using the Greedy algorithm, includes (a) defining an object-based quad-tree mesh, (b) segmenting each block in an image frame, which is segmented into blocks of predetermined sizes, in order to form the object-based quad-tree mesh of the step (a), and (c) estimating the motions of vertices to minimize distortion during compensation of motions within the segmented block, and compensating for the motion of an image within the block.

Abstract: A method that enables the carrier of letters, flats and/or packages (mail) that are addressed to a recipient to determine if the mail contains life harming materials, before the mail is delivered to the recipient. The invention accomplishes the foregoing by receiving mail that is addressed to a recipient which contains material that may or may not be life harming; capturing an image of the face of the mail, which includes the name and physical address of the recipient; processing the image on the face of the mail to determine if characteristics of the image match characteristics of known mail that may contain life harming materials; testing the mail if the image contains characteristics of life harming material; and delivering the mail to the recipient if the image does not contain life harming characteristics.

Abstract: A system and method for using a machine vision system to locate and register patterns in an object using range data is provided. The machine vision system includes an acquisition system for acquiring a range image of an object. The system also includes a machine vision search tool coupled to the acquisition system for locating an instance of a trained pattern in the image. The tool registering the trained pattern transformed by at least two translational degrees of freedom and at least one non-translational degree of freedom with respect to an image plane. The acquisition system preferably includes a three-dimensional camera.

Abstract: The present invention relates generally to interpolation methods for automatic generation of an accurate digital elevation model, and more particularly relates to intelligent interpolation methods for accurate extraction of 3-dimensional digital elevation models from satellite images, aerial photographs, or land surveying. The present invention is composed of three basic processes: The first process (102) of COG/ECI elimination, the second process (104) of hole-fill segmentation, and the third process (103) of noise-remove segmentation. The invention produces an accurate digital elevation model even for the areas with open boundaries such as the sea off the coast and over a river.

Abstract: A color correction apparatus and method in which a mask is derived from image data in a first pixel representation and is used to convert the image data into a perceptual color space representation which is a function of a background luminance parameter. The mask corresponds to a blurred monochrome version of the original image and includes a set of averaged greyscale values having a pixel-by-pixel correspondence with the original image. The values within the mask vary dependent on the location of the corresponding pixel within the image data. When converting the image data pixel-by-pixel into the perceptual color space representation, localized color correction is obtained by using varying mask values as the background luminance parameter for each pixel conversion.

Abstract: This invention relates to a method and apparatus for implementing a trapping operation on a digital image during image processing. More specifically, the invention is directed to implementation of a trapping technique to prevent visual gaps or overlaps between colors on a poorly registered image that is produced by an imaging device, e.g. a color printer. The invention is most advantageously used in an imaging device that incorporates therein a split-level buffer.

Abstract: A method of registering images is provided which includes capturing a first original image of a scene under surveillance, capturing a second original image of the scene under surveillance, coarsely matching the first original image to the second original image to give approximate angle and offset parameters of the first original image to the second original image, and finely matching the first original image to the second original image based on the approximate angle and offset parameters of the coarsely matching step. The coarsely matching step involves applying a plurality of rotations to a reduced version of the first original image to form a rotated and reduced first original image and performing a correlation match between the rotated and reduced first original image and a reduced version of the second original image.

Abstract: In a color image dividing method, color differences between pixels of the color image are calculated, and widths of division in directions of axes of a color space are determined on the basis of the color differences between the pixels. Then, the color space is divided into regions according to the widths of division in the directions of the axes, and a color classification number is set for each of the color space regions. Each pixel of the color image is labeled with the color classification number of the corresponding color space region in which a color of the pixel is included. Then, the color image is divided into regions based on the classification numbers of the labeled pixels. When pixels having a same classification number occur consecutively, those pixels are determined to constitute one region.

Abstract: An image processing system and method employs a registration processor (130) to calculate a statistical measure of likelihood for two volumetric images (110, 112). The likelihood is calculated based on an assumption that the voxel values in two images in registration are probabilitically related. The likelihood is calculated for a plurality of relative transformations in iterative fashion until a transformation that maximizes the likelihood is found. The transformation that maximizes the likelihood provides an optimal registration and the parameters for the optimized transform are output to memory (150) for use by a display system (160) in aligning the images for display as a fused or composite image. If statistics about the relationship between the involved images are known, a mutation probability can be derived and used in the likelihood calculation. If there is no such prior knowledge, the mutation probability can be estimated purely from the image data.

Abstract: A method and apparatus is disclosed for converting raster images into a vector format by identifying and converting the borders of image features into a mathematical format referred to as string sequences. To enable the string sequencing of color images, the present invention identifies and resolves contrast conflicts in the image features in order to avoid misperceiving the vectorized image when converted back into a raster format. A contrast conflict occurs when there is a “contrast tie” between overlapping features of the image. The feature that would normally be perceived as the dominant feature breaks the contrast tie so that when the vector image is reconstructed, the dominate feature appears in the foreground of the image while the recessive feature appears in the background.

Abstract: A position detection tool in a machine vision system finds the position of target objects in a digital image using the length and width of the target object as parameters. The input length and width dimensions are measured by the developer as the length and width of a simple hypothetical rectangle that surrounds the object. For most shapes, the developer can easily obtain these two measurements. The position detection tool can easily be adapted to discern particular image patterns from multiple component images.