Abstract: In a method for identifying objects in a digital image which is included in a sequence of images, luminance values of a current digital image are compared with at least one threshold value in order to create a current binarized image on the basis of the comparison. A quality measure for the current binarized image is also calculated, whereupon said at least one threshold value is updated on the basis of the quality measure for use in binarization of a subsequent image. The method can be realized in the form of a computer program, a computer program product, a device, and a hand-held apparatus for position determination.

Abstract: Methods and apparatus, including computer program products, for protecting colors from being clipped during color adjustment. A first set of colors is identified in a source color space, and a first color mapping is specified to associate colors in the source color space with mapped colors. The first set of colors and the first color mapping are used to construct a third color mapping that can be represented as a concatenation of an injective second color mapping with the first color mapping. The third color mapping is constructed such that each color in the first set of colors is associated with a mapped color inside a destination color space.

Abstract: A method and computer program product are disclosed for refining character segmentation in an optical character recognition system receiving as input a plurality of candidate objects. Each candidate object below a threshold character width is merged with another candidate object at one or more merge lines to form a composite object. The plurality of candidate objects are preclassified to identify a plurality of composite objects and a plurality of character portions. Proposed split lines are determined for each of the composite objects. Regions are defined within each of the composite objects from the position of the merge and split lines. The defined regions are classified to obtain an associated score for each region. Complete region sets are defined for each composite object, each with an associated set ranking determined from the associated score of the regions comprising the set. The set having the highest ranking is selected.

Abstract: A method for compressing/restoring image data free from degradation of image quality caused by compression/decompression, a method for compressing image data at high compression ratio, and its restoring method are disclosed. In the image data compressing method, image elements contained in a digital image read from a sheet of paper are extracted (S02), each of the extracted image elements (51-53) is subjected to data compression by a compression method corresponding to the type of the image element (S03-S05), and the compressed image element data (54-56) are stored.

Abstract: Intensity of each pixel in a source video frame is compared with intensities of one or more corresponding pixels in a reference video frame to calculate one or more intensity differences for each pixel in the source video frame. Further, a determination is made for each pixel in the source video frame, based on the intensity differences and multiple threshold sets, as to whether each pixel in the source video frame is a foreground pixel or a background pixel.

Abstract: A method for determining a border of an image includes (a) receiving a composite image including a background image and a foreground image, (b) following one geometric feature (e.g., a line) of the background image, and (c) detecting two or more breakpoints in the first geometric feature where the foreground image superimposes the geometric feature. Actions (b) and (c) are repeated to detect breakpoints for a number of the geometric features. The border of the foreground image is determined by constructing linear edges that each connects three or more breakpoints and extending the linear edges until each intersect with two other linear edges to form the border of the foreground image. An apparatus for determining a border of an image includes a scanner and a document cover. The document cover includes a blue backdrop and geometric features. The geometric features include green vertical and horizontal lines.

Abstract: A system and method for effectively performing an image data transformation procedure may include an electronic camera device that is implemented to capture primary image data corresponding to a photographic target. A transformation manager in the electronic camera device may be configured to convert the primary image data into secondary image data by utilizing selectable transformation parameters that are optimized by utilizing an optimization metric to thereby minimize noise characteristics in the secondary image data. The transformation parameters may be stored in parameter lookup tables in the electronic camera device for use by the transformation manager in performing the image data transformation procedure.

Abstract: A method and apparatus to reduce the system load of motion estimation for DSP discloses circular buffers, a plurality of absolute difference calculation circuits, a multiple input adder, a full adder, a plurality of accumulators, and a control circuit. The first four bytes from the reference block buffer and the first four bytes from the search window buffer are sent to the four absolute difference calculation circuits. The control circuit determines which of the accumulators requires incrementing the value already in that accumulator by the current output of the multiple input adder. A new set of bytes from the search window buffer is then sent to the absolute difference calculation circuits, a new sum is calculated, and a second accumulator is incremented by the new sum. When all accumulators have been updated, new reference block data used. Each byte of data is loaded from memory only once.

Abstract: Undesirable artifacts appearing in color images, such as blooming or smudging around the edges of text, are avoided through selective reduction of the color gamut for objects which form the image. Individual component color values are modified by taking into account combinations of colors and their effect upon the artifacts to be eliminated. Only those parameter values which contribute to the artifact are modified. Other parameter values are left intact, to maintain the original image characteristics. When a color value is modified, all components of that color are modified in a symmetrical manner, to preserve the hue of the original color. The impact on the image is further minimized by selectively applying color correction only to those objects in which the artifact is pronounced.

Abstract: A method and apparatus for coding a chrominance component of an intra-image using spatial predictive coding and a method and apparatus for decoding the coded chrominance component are provided.

Abstract: A method for detecting an object in a digital image including the steps of performing color quantization on a model image including the object and on a search image that potentially includes the object, generating a plurality of search windows, computing spatial-color joint probability functions of each model and search image, where the color co-occurrence edge histogram is chosen to be the spatial-color joint probability function, assessing the similarity of each search image to the model, and designating search windows as containing the target object.

Abstract: Techniques and tools for spatial extrapolation of pixel values in intraframe video encoding and/or decoding are described. For example, to predict the pixel values for a block of pixels, a video encoder or decoder uses spatial extrapolation from the pixel values of pixels in a causal neighborhood for the block of pixels.

Abstract: An image compression technique in which patterns identified, the means of separating the image components, the parameterization of the patterns, and the lower level numerical encodings are all designed around a narrow class of images, such as two-dimensional projections of three-dimensional visualizations of data generated by numerical weather simulations. The process analyzes an image in terms of perceptual constructs of the human visual system and searches for patterns among analyzed abstractions of the image. The image is then described in terms of the perceptual constructs and the patterns found among them. The image is re-represented by describing the image as a collection of parameterized versions of the patterns prevalent in that class of image. A resulting description is taken outside of the context of abstract patterns. Redundancies in the description are looked for and the data is re-represented so as to eliminate the redundancies and compress the description.

Abstract: A method for resizing images using the inverse discrete cosine transform (IDCT). The method enables digital video processing devices such as DVD players, digital broadcast receivers, or HD TVs to enlarge an original image to an arbitrary size without resulting in distortions in the enlarged image, thereby preventing deteriorated image quality.

Abstract: Further compression of data allowing economical storage of data for extended periods of time in high-speed access memory is performed in reduced time by performing further compression during transcoding in the transform domain and without restoring image data to its original image data form. The reduction in processing time is achieved by exploiting the large number of zero-valued quantization transform coefficients and not changing quantized transform coefficients at zig-zag scan positions where non-zero coefficients are rare during range reduction of the entropy decoded quantized transformed data. The range can be restored by computation or estimation of an altered quantization table which is stored with the further compressed a quantization values. Further advantages accrue from use of JPEG packed format for the data during transcoding.

Abstract: From inputted multilevel image data it is generated, for each pixel, image area information constituted by an image area component indicating whether the pixel exists in a character•line drawing area or halftone area and an image area component indicating whether the pixel is chromatic or achromatic. The information is encoded by a lossless encoding unit on a block basis and stored, and an amount of code is monitored. When the amount of code exceeds a target amount, the lossless encoding unit performs encoding upon changing image area components, of subsequently input image area components, which coincide with a condition. The codes that have already been stored are temporarily decoded by a lossless code re-encoding unit, and the above image area components are changed. The resultant data is then re-encoded and stored.

Abstract: An image capturing apparatus for capturing an image of a subject; has: an image pick-up unit for acquiring the image; and a noise reduction unit which removes a frequency component of a color difference signal of the image corresponding to a frequency component of a luminance signal based on the frequency component of the luminance signal of the image.

Abstract: An image compression system and method is described, which makes use of the symmetry found in faces and heads to perform the compression. The image is divided along the line of symmetry, and pairs of corresponding pixels on the two divided sides are determined. A weighted average and a weighted variance of the pixel values of the pairs is computed, and is used to encode the image. A transform such as the Karhunen-Loeve transform is used to compute the weighted averages and variances.

Abstract: The present invention relates to a real-time wideband compressor for multi-dimensional data. The compressor comprises a plurality of compression engines for simultaneously compressing a plurality of data subsets of a set of input data vectors and providing compressed data thereof using one of SAMVQ or HSOCVQ data compression. Each compression engine comprises an along spectral vectors codevector trainer as well as an across spectral bands codevector trainer. The compression engines are programmable to perform either along spectral vectors codevector training or across spectral bands codevector training in combination with one of the SAMVQ or HSOCVQ techniques without changing hardware. The compressor further comprises a network switch for partitioning the set of input data vectors into the plurality of data subsets, for providing each of the plurality of data subsets to one of the plurality of compression engines, and for transmitting the compressed data.

Abstract: A method for volume scoring a concentration of calcification within a region of interest includes receiving a value for a first calcium lesion volume based on the concentration of calcification within the region of interest, determining an intensity value of the concentration of calcification within the region of interest, calculating the slope of a regression line based on the determined intensity value, and calculating a second calcium lesion volume based on the first calcium lesion volume and the calculated slope of the regression line.