Abstract: A method of adapting image information to the perceptive capacity of the human eye, having the following steps: (a) displaying lightness values and colorimetric values or chromaticity steps from an original image as a group of points in an initial color space; (b) transferring the group of points into a physiological substantially equal-spaced perceived color space while maintaining the geometry of the group of points within the limits of an output color space projected into the perceived color space; (c) transforming the group of clouds from the perceived color space into the output color space by using the transformation equations existing between the perceived color space and the output color space; and/or (d) displaying the image with lightness values and colorimetric values or chromaticity steps in accordance with the points contained in the output color space.

Abstract: An image processing apparatus and method for analyzing a digital image and automatically generating a visually attractive frame for the image. A data set for the image is analyzed, preferably in color space, to determine one or more image components representing dominant colors in the image. The components are characterized individually, and then these individual component characterizations are used to characterize the image overall. Based on the overall image characteristics, the framing scheme parameters are determined and used in turn to generate the attributes of a visually attractive frame for the image. A data set for the framed image is then generated, which may be sent to an imaging device for display or printing, or simply stored as a new data set for later use. The user has the ability to modify the rules that determine the framing scheme parameters so as to adjust the framed image if desired.

Abstract: A digital image processing method for locating eyes and mouth in a digital face image. The method includes the steps of detecting iris colored pixels in the digital face image; grouping the iris colored pixels into clusters; detecting eye positions using the iris colored pixels; identifying salient pixels relating to a facial feature in the digital face image; generating a signature curve using the salient pixels; and using the signature curve and the eye positions to locate a mouth position. In a preferred embodiment, a summation of squared difference method is used to detect the eye positions. In another preferred embodiment, the eyes and mouth positions are validated using statistics.

Abstract: In an embedded DCT-based (EDCT) image coding method, decoded images which give better PSNR over earlier JPEG and DCT-based coders are obtained by a scanning order starting, for each bitplane, from the upper left corner of a DCT block (corresponding to the DC coefficient) and transmitting the coefficients in an order of importance. An embedded bit-stream is produced by the encoder. The decoder can cut the bit-stream at any point and therefore reconstruct an image at a lower bitrate. The quality of the reconstructed image at this lower rate is the same as if the image was coder directly at that rate. Near lossless reconstruction of the image is possible, up to the accuracy of the DCT coefficients. The algorithm is very useful in various applications, like WWW, fast browsing of databases, medical imaging, etc.

Abstract: A method and apparatus for sectioning an image into a plurality of regions, by which regions of an image having various features can be extracted stably in a form similar to what humans can perceive, are provided.

Abstract: An electronic camera imaging system records a color filter array (CFA) image. The missing color values of the CFA image are reconstructed using a linear transformation. The coefficients of the linear transformation are estimated in one embodiment by computing an average value over a window of the CFA image by equalizing the mean and the variance of the color channels of the window. In another embodiment, the coefficients of the linear transformation are estimated by fitting a line to a set of the sums of column and rows of color channels of a window of the CFA image.

Abstract: A high-resolution still picture decoding device is disclosed, which has a memory device, an image decoder, and a decoding controller. The memory device has a bit-stream buffer, a frame buffer and a temporary buffer. The image decoder and decoding controller decode the bit-stream data in the bit-stream buffer and store the decoded data in the frame buffer or temporary buffer. When a still picture is to be displayed, the frame buffer stores part of the frame data corresponding to the still picture and the temporary buffer is provided to store the other frame data which is decoded in real time as the still picture is displayed. The data in the frame buffer and temporary buffer is output for displaying a high-resolution still picture.

Abstract: A method and apparatus for enhancing a digital image. First, human faces are located within a digital image. The digital image is then analyzed, including analysis of the regions determined to be human faces and the analysis of the digital image as a whole. A tone mapping function is then determined for enhancing the image quality of the digital image. The tone mapping function is determined using both the analysis of detected faces and the analysis of the image as a whole to obtain a tone mapping function that incorporates both psychological factors (e.g., average face region lightness and average picture lightness) and signal factors (e.g., digital resolution, face region contrast, histogram uniformity, and noise issue). The tone mapping function is then applied to the digital image so as to produce an enhanced digital image. The present invention is automatic and does not require that the user provide any input.

Abstract: A plurality of images of portions of a fingerprint surface is generated by measuring structural features the portions of the surface with a sensor array as the surface is moved relative to the array. A two-dimensional image of the fingerprint surface is constructed from a portion of the plurality of images. In one embodiment, a varying voltage is applied to a finger positioned over an exciting electrode and a capacitive sensor array, and the capacitance or impedance through the finger is measured between the electrode and the array to detect variations in capacitance or impedance caused by variations in the structural features of the fingerprint surface.

Abstract: An image processing system is arranged to process an array of pixels. The array is scanned in a sequential manner, pixel by pixel, each pixel being scanned only once. The resulting scan data is processed to identify pixels which contain image information of significance, and to assign these pixels to an image segment which may contain a number of such pixels. The system provides a data output of summary information pertaining to the segment or segments identified in the image. In this way a segmentation scan is performed which is very efficient and which produces summary information without a further processing step.

Abstract: The invention relates to digital image enhancement, and more precisely to a guided color correction system that produces a desirable image display and reproduction. A major objective of the invention is to determine appropriate image transformations based on the user's personal preference. This is achieved by using a guided system that employs diametrically opposed or contrariwise enhancement parameter transformation previews. During the process, the user chooses the most preferred preview to determine a parameter. The amount for each parameter is determined and a final transformation is applied. The invention is designed to increase color correction speed, efficiency, and accuracy by drastically reducing the complexity and heretofore random, haphazard, and arbitrary process of conventional digital image enhancement and color correction.

Abstract: Quantization in video coding is a lossy treatment and has as its main result that blocking artefacts occur at the boundary of two blocks during the decoding process. The invention relates to a method of removing these blocking artefacts. It implements a filtering step in the decoding process applied to a segment of pixels phaddling the boundary, which segment has pixels at the ends (R3, L3) that agree with a chrominance similarity criterion (step 1), i.e. filtering is applied to segments for which the pixels at the ends have similar colors.

Abstract: An optical inspection system and method for inspecting a component on a printed circuit board (PCB) which determines three-dimensional information in a single scan. A first visual light source illuminates the PCB surface and component with a green light while a second visual light source illuminates the PCB and component with a blue light. At least one laser light source simultaneously illuminates the surface of the PCB with a narrow coherent red-light laser beam. The laser light source is mounted off vertical on a movable mount which enables the laser beam to be directed over an area of interest on the surface of the PCB. The system also includes a color scan camera mounted vertically above the PCB. The camera has red, green, and blue channels. The green and blue channels capture an image of the illuminated surface of the PCB which is used by a computer to determine two-dimensional information about the component.

Abstract: A document image processing device and method for extracting a title region and a mark attached by the user from a document image to use them as document tag information. A region with a region average character size larger then a predetermine extraction judging value is extracted as a title region by title region extracting means. As a result, title regions can be extracted from one document image. A mark that the user makes on an input image is extracted by mark extracting means, and characteristic value of the mark is found by calculating means. Document tag information to be imparted to the input image is selected from reference tag information according to the characteristic value and the attribute value of the reference tag information imparting means. Thus, document tag information is automatically imparted to a document image.

Abstract: A system comprising means, which stores, regenerates, or matches shape of curves, by using a specified group of data in length to express a shape of curve. The system uses a sequence of several measure points on the curve, which are determined so as to make the same distances between those adjacent measure points. They are the data of lengths of arcs between starting measure point and ending measure points among every three consecutive measure points on the curve.

Abstract: A method is disclosed for classifying an input pattern into an associated class through use of a compound classifier. Data pertaining to preselected features present within the input pattern are extracted. A discriminant value for each of a plurality of classes is then determined via a first classification technique. This value reflects the relative likelihood that a class is the associated class. The class with the highest relative likelihood is selected. A confidence value is generated via a second classification technique. This confidence value is reflective of the a posteriori probability that the selected class is the associated class. The selected class is rejected if the determined confidence value is below a predetermined threshold value.

Abstract: The method discloses a method of segmenting an image. The method firstly (304) allocates pixels as seeds in areas of an image as a function of the luminance of the pixels and the size of those areas. The method then grows (306) regions from said seeds so as to segment the image into a number of regions. The method considers a number of pixels that border the growing regions and the pixel that is most similar in luminance to a region it borders is appended (528) to that region. The method then updates (528) the luminance of the appended region. The method continues until there are no more pixels bordering the growing regions. The method then encodes the segmented image (106). It does this by splitting (604) the image into a number of rectangular sub-images in a quadtree manner until each rectangular sub-image comprises a segmented image forming the dominant portion of the sub-image. The method then merges (606) rectangular sub-images which have a common dominant portion and share a common edge.

Abstract: Methods for decomposing compound documents for mixed raster content representation are provided. A method for decomposing an image includes the step of decomposing the image into a plurality of stripes. Each stripe is decomposed into foreground, background, and mask layers. The layers are interpolated to modify values of irrelevant pixels in order to achieve more efficient compression. The layers may subsequently be compressed with a coder.

Abstract: A method of pattern matching for recognition of objects within an image, uses a model defined by a set of one or more model primitives representative of large scale structures of an archetype. The image is analyzed to derive at least one target primitive representative of a large scale structure of the image. A basis is derived from at least one of the target primitives, and each of the target primitives represented as invariants in the derived basis. For each target primitive, any model primitives that at least partially match the target primitive are identified. Each identified model primitive is then processed to calculate a figure of merit indicative of a degree of correspondence between the target primitive and the model primitive. In some embodiments, the figure of merit is an Orthogonal projection between the target and model primitives, which is and accumulated for each model basis.

Abstract: Methods and systems for compression of digital images (still or motion sequences) are provided wherein predetermined criteria may be used to identify a plurality of areas of interest in the image, and each area of interest is encoded with a corresponding quality level (Q-factor). In particular, the predetermined criteria may be derived from measurements of where a viewing audience is focusing their gaze (area of interest). In addition, the predetermined criteria may be used to create areas of interest in an image in order to focus an observer's attention to that area. Portions of the image outside of the areas of interest are encoded at a lower quality factor and bit rate. The result is higher compression ratios without adversely affecting a viewer's perception of the overall quality of the image.