Abstract: Two document images which have been compressed using the JBIG-2 standard for facsimile applications so as to include a plurality of index numbers, one or more positions in each image associated with the index numbers, and a group symbol for each index number can be merged to form a final composite image. Firstly, two virtual indexed images are formed by patterns of the index numbers at their associated positions in the document images. The patterns of index numbers in the two virtual indexed images are then compared (22) to determine whether there is correlation between the patterns of index numbers in at least parts of the two virtual indexed images. The two virtual indexed images are then merged (25), when there is a sufficient correlation, such that the parts that correlate overlap each other to provide a merged virtual indexed image, and then the index numbers in the merged virtual indexed image are replaced (7) by the corresponding group symbol to provide the final composite image.

Abstract: A method of digital image processing for detecting whether a test point within a digital representation of an image lies inside or outside a closed curve defined by an ordered series of curve points within the representation of the image, comprises the steps of: (i) detecting an angle subtended at the test point by pairs of the curve points adjacent to one another in the ordered series; (ii) summing the detected angles for all pairs of the curve points adjacent to one another in the ordered series; and (iii) detecting whether the summed angle is equal to a non-zero integral multiple of 360°, thereby indicating that the test point lies within the closed curve.

Abstract: An image processing apparatus determines whether the longitudinal direction of an image area which is represented by image data inputted in an image processing section and the longitudinal direction of a recording area are correspondent with each other, and then rotates the image by 90 degrees when it is determined that the longitudinal direction of the image area and the longitudinal direction of the recording area are not correspondent with each other.

Abstract: A centroid computation system is disclosed. The system has an imager array, a switching network, computation elements, and a divider circuit. The imager array has columns and rows of pixels. The switching network is adapted to receive pixel signals from the image array. The plurality of computation elements operates to compute inner products for at least x and y centroids. The plurality of computation elements has only passive elements to provide inner products of pixel signals the switching network. The divider circuit is adapted to receive the inner products and compute the x and y centroids.

Abstract: A system and method that computes the degree of translational offset between corresponding blocks extracted from images acquired by two sensors, such as electro-optic, infrared sensors, and radar for example, so that the images can be spatially registered. The present invention uses fast Fourier transform (FFT) correlation to provide for speed, and also uses gradient magnitude and phase (direction) information to provide for reliability and robustness.

Abstract: A method is provided for efficiently finding a pattern in an image using a full curvilinear model having a plurality of sub-models. Generally, the method includes maximizing the percentage of each segment connected to each vertex of each sub-model, and finding the pattern in the image using the model so-constructed. The invention permits the rapid determination of characteristics, such as dimensions, position, and orientation, of rectilinear and other polygonal objects, and is particularly well-adapted for analyzing images of back-lit objects.

Abstract: A system and method for accurately mapping between camera coordinates and geo-coordinates, called geo-spatial registration. The system utilizes the imagery and terrain information contained in the geo-spatial database to precisely align geographically calibrated reference imagery with an input image, e.g., dynamically generated video images, and thus achieve a high accuracy identification of locations within the scene. When a sensor, such as a video camera, images a scene contained in the geo-spatial database, the system recalls a reference image pertaining to the imaged scene. This reference image is aligned very accurately with the sensor's images using a parametric transformation. Thereafter, other information that is associated with the reference image can easily be overlaid upon or otherwise associated with the sensor imagery.

Abstract: A scanning circuit for use with an active pixel sensor array comprises a row-address generator configured to start at a selected row-start address, stop at a selected row-stop address, and increment row addresses by a factor K. A column-address generator is configured to start at a selected column-start address, stop at a selected column stop address, and increment column addresses by a factor K. Circuitry is coupled to the row address generator and the column address generator, for storing the row-start address, the row-stop address, the column-start address, the column-stop address and the factor K. A row decoder is coupled to the row-address generator and a column selector is coupled to the column-address generator. A plurality of row select lines are coupled to the row decoder, each one of the row select lines associated with a different row in the active pixel sensor array.

Abstract: A method of analyzing defect images in a semiconductor manufacturing process wherein descriptors are assigned to images of defects caught during scanning of an inspection wafer. The images, assigned descriptors and linkage data are stored in a relational database. An operator can select an image to analyze and the review station assigns descriptors to the selected image and the database is searched for images having the assigned descriptors.

Abstract: A scanned image is stamped with additional information at a user settable location and color during the scanning process. The information can be the time and date that the scan occurred or information supplied by the user. The location can be at one of the predefined locations or at a location defined by the user. The information is not limited to text but can also contain bitmap image information.

Abstract: An image data interpolation apparatus includes an image data obtaining unit for obtaining image data representing an image as dot-matrix picture elements, a picture element interpolating unit capable of selectively executing one of a plurality of interpolating processes when the image data is interpolated so that the number of constituent picture elements thereof is increased, an interpolating scale factor obtaining unit for obtaining an interpolating scale factor suitable for the image data, and an interpolating process selecting unit for selecting one of the interpolating processes capable of obtaining an optimum result of interpolation according to the interpolating scale factor obtained by the interpolating scale factor obtaining unit and causing the picture element interpolating unit to execute the selected interpolating process.

Abstract: The invention intends to enable unified management of the image data taken with the digital camera and the corresponding print format separately set for the printing device. For this purpose there is disclosed an image processing apparatus comprising an image taking unit for outputting image data by taking the image of an object, a memory medium capable of storing a plurality of print formats to be set in a predetermined print apparatus, together with the image data outputted from said image taking unit, and a communication unit for communicating with an external output apparatus thereby transferring the image data and the print formats stored in the memory medium to the external output apparatus.

Abstract: An image recognition apparatus and method in which an image capture device captures a distance image stream of an object body. A mouth portion extraction mechanism extracts a mouth portion from the distance image stream that has been extracted by the image capture device. An image recognition mechanism recognizes at least one of a lip shape and a lip movement based on a mouth portion distance image stream that has been extracted by the mouth portion extraction mechanism. Instructions for causing a computer to perform the method may be stored in a computer readable memory.

Abstract: Apparatus and method for classifying regions of an image, based on the relative “importance” of the various areas and to adaptively use the importance information to allocate processing resources and input image formation.

Abstract: The invention relates to a method and device for generating a large static image M(n), such as a sprite or a mosaic, from a video sequence including successive video objects. This method comprises a first step for estimating motion parameters related to the current video object V0(n) of the sequence with respect to the previously generated static image M(n−1), a second step for warping this video object on the basis of the estimated motion parameters, and a third step for blending the warped video object WV0(n) thus obtained with the previously generated static image M(n−1). According to the invention, an additional step for computing, for each picture element of the current video object, a weighting coefficient wWF(n)[x,y] correlated to the error between the warped video object and the static image M(n−1) is provided, and the blending formula now takes into account said weighting coefficients.

Abstract: The present invention may be introduced to an architecture such as a personal computer or an amusement equipment for realizing a high-speed graphic processing and provides an optimum arrangement along the flow of information in the case where a frame buffer, a command memory and an image processor are incorporated in one chip in order to improve the drawing performance of an image processing device. Thereby, unnecessary drawing-around of wiring is eliminated and it is possible to reduce the chip area. Further, since the wiring length is shortened, signal delay becomes small, thereby enabling a high-speed operation.

Abstract: The invention relates to a method for generating a large static image M(n), such as a sprite or a mosaic, from a video sequence. This method first comprises, in view of a first accretion step, an estimation of the motion parameters related to the video objects of the sequence, with respect to the previously generated static image. Each video objects is then warped on the basis of said parameters, and the warped video objects are blended with the previously generated static image. According to the invention, said method also comprises (n−1) further accretion steps, but applied this time to the same video sequence considered in the reverse order. Each additional accretion step itself includes a warping sub-step, based on each successive video object considered in said reverse order and on the corresponding motion parameters already estimated, and a blending sub-step, pixel-based or region-based weighting coefficients being then computed in order to be taken into account during the blending steps.

Abstract: A picture processing apparatus having a shape memory with shape data of an object previously stored therein, a processor to set a coordinate value of an object in a three-dimensional virtual space of the basis of the shape date stored in the shape memory, a transformation device to receive the coordinate value set by the processor and transform the coordinate value into a visual field coordinate system based on a specified visual point, and a visual point setting device to move the visual point position from a predetermined standard position for a predetermined base object as defined in the three-dimensional virtual space on the basis of data of the base object as well as changes in the situation caused by the movement of the base object, and for sending a new position after the movement to the transformation device.

Abstract: A video filter unit is described which is implemented as a three-stage filter comprising a vertical filter, a horizontal decimation filter, and a horizontal interpolation filter. The three stages of the filter unit preferably connect serially with the vertical filter comprising the input first stage, the horizontal decimation filter comprising the second stage and the horizontal interpolation filter comprising the third stage which provides the output filtered image from the filter unit. As such, the video data to be filtered is provided to the vertical filter which provides its output to the horizontal decimation filter. After horizontal decimation, which can be disabled if desired (i.e., no horizontal decimation), the video data is then horizontally interpolated. The horizontal interpolation filter stage can also be disabled if desired. The vertical filter can be configured to operate either as a decimation filter or an interpolation filter.

Abstract: In order to measure a distance with high accuracy, a corresponding pixel extraction section reads a projection transformation matrix from a storage section, determines a reference pixel corresponding to a standard pixel, and outputs the pixel value thereof to a correlation value computation section. The correlation value computation section computes the mutual correlation value between a predetermined small area with the standard pixel being the center and a similar small area with the reference pixel being the center, as the sum of the squares of the difference of each pixel within the small area. A distance computation section extracts the point of the smallest value of an addition value input from the correlation value computation section and the points before and after it, creates a second-order curve passing through the three points, and outputs a distance corresponding to the smallest value of the second-order curve, as the distance of the standard pixel, to a distance image memory.