Abstract: An environment recognizing unit extracts the first through N-th states from an input image and calls data corresponding to the first through N-th states from the first through N-th pattern recognizing units to perform a recognizing unit.

Abstract: An image is read by moving a line sensor relative to the image in a subsidiary scanning direction perpendicular to the direction of a pixels array of the line sensor. An image processor receives image signals from the sensor and produces an output image magnified relative to the image in accordance with a magnification ratio. The magnification ratio falls into one of n contiguous magnification ratio ranges between a reference magnification ratio and a minimum magnification ratio.

Abstract: A method for automatically generating a knowledge database in an object classification system having a digital image data source, and a computer, includes the steps of inputting digital image data corresponding to a plurality of training images, and characterizing the digital image data according to pre-defined variables, or descriptors, to thereby provide a plurality of descriptor vectors corresponding to the training images. Predetermined classification codes are inputted for the plurality of training images, to thereby define object class clusters comprising descriptor vector points having the same classification codes in N-dimensional Euclidean space. The descriptor vectors, or points, are reduced using a similarity matrix indicating proximity in N-dimensional Euclidean space, to select those descriptors vectors, called extreme points, which lie on the boundary surface of their respective class cluster. The non-selected points interior to the class cluster are not included in the knowledge database.

Abstract: A learning system learns terms in the context of a set of documents. During an accumulation phase, the learning system accumulates contextual data for a term in the form of a categorization schema. The categorization schema, which is based on a classification hierarchy, classifies the term in categories such that the classifications are based on uses of the terms in the set of documents During a computational phase, the learning system analyzes the categorization schema, and selects, if sufficient contextual data has been accumulated, a single category in the classification system to classify the term. A content processing system, which understands the thematic content of documents, is used in conjunction with the learning system.

Abstract: When a status change of a printer engine occurs, a status change signal is output to an image data output apparatus. In response to input of the status change signal, the image data output apparatus inquires or confirms the printer engine what kind of status change occurs so that processing to compensate for the status change will be subject to image data to be output to the printer engine.

Abstract: A neural network architecture is provided for optical character recognition from an input image in which the target character may be rotated in the image plane. The architecture includes hidden units whose inputs receive image information from portions of the image which are rotationally distributed. That is, the local link between input units and the hidden units is adequate for rotation of the character in the image. Therefore, regardless of the orientation of the image, it is right side up, or approximately so, with respect to one of the hidden units. The hidden units have corresponding inputs with corresponding weight factors, i.e., symmetric weight sharing. Thus, regardless of the orientation of the image, one of the hidden units will produce a high output value indicative of an upright character. Alternatively, a single hidden unit has groups of inputs, each group having a corresponding set of weight factors. The groups are coupled to input units for rotationally distributed portions of the image.

Abstract: A digital full-color copying machine (1) has a full-size mode for copying the entire extent of an original document (210) and a normal mode for copying the original document except for peripheral edge portions. When the normal mode is selected, the original document is conveyed to a position wherein a rear side edge of the original document contacts and is aligned by a fixed scale (205) provided at a side edge portion of an original document glass table (29) and a leading end edge of the original document contacts and is aligned by a movable scale (120) provided at a leading end portion of the original document glass table (29). When the full-size mode is selected, the original document is conveyed and positioned at a modified position with the rear side edge of the original document being aligned by the fixed scale (205) but with the leading end of the original document being spaced a specified distance from the movable scale (120).

Abstract: A projective panchromatic sharpening method and apparatus combines registered high spatial resolution panchromatic imagery and lower spatial resolution multispectral imagery to synthesize higher spatial resolution multispectral imagery. The degree of misregistration between bands and the correlation of intensity values are key factors in generating radiometrically accurate and visually crisp output images. The projective panchromatic sharpening method and apparatus comprises two components. The first component determines the linear radiometric relationship between the panchromatic and multispectral bands, and the second component processes pixels to produce the sharpened product.

Abstract: The architecture of the inventive correlator is, in a preferred embodiment, an array of correlation cells each containing a delay pipe, a math unit and an accumulator. An array of these correlation cells are tiled together to allow simultaneous processing by all cells. The array is disposed so that each cell accumulates an output value in a result surface. There is no electrical limit to the number of correlation cells that may be tiled together. A preferred embodiment uses nine cells tiled together into a 3.times.3 correlation result surface. Other embodiments have been tested in accordance with the present invention having twenty-five cells tiled together into a 5.times.5 correlation result surface. A stream of compare pixel values is presented to the array wherein each compare pixel value is presented to each cell concurrently. A reference memory supplies the appropriate reference pixel values to the cells to enable all calculations for that compare pixel value to be done concurrently.

Abstract: Methods and systems for verifying the volume of a reagent dispensed into an affinity assay vessel are described. In one embodiment, a method is for verifying the volume of a reagent dispensed into an affinity assay vessel described in which a fluid sample is deposited into a vessel that includes a reaction chamber and a volume determination reference point. The reaction chamber further includes a test strip. According to one embodiment, the dispensed fluid is agitated to promote contact between the fluid and a test strip disposed within the reaction chamber. The relative positions of the volume determination reference point and an edge of the meniscus of the dispensed fluid are then determined such that the meniscus of the dispensed fluid is not penetrated. The volume of the dispensed fluid is determined from these relative positions.

Abstract: An imaging subsystem for a printer is configured to support multiple printer personalities. The imaging subsystem has an integrated display list that is accessed and used by all of the printer personalities. The printer implements a display list builder tool that assists each personality in posting its objects to the display list.

Abstract: A method and apparatus for locating geometric shapes or edges thereof in data collection symbols initially samples and stores an image of light reflected from the symbol. Thereafter, two routines are performed. A first routine performs low level vision processing by identifying linked points along edges, lines, curves or within shapes. A rapid pixel linking subroutine identifies edge pixels in symbol images lacking distortion. If the edge or shape suffers from distortions, then one or more distortion compensating subroutines locate sequential linked pixels despite such distortions. The resulting coordinates of linked points, which represent lines, curves and other geometric shapes, are then employed by a second routine which identifies patterns within the identified lines/curves. Based on these identified patterns, types of symbols from various symbologies can be identified and located within the stored image.

Abstract: Quantized DCT coefficients Rvu are inputted to a pre-processing unit, in which pre-processed DCT coefficients are obtained by multiplying a quantization/multiplying-term table and the quantized DCT coefficients. The quantization/multiplying-term table are generated by multiplying a multiplying-term corresponding to a part of a two dimensional IDCT and a quantization coefficient. The pre-processed DCT coefficients are inputted into first through fourth stages forming a post-processing unit. The pre-processed DCT coefficients are subjected to a process corresponding to a multiplication of a DCT coefficient in the first through fourth stages. By integrating output data of the each of the first through fourth stages, the remaining part of the two dimensional IDCT is performed, so that 64 pixel values forming an 8.times.8 matrix are obtained.

Abstract: A high-yield printhead where density unevenness is surely corrected taking into consideration various factors related to manufacturing processes of the printhead, a printer utilizing the printhead, and an apparatus and method for correcting print density unevenness by the printhead, are provided. According to the method, a plurality of correction tables generated based on the data reflecting the various factors related to manufacturing processes of the printhead are prepared in advance. A test print pattern is printed by using a full-line printhead having a memory for storing correction data, and a tendency of density distribution of the printed pattern image is analyzed. On the basis of the tendency of the density distribution obtained as a result of the analysis, the most appropriate correction table is selected from the plurality of stored correction tables.

Abstract: An apparatus and method for correctly determining the position of a vehicle in a traffic lane by obtaining correct information about the position of the traffic lane without being affected by variations in the road surface, weather, time of day, or such imaging conditions as fixed or moving lighting, are provided. An edge signal of a high spatial frequency component and a luminance signal of a low spatial frequency component of a digital image signal representing the view of the local area to the front of a vehicle are extracted. A road contour signal is then extracted from the edge signal, and a road region signal is extracted from the luminance signal. The position of the lane Sre is then detected with high precision by evaluating the lane contour Sre based on the road region signal Srr and lane contour data Sre.

Abstract: A journal device including a printing unit for printing journal data on journal paper, as well as printing a retrieval mark indicative of information specifying the journal data, an operation unit for specifying jour data to be retrieved and designating information represented by a retrieval mark, a reading unit for reading a retrieval mark printed on journal paper to extract information represented by the retrieval mark, a printer control unit for receiving input of information extracted by the reading unit and collating the information with information designated by the operation unit to retrieve a retrieval mark containing target information, and first and second take-up means for running the journal paper with printing processing and retrieval processing of journal data and a retrieval mark.

Abstract: An image forming system in which an energy saving mode can be canceled by an external device when the external device requests a printing operation to an image forming apparatus which is set in the energy saving mode. The external device outputs image data to be printed. Power consumption of the image forming apparatus is reduced when the image forming apparatus is waiting to receive the image data. A communication line connects the external device to the image forming apparatus. An energy saving control unit, provided in the image forming apparatus, recognizes a print request sent from the external device via the communication line when the image forming apparatus is set in the energy saving mode so that the energy saving mode is canceled when the print request is recognized. The print request can be either a strobe signal or a wakeup command. A ready command may be sent to the external device when the image forming apparatus is set in a stable state.

Abstract: A method and apparatus for changing a video image having a number of luminance areas to a drawing-style image. An edge boundary between two luminance areas of the video image may be detected and a key signal may be generated therefrom. The key signal may be nonlinear transformed to generate a transformed key signal. Two color signals may be mixed in accordance with the transformed key signal so that the boundary of the video image may be displayable as a line in the drawing-style image.

Abstract: A reference image R is selected and a region of interest (ROI) is interactively selected encompassing a desired structure from a sequence of images of a moving structure. This ROI is cross-correlated with other real-time images by multiplication in the Fourier frequency domain, to determine if the desired structure is present in the image. If the structure is present, this image may be averaged with other images in which the structure is present to produce higher resolution adaptively averaged images. This invention is particularly useful in imaging coronary vessels. In an alternative embodiment, the offset of the desired structure may be calculated in a series of images. The images may then be sorted by this offset, and played back in that order to provide a "movie-like" display of the desired structure moving with the periodic motion.

Abstract: Provided are an image processing method employing pattern matching, whereby the number of calculations for a normalized correlation factor can be reduced and processing speed can be increased in a pattern matching process, and an image processing system therefor. In the pattern matching processing when an insensitive region is set in a template image, values (the sum and the squared sum) obtained during a previous operation for a prior search target sub-image are employed to perform calculations for a current search target sub-image, relative to coordinate sequence code that indicates the start point and the end point of a sequence of pixels having values of "1.