Abstract: This invention for reading an image of a document employs a optical projection magnification lens for projecting the image of a document; a movable image reading device for transforming the projected image into electrical signals and for providing a focussing adjustment; an electrical magnification process for varying electrically the size of the image projected on the image reading device; and a controller for controlling the optical projection lens, the electrical magnification process, and the movable reading device.

Abstract: A method and apparatus for identifying and correcting for document skew. Lines of a bitmap are scanned and a variance in the number of ON pixels as a function of skew angle is calculated. Skew of the original document occurs when the variance is a maximum. Once the skew has been identified, the document is deskewed accordingly.

Abstract: In a method of extracting feature quantities of a character, a pair of region dividing lines which intersect a character image are obtained by using generated projections of direction codes. Then, a reference position for extracting feature quantities of the character is decided by finding positions at which the region dividing lines intersect the character image. Thereafter, the feature quantities of the character having the reference position are extracted by subjecting the codes of the divided segments to a predetermined operation for obtaining information regarding a shape of each of the divided segments.

Abstract: An image processing apparatus processes diagnostic image data bearing thereon an image through which a disease is to be diagnosed so that a visible image having a quality optimal to diagnose the disease can be obtained. The image processing apparatus includes an image processing condition storage section and an image processing section. Names of various diseases and image processing conditions for the respective diseases are stored in the image processing condition storage section. The diagnostic image data is input into the image processing section. The name of a disease which is to be diagnosed is input into the image processing condition storage section, and the image processing condition corresponding to the disease is input into the image processing section from the image processing condition storage section. The image processing section carries out image processing on the image data according to the image processing condition input thereinto and generates a processed image data.

Abstract: A method and apparatus for detecting an object of interest against a cluttered background scene. In a first preferred embodiment the sensor tracking the scene is movable on a platform such that each frame of the video representation of the scene is aligned, i.e., appears at the same place in sensor coordinates. A current video frame of the scene is stored in a first frame storage device (14) and a previous video frame of the scene is stored in a second frame storage device (20). The frames are then subtracted by means of an invertor (24)and a frame adder (28) to remove most of the background clutter. The subtracted image is put through a first leakage reducing filter, preferably a minimum difference processor filter (32). The current video frame in the first frame storage device (14) is put through a second leakage-reducing filter, preferably minimum difference processor filter (36).

Abstract: In order to easily identify a pattern of time-series state changes based on measured information so as to facilitate representation of edge portions of an image, features extracted in a form of expansion coefficients of polynomials from the measured information are translated into abstract expressions so as to detect from the measured information significant control information which has not been used in the conventional technology, and features extracted in a form of expansion coefficients from brightness changes in the vicinity of each pixel constituting image data are translated into abstract expression.

Abstract: A method is described for producing a mesh of finite elements that are entirely within a body to be analyzed, the body exhibiting edges and surfaces. The method comprises the steps of: producing an initial mesh of elements for the body, each element having a plurality of vertices and edges; finding any body edge segment which is not coincident with a finite element edge and adding a vertex on that segment, the added vertex positioned to minimize the number new vertex points needed on the body edge segment. Additional finite elements are then created by connecting the new vertex to adjacent close vertices. A finite element is now identified which has both an edge coincident with an edge segment of the body and another edge segment that passes through a face of the body.

Abstract: In an image processor for detecting incomplete articles the image of a complete article is produced by a television camera so as to record the image, and the operator designates an area of the complete article that is considered to be essential in judging whether or not the subject of the inspection is complete while observing the reproduced image. Following this, the image of an inspection article is produced by another television camera. The video signals are binarized, and the number of the picture elements of the inspection article within the designated area is then counted. The inspection article is judged as being incomplete when this counted value fails to conform to the reference value obtained by statistically processing the number of the picture elements of the complete article.

Abstract: Method and apparatus for construction and use in real time of a sequence of pixel-to-pixel mappings that define a video image transformation of a sequence of video images in digital animation video image processing and display. A sequence of compressed mappings that approximate the required sequence of pixel-to-pixel mappings is constructred off-line, and this sequence of compressed mappings is stored for subsequent use and is designated by a selected indicium. When that sequence of pixel-to-pixel mappings is to be applied to a chosen set of video image fields, the sequence of compressed pixel mappings is called up by use of the indicium, the compressed mappings are decompressed, and the sequence of decompressed mappings is applied to the chosen set of video image fields in real time.

Abstract: A tabular document reader device for recognizing characters on a tubular document which is composed of a plurality of items and which has different categories according to each of the items includes a ruled line extracting portion (14) for detecting and extracting ruled lines from the read tabular document. An item specifying input portion (15) inputs proper reading conditions for items delimited by the extracted ruled lines. A character recognizing portion (17) limits what should be recognized in the respective items according to the input reading conditions for the items.

Abstract: An image motion vector detecting apparatus includes a low-pass filter having a non-zero impulse response for at least one of a delay of a predetermined interval LX in the horizontal direction and a delay of a predetermined interval LY in the vertical direction of input image signals, a memory for storing image signals corresponding to a plurality of representative points arranged at a predetermined horizontal direction interval LX and at a predetermined vertical direction interval LY within a motion vector detection area for input image signals of a given frame, a subtracter for obtaining differences between the stored image signals corresponding to each of the plurality of representative points and input image signals of frames subsequent to the given frame which input image signals correspond to points neighboring each of the plurality of representative point within the motion vector detection area, an adder which adds up the differences thus obtained, a unit for obtaining correlation values for shafts with

Abstract: Three image frames containing an object of interest and background clutter are taken at successive time intervals and stored in memory. The background of images A, B and C are registered preferably using an area correlator 12. A median filter 16 is used to select a median value from the registered image frames. Then, subtractor 18 serves to subtract the median pixel values from one of the image frames. This difference output is then thresholded to provide a binary signal whose pixel values exceeding the threshold levels are generally associated with the position of the moving object.

Abstract: A method of compressing a text file in digital form is disclosed. A full text file having characters formed into phrases is provided by an author. The characters are digitally represented by bytes. A first pass compression is sequentially followed by a second pass compression of the text which has previously been compressed. A third or fourth level compression is serially performed on the previously compressed text. For example, in a first pass, the text is run-length compressed. In a second pass, the compressed text is further compressed with key phrase compression. In a third pass, the compressed text is further compressed with Huffman compression. The compressed text is stored in a text file having a Huffman decode tree, a key phrase table, and a topic index. The data is decompressed in a single pass and provided one line at a time as an output. Sequential compressing of the text minimizes the storage space required for the file. Decompressing of the text is performed in a single pass.

Abstract: An image reader for reading an image on a document having apparatus for projecting an image of the document optically to permit optical magnification. An image reading device transforms the projected optical image into electrical signals which can be transformed into bi-level signals with the picture element density of the bi-level signals varied. Apparatus is provided for designating picture element density and for controlling the optical magnification in accordance with the designated picture element density.

Abstract: A high-speed image recognition system operates in response to a binary digitized picture image signal. The system comprises a first memory for storing a bi-level reference image pattern therein, a selector coupled to the first memory for manually designating a plurality of selected points of the bi-level reference image pattern, a detector coupled to the selector for detecting signal levels at each of the points selected by the selector, a second memory coupled to the detector for storing therein detected signal levels obtained from the detector, and a comparator coupled to the second memory for comparing the detected signal levels at the selected points of the bi-level reference image pattern with signal levels at the same points of a candidate image pattern, whereby an object corresponding to the candidate image pattern is recognized.

Abstract: An image coding method extracts a contour of a bi-level image, segments the contour into a plurality of segments by fitting a predetermined generation curve on each of the segments, where the predetermined generation curve is described by control points which include end control points and direction control points, the end control points indicate ends of each segment and the direction control points indicate directions of each segment at the two ends of each segment, and codes the control points.

Abstract: An image reader which has a criterion member arranged at the upstream side of a platen with respect to the subscan direction and controls a scanner so as to scan the criterion member and subsequent thereto the document. The criterion member is used to determine a reference edge from which the image reading of the document should be started.

Abstract: A recursive spatial filter interchanges the value of a control pixel with that of the value of a predetermined one of the surrounding pixels in a pixel mask when a specific image pattern occurs in the digital image. The use of such a filter eliminates certain highly visible grain patterns from the halftoned digital image while preserving the average gray level.

Abstract: The apparatus and method of the present invention utilizes three scaling functions for bi-tonal digitized image data such as documents. The digitized document resolution (i.e. from a digitizing scanner) may be different from the resolution of an image output device (i.e. laser printer, CRT display, fax machine, etc.). The invention takes in the scanned image data and scales the data to compensate for the resolution mismatch of the output device. Although the invention is intended for document archive applications (such as scanning documents on microfilm), the scaling can be performed on any bi-tonal image.

Abstract: An apparatus and method for removing background noise and high frequency noise from an image by comparing each pixel in the image with neighboring pixels defining a variably shaped and sized kernel. The size and shape of the kernel are optimized for the particular characteristics of the data to be analyzed.