Patents Examined by Steven P. Klocinski
-
Patent number: 5410620Abstract: A system and method for locating and reading digital data in data regions within a data field disposed on a surface of an object to be identified include the capability of compensating for optical or physical distortions of the data field as viewed by an optical reader. The data field is defined by X-axis and Y-axis intersecting basic lines disposed at a predetermined angle with respect to each other and a corner mark disposed on the opposite side of the data field from those basic lines. A plurality of positions marks for marking predetermined distances between a plurality of imaginary X and Y axis internal lines are also provided. The positions of the imaginary X-axis internal lines within the data field are determinable from their spacings and angles with respect to the Y-axis basic line. The positions of the imaginary Y-axis internal lines are determinable from their spacings and their angles with respect to the X-axis basic line.Type: GrantFiled: February 9, 1993Date of Patent: April 25, 1995Assignee: Teiryo Sangyo Co., Ltd.Inventor: Hirokazu Yoshida
-
Patent number: 5375175Abstract: A method of processing images obtained with a microscope along a line on an object, in which the object, having trenches or lines, is moved in the z direction to form a cloud plot; signals in the z direction are scanned to form a linescan vector; the linescan vectors are clustered and classified; a centroid is defined; a similarity curve is created from the linescan vectors and the centroids; and the distance between adjacent points on the similarity curve are measured to provide a measure of line or trench width.Type: GrantFiled: March 6, 1992Date of Patent: December 20, 1994Assignee: The Board of Trustees of the Leland Stanford Junior UniversityInventors: Gordon S. Kino, Stanley S. Chim
-
Patent number: 5353385Abstract: An inference method and an inference apparatus for use with a knowledge base system and knowledge base system supporting method and apparatus using the inference method and apparatus wherein there are employed rules each being comprised of a set of (1) a condition description part including a condition stipulating a plurality of states of a frame representing an object and constituting an object world of at least one pair of a slot and a value thereof and (2) an operation description part stipulating an operation to be executed when the condition is satisfied. For an inference processing, a rule for which a condition of its condition description part is satisfied is executed according to an operation described in the operation description part. A condition judging sequence is specified for satisfaction of a condition for each frame of the condition description part of the rule.Type: GrantFiled: March 29, 1991Date of Patent: October 4, 1994Assignee: Hitachi, Ltd.Inventors: Shunichi Tano, Shoichi Masui, Toshihiko Nakano
-
Patent number: 5347589Abstract: A system and method of displaying handwriting parameters in which a dynamic parameter, such as the tangential speed, of a stylus moving across a surface is determined, a trace of the stylus across the surface is recorded on a record member, and the dynamic parameter is represented on the record member to provide a means of visually observing both the handwriting itself and one or more dynamic parameters of the handwriting process.Type: GrantFiled: June 22, 1993Date of Patent: September 13, 1994Assignee: Meeks Associates, Inc.Inventors: M. Littleton Meeks, Theodore T. Kuklinski
-
Patent number: 5341441Abstract: A coding apparatus divides digital image information into pixel blocks each having a size of m.times.n pixels, and subjects the image information to vector quantization in block units. The pixel blocks are orthogonally transformed and the characteristics and sequency components of the pixel blocks are detected. Each pixel block is divided into a plurality of sub-blocks in conformity with the detected sequency components. Respective ones of the plurality of divided and outputted sub-blocks are scalar-quantized into sub-vectors of a predetermined number of bits in conformity with the characteristics of the pixel blocks. Respective ones of the scalar-quantized values of the quantized sub-blocks are vector-quantized in conformity with the characteristics of the pixel blocks, these vector-quantized reproduction vector codes are combined and the result is subjected to further vector quantization.Type: GrantFiled: January 11, 1993Date of Patent: August 23, 1994Assignee: Canon Kabushiki KaishaInventors: Mitsuru Maeda, Tadashi Yoshida
-
Patent number: 5341436Abstract: A real-time radioscopy system produces an X-ray image of a sample of reinforced composite material or a manufactured part that has been molded from the reinforced composite material. By examining the statistics of the distribution of gray levels within the image, it is possible to measure the local and average reinforcing material content (loading) as well as how well the reinforcing material is distributed (the reinforcing material dispersion). The mean gray level is used to determine the local loading of the reinforcing material, which is measured as a function of position in the sample or part using this technique. In addition, an average value of the loading may be obtained. The standard deviation of the gray level image correlates with the quality of dispersion of the reinforcing material.Type: GrantFiled: November 6, 1992Date of Patent: August 23, 1994Assignee: E. I. du Pont de Nemours and CompanyInventor: David M. Scott
-
Patent number: 5341435Abstract: Apparatus for detecting and identifying, by video imagery, an object such as a helicopter, having a characteristic temporal signature containing phase and magnitude information. The object is acquired and the video signals are stored and then temporally filtered by a FFT on a pixel to pixel basis. The magnitude and phase of pixel at a predetermined frequency is determined and compared with periodic frequencies generated by known objects, such as helicopter rotors, to determine if the frequency generated by the object matches any of the known frequencies. Further processing determines the number of blades and directions of rotation of the blades which removes ambiguities from frequency only processing.Type: GrantFiled: March 17, 1992Date of Patent: August 23, 1994Assignee: Corbett Technology Company, Inc.Inventors: Kenneth A. Corbett, David R. Anderson
-
Patent number: 5329594Abstract: A recognizing and judging apparatus has a network organized in a multilayered hierarchical manner and a plurality of branched tree structures corresponding to the number of inputted data. The branched tree structures are organized by a plurality of recognition units, each of which includes a signal input section and a quantizer for performing a quantization according to a signal inputted from the signal input section. Each of the recognition units further includes a path input section having at least one path input terminal, a path output section having at least one path output terminal, and a path selecting section operatively coupled with both the path input section and the path output section for performing a selection of paths according to an output of the quantizer.Type: GrantFiled: March 3, 1992Date of Patent: July 12, 1994Assignee: Matsushita Electric Industrial Co., Ltd.Inventors: Susumu Maruno, Shigeo Sakaue, Toshiyuki Kohda, Yoshihiro Kojima
-
Patent number: 5321771Abstract: A device for automatic image segmentation according to the invention comprises a data processor associated with a network of automata organized in three levels; the inputs of each of the automata are weighted by adjustable coefficients; the number of automata of the first level is equal to the number of characteristic values computed from observation windows taken firstly in a set of examples of image zones having different textures. Learning by the network permits adjustment of the weighting coefficients of the automata of the network until all the examples of the same texture lead to the same configuration.Type: GrantFiled: November 25, 1992Date of Patent: June 14, 1994Assignee: Thomson-CSFInventors: Gilles Burel, Jean-Yves Catros
-
Patent number: 5319721Abstract: A method for use in a handwriting recognition system, and apparatus for accomplishing the method, that generates a User set of prototype symbols. The method includes the steps of (a) inputting one or more strokes for representing a predetermined symbol; and (b) comparing characteristics of the inputted strokes to stroke characteristics associated with one or more predetermined Starter prototype symbols. If the stroke characteristics match to within a predetermined threshold, the method further includes a step of (c) averaging the characteristics of the inputted stroke or strokes with the characteristics of a corresponding one or ones of the strokes of the matching one of the Starter prototype symbols to form a User prototype symbol. Further steps include (d) storing the User prototype symbol for subsequent use; and (e) deleting one or more Starter prototype symbols of the same label as the input symbol.Type: GrantFiled: April 14, 1992Date of Patent: June 7, 1994Assignee: International Business Machines CorporationInventors: Thomas E. Chefalas, Charles C. Tappert
-
Patent number: 5317428Abstract: There is provided an image encoding method in a facsimile apparatus or an image filing apparatus as an image communication apparatus. In this method, a color image signal which is expressed by a plurality of color component signals to be encoded is input, the input color image signal is converted into a bit stream signal, and the bit stream signal is encoded by the prediction encoding. A parameter for the prediction encoding is changed in accordance with the color image signal to be encoded. The encoding operation is executed adaptively to the color image signal to be encoded. By bit stream converting the binary color signal, the efficient encoding using the color correlation can be executed and an increase in data amount is prevented. By encoding the bit stream signal by using a dynamic arithmetic code, a binary color image can be efficiently encoded.Type: GrantFiled: November 25, 1992Date of Patent: May 31, 1994Assignee: Canon Kabushiki KaishaInventors: Hidefumi Osawa, Yasuhiko Yasuda, Shigeo Kato
-
Patent number: 5317653Abstract: A method and arrangement for the application of under compensated error diffusion to a pixel quantizing method in the conversion of image data from a number of input levels that is relatively large with respect to a number of desired output levels.Type: GrantFiled: May 20, 1993Date of Patent: May 31, 1994Assignee: Xerox CorporationInventors: Reiner Eschbach, Keith T. Knox, David Birnbaum
-
Patent number: 5313532Abstract: A pattern (e.g., the normal or abnormal characteristics of a biological cell) within an image is recognized based on visual characteristics of the pattern, the image being represented by signals whose values correspond to the visual characteristics, using a location channel which determines the location of the pattern within the image based on the signal values, and a classification channel which categorizes the pattern based on the signal values, the location channel and the classification channel operating in parallel and cooperatively to recognize the pattern.Type: GrantFiled: October 28, 1991Date of Patent: May 17, 1994Assignee: Massachusetts Institute of TechnologyInventors: Robert L. Harvey, Paul N. DiCaprio, Karl G. Heinemann
-
Patent number: 5309527Abstract: An image data processing apparatus selects and extracts the elements of a desired 8.times.8 matrix from four matrices in real space each having 8 rows and 8 columns and effects an inverse discrete cosine transform on the four matrices. The elements of the four matrices each of the 8 rows and 8 columns are arranged into four vectors each of 64 elements. The elements of the vectors are supplied serially to four 64-output serial-to-parallel converters, which output the elements in parallel. Data selectors then select the 64 elements of one of the vectors. Half of the selected elements are processed by a 32-element inner product processing circuit, which produces a first inner product output signal. The remaining selected elements are processed by another 32-element inner product processing circuit, which produces a second inner product output signal. The first and second inner product output signals are added into a final output signal by an adder.Type: GrantFiled: January 15, 1992Date of Patent: May 3, 1994Assignee: Sony CorporationInventor: Mitsuharu Ohki
-
Patent number: 5303311Abstract: A character recognition system identifies characters including hand written characters with a high degree of accuracy by use of spiral view codes for pels in the scanned character image. The spiral view codes are developed by comparing stroke length or distance to a remote stroke from a first radial view from a character pel to stroke length or distance to a remote stroke from a counterclockwise adjacent view for the same character pel. These spiral view codes are collected into a spiral view pattern for each character pel. The spiral view patterns for a character are accumulated to form a character vector. The character vector is analyzed by a linear decision network or a neural network.Type: GrantFiled: April 9, 1992Date of Patent: April 12, 1994Assignee: International Business Machines CorporationInventors: Alec K. Epting, Terry A. Will
-
Patent number: 5299269Abstract: Character segmentation apparatus for an optical character recognition system for segmenting individual character images in an image of a document having many characters prior to performing character identification, including a movable kernel for capturing a sub-image framed within a window having an area corresponding to an area occupied by an individual character, the window being movable in the document image in pixel-by-pixel steps to capture a sub-image for each step of the window, an associative memory for responding to the captured sub-image by producing a corresponding one of a set of images of known characters with which the associative memory has been trained, and a sensor responsive to the behavior of the associative memory for determining whether the sub-image is the image of an individual character or a non-character.Type: GrantFiled: December 20, 1991Date of Patent: March 29, 1994Assignee: Eastman Kodak CompanyInventors: Roger S. Gaborski, Lori L. Barski
-
Patent number: 5297217Abstract: A tile-oriented technique and associated apparatus for manipulating a continuous tone (contone) image through image rotation, anamorphic scaling and digital halftone screening for use in illustratively implementing a page description language. Specifically, an incoming contone image is first partitioned into aligned non-abutting tiles (e.g. 215.sub.1, 215.sub.2, . . . , 215.sub.9). Overlapping blocks (e.g. 217.sub.1, 217.sub.2, . . . , 217.sub.9) are then defined which will hold output data for corresponding tiles. Two dimensional sampling increments, in fast and slow scan directions, are defined to relate movement between successive pixels in an output block to movement between corresponding pixels in the contone image. Similar, though independent, sampling increments, also in the fast and slow scan directions and based in part upon screen angle and screen ruling, are defined for movement between successive pixels in a halftone reference cell.Type: GrantFiled: August 21, 1992Date of Patent: March 22, 1994Assignee: Eastman Kodak CompanyInventors: John F. Hamilton, Jr., Anthony J. Leone, III
-
Patent number: 5293426Abstract: A system for calibrating engraving heads used for engraving gravure printing cylinders determines a cell volume for cells formed in a test cut in a printing cylinder. The system of the present invention includes a procedure of cutting two or more test cuts in each printing cylinder. One of the test cuts is at the light end of the cylinder and the second is at the dark end. The morphological characteristics of each individual cell in each of the test cuts is measured, and the average cell dimensions and volume per unit area are computed. These average values are compared with desired average values, and each engraving head is adjusted in accordance with this comparison to cut the desired values within an acceptable tolerance band. The desired average values can be adjusted to take into account new inks, papers, batch variations in inks and papers, and diamond wear in the engraving head.Type: GrantFiled: May 25, 1990Date of Patent: March 8, 1994Assignee: R. R. Donnelley & Sons CompanyInventors: Gerald Wouch, Gary Procknow
-
Patent number: 5287416Abstract: A pipelined image processor generates an image of the information contained on first and second portions of a document. The pipelined image processor includes a first pipe for processing information contained on the first portion of the document, and second pipe for processing information contained on the second portion of the document. The pipes receive the output from two camera assemblies which are used for generating an electrical signal in response to information contained on the document, an image digitizer for generating digitized information from the electrical signal by the means for generating an electrical signal. In addition, both pipes also include a resequencer for generating resequenced information from the digitized information, as well as an image processor for generating processed information from the resequenced information.Type: GrantFiled: August 17, 1992Date of Patent: February 15, 1994Assignee: Unisys CorporationInventors: Joseph M. Capo, Robert D'Aoust, Debora Y. Grosse, Robert Klein, Ravi K. Nigam, George E. Reasoner, Jr., David C. Williams
-
Patent number: 5283670Abstract: A hardware implementation of a digitized image corrector is disclosed that converts a colorimetric representation of an original image into a new representation based upon the colors of the original and target images, as well as user supplied artistic parameters. The digitized image corrector receives digitized Red, Green and Blue input signals that comprise a colorimetric representation of an original film scene, and generates digitized Red, Green, and Blue output signals according to the specifications of SMPTE 240 M. The digitized image corrector is comprised of four identical hardware correction modules, which are coupled to receive correction parameters from an external source. Each module has a bypass switch for entering a bypass mode, which is used for reconfiguration of the module's correction parameters without affecting the output image.Type: GrantFiled: March 19, 1992Date of Patent: February 1, 1994Assignee: Sony Electronics Inc.Inventors: Patrice Capitant, Gary M. Bennett, Dave Collier, O. F. Morgan, David Rossmere