Based On A Local Average, Mean, Or Median Patents (Class 382/272)
  • Patent number: 6332045
    Abstract: An image processing device includes an image data correction unit for correcting multi-level image data of a target pixel; an image data binarizer for binarizing the corrected multi-level image data of the target pixel; a binarization error calculator which calculates a first error between the corrected multi-level image data and the image data of pixels within a first region on a periphery of the target pixel that is binarized by the image data binarizer; and a device for executing a predetermined filtering process on the first error to calculate a second error, and for weighting and averaging the second error for pixels within the first region; wherein the image data correction unit corrects the multi-level image data by using the weighted and averaged second error.
    Type: Grant
    Filed: November 25, 1998
    Date of Patent: December 18, 2001
    Assignee: Minolta Co., Ltd.
    Inventors: Kenichi Sawada, Atsushi Ishikawa
  • Patent number: 6320593
    Abstract: A method for interpolating a first color value associated with a first color and a second color value associated with a second color for use in generating a pixel that represents a portion of a digital image, based on a third color value that is associated with a third color. A first matrix is created and stored, comprising first coefficient values that are associated with a other values of the first color for pixels that surround the current pixel of interest. A second matrix is stored that holds second coefficient values that are associated with a second color value. Each of the first coefficient values is bitwise shifted by a pre-determined power of 2. The first color value is created and stored by applying the first coefficient values to the other values of the first color using a bitwise shift operation. The first color value is bitwise shifted by a complement of the pre-determined power of 2.
    Type: Grant
    Filed: April 20, 1999
    Date of Patent: November 20, 2001
    Assignee: Agilent Technologies, Inc.
    Inventors: Arthur Sobel, Todd S. Sachs
  • Patent number: 6314136
    Abstract: A system and method used to perform lossless wavelet-based image transformations. In one embodiment, the method used for these transformations and for bit precision reduction. First, at least a luminance value is produced for each row of pixels of a selected pixel block. Next, a determination is made as to whether a luminance value associated with a particular row of pixels of the selected pixel block is positive. Thereafter, a reduced luminance value is produced when the luminance value is determined to be positive, the reduced luminance value is represented by a lesser number of bits than the luminance value. Finally, the second and third steps are continued for each luminance value associated with each row of the selected pixel block. The values are used in an iterative fashion to calculate the low and high spatial frequency and create graphics with minimal use of bandwidth.
    Type: Grant
    Filed: August 1, 1997
    Date of Patent: November 6, 2001
    Assignee: Creative Technology Ltd.
    Inventor: Emmett Kilgariff
  • Patent number: 6296387
    Abstract: The invention relates to a method for correcting image defects from a matrix-type X or &ggr;-ray detector, consisting in producing a confidence map on the basis of continuous confidence ratings, between 0 and 1, and representing the level of confidence assigned to each detector pixel. It then consists in using this confidence map to correct the defects of the matrix detector.
    Type: Grant
    Filed: November 12, 1999
    Date of Patent: October 2, 2001
    Assignee: Commissariat a l'Energie Atomique
    Inventor: RĂ©gis Guillemaud
  • Patent number: 6289112
    Abstract: A reliable estimate of image pixel (fingerprint ridge) orientations, and block orientations for a given block is determined by finding an optimal block size in an area of an image, e.g., a fingerprint image. An initial block size is chosen. Then a block direction is determined, e.g., by analyzing intensity gradients in two directions, preferably two orthogonal directions, at a plurality (preferably all) of the pixels locations in the block. Block directions of blocks in a given area of the images (fingerprint) are compared. If the compared directions are within a tolerance of one another, the determined direction of the block is considered correct. However, if the compared directions are not within a tolerance of one another, the block size is changed and the process is repeated.
    Type: Grant
    Filed: February 25, 1998
    Date of Patent: September 11, 2001
    Assignee: International Business Machines Corporation
    Inventors: Anil K. Jain, Lin Hong, Rudolf Maarten Bolle, Sharathchandra Umapathirao Pankanti
  • Patent number: 6178268
    Abstract: The present invention is directed to a method of and an apparatus for applying predetermined processing to an original image pixel by pixel. A main signal (S) regarding an objective pixel which is a pixel which is to be processed is supplied to an average density value extracting portion (10), a multiplier (51), and a filter computation portion (30). The filter computation portion (30) executes computation based on an image filter which has a larger size than the size of halftone dots, to thereby generates a filtered signal (S′). The average density value extracting portion (10) extracts an average density value (D) in an area which is larger than the size of the halftone dots, and supplies the average density value (D) to a table reference portion (20). The table reference portion (20) identifies a mixing rate (M) for mixing in the main signal (S) and a mixing rate (1−M) for mixing in the filtered signal (S′), in accordance with the average density value (D).
    Type: Grant
    Filed: March 20, 1998
    Date of Patent: January 23, 2001
    Assignee: Dainippon Screen Mfg. Co., Ltd.
    Inventors: Itaru Furukawa, Fujio Akioka
  • Patent number: 6154573
    Abstract: An image processing method and device computes the image quality as an evaluation value, determine the image quality based on this evaluation value, and employ a restoration process in accordance with image quality when this image quality is poor.
    Type: Grant
    Filed: March 24, 1999
    Date of Patent: November 28, 2000
    Assignee: Seiko Epson Corporation
    Inventors: Yasuhiko Murayama, Ayako Kobayashi, Naoki Kuwata
  • Patent number: 6137917
    Abstract: An apparatus and method of reducing impulse noise using a median filter involve selecting a pixel of median.sub.-- value from a plurality of pixels, comparing a reference range, determined by adding or subtracting an offset value to or from the selected median.sub.-- value, with a mid.sub.-- pixel among the plurality of pixels, to determine whether the input image signal has impulse noise and generate a noise coefficient depending on the presence of impulse noise, calculating a correlation between the luminance component of a pixel and the color component thereof depending on the noise coefficient, and cross-fading the pixel of median.sub.-- value and the mid.sub.-- pixel depending on the correlation.
    Type: Grant
    Filed: August 13, 1998
    Date of Patent: October 24, 2000
    Assignee: Samsung Electronics Co., Ltd.
    Inventor: Se-woong Park
  • Patent number: 6134355
    Abstract: There is provided an image processing apparatus such as facsimile apparatus or digital copying machine for digitizing image data into two values or multi-values. The apparatus comprises: an input device to input data of a target pixel to be digitized; a calculating circuit to obtain an average density value of a predetermined region; a digitizing circuit such as a binarizing circuit for digitizing or binarizing the target pixel data on the basis of the average density value obtained by the calculating circuit; and a correction circuit to correct a difference which occurs upon digitization by the digitizing circuit. The calculating circuit calculates the average density value m.sub.1 of the pre-determined region when the target pixel data was binarized to 1 and the average density value m.sub.2 of the predetermined region when the target pixel data was binarized to 0 by using a predetermined weighting mask. The digitizing circuit binarizes the target pixel data by using (m.sub.1 +m.sub.
    Type: Grant
    Filed: June 7, 1995
    Date of Patent: October 17, 2000
    Assignee: Canon Kabushiki Kaisha
    Inventors: Yasuhiro Yamada, Hiroshi Tanioka
  • Patent number: 6130723
    Abstract: The present invention provides a method and system for reducing flicker within an interlaced image. The method and system comprises identifying an area of the interlaced image where flicker needs to be reduced and adaptively adjusting a pattern of pixels derived from a non-interlaced spatial relationship of the interlaced image within the area based upon characteristics of the image. A flicker filter is provided which utilizes an adaptive technique whereby pixel-blending characteristics are constantly changed within the image depending on particular image attributes. It is unique in that high vertical resolution is maintained for detailed image content such as text and most graphics, while flicker is effectively reduced on image content that is flicker prone. The filter is based on psycho-visual studies and simulations performed by the company as well as numerous prior flicker filter implementations.
    Type: Grant
    Filed: January 15, 1998
    Date of Patent: October 10, 2000
    Assignee: Innovision Corporation
    Inventor: David Medin
  • Patent number: 6122407
    Abstract: A method and apparatus for creating threshold arrays having a minimized gray scale variance without geometric artifacts. The invention comprises the steps of processing each candidate pixel in the threshold array using a variance minimization technique and applying a sparse image calculation on the same pixel. The preferred embodiment of the invention comprises the application of a variance minimization technique on a threshold array. The threshold array is analyzed on a pixel-by-pixel basis. Each candidate pixel that is to be turned on is examined in relation to the previous pixels that already exist. The candidate pixel is examined to determine its effect on the variance of the smoothed gray level determined by the convolution of the pixel pattern with a smoothing kernel. The candidate pixel is also examined in relation to the distribution of the angles it forms with the previously selected pixels. The preferred embodiment uses a variant of the combinatorial Hough transform.
    Type: Grant
    Filed: December 19, 1997
    Date of Patent: September 19, 2000
    Assignee: Electronics for Imaging, Inc.
    Inventor: Michael Alan Peters
  • Patent number: 6108456
    Abstract: There is disclosed an image processing apparatus such that after completion of one scan of a scanner unit, a controller obtains a background value in a range to be read by one scan from an image processing IC and compares the background value with a binarization threshold value used in the present scan, and when it is equal to or less than a predetermined value, the background value is used in the next scan, and when it is equal to or larger than the predetermined value, by correcting the threshold value, an image can be read at a high quality.
    Type: Grant
    Filed: October 16, 1996
    Date of Patent: August 22, 2000
    Assignee: Canon Kabushiki Kaisha
    Inventor: Tadashi Yamamoto
  • Patent number: 6094508
    Abstract: What is disclosed is a method for dynamically and automatically determining the threshold value for edge detection based on localized intensity information. Each pixel can be assigned a threshold to which its gradient or other intensity change information can be compared so as to detect whether or not the pixel belongs to an edge feature of the image or not. Further, the thresholding can be based upon the response of the human vision system so that visual appearance of the image to users is considered when analyzing localized intensity information. The localized thresholding technique can be applied to any edge detection scheme.
    Type: Grant
    Filed: December 8, 1997
    Date of Patent: July 25, 2000
    Assignee: Intel Corporation
    Inventors: Tinku Acharya, Ping-Sing Tsai
  • Patent number: 6072907
    Abstract: An image processing method and system for generating enhanced binary image data from greyscale input image data. The method includes the steps of (a) receiving first image data, the first image data being greyscale image data defining an input image, (b) performing a high frequency boost operation on the first image data to produce second image data, (c) performing a linear interpolation operation on the second image data to produce third image data, the third image data having a resolution higher than the resolution of the second image data, (d) performing a contrast enhancement operation on the third image data to produce fourth image data, and (e) thresholding the fourth image data to produce fifth image data, the fifth image data being binary image data defining an output image. The techniques find application, for example, in over-the-desk scanning of documents, and in video-conferencing.
    Type: Grant
    Filed: May 19, 1998
    Date of Patent: June 6, 2000
    Assignee: Xerox Corporation
    Inventors: Michael J. Taylor, Anthony Zappala
  • Patent number: 6057586
    Abstract: A method and apparatus for employing a light shield to modulate pixel color responsivity. The improved pixel includes a substrate having a photodiode with a light receiving area. A color filter array material of a first color is disposed above the substrate. The pixel has a first relative responsivity. A light shield is disposed above the substrate to modulate the pixel color responsivity. The light shield forms an aperture whose area is substantially equal to the light receiving area adjusted by a reduction factor. The reduction factor is the result of an arithmetic operation between the first relative responsivity and a second relative responsivity, associated with a second pixel of a second color.
    Type: Grant
    Filed: September 26, 1997
    Date of Patent: May 2, 2000
    Assignee: Intel Corporation
    Inventors: Edward J. Bawolek, Lawrence T. Clark, Mark A. Beiley
  • Patent number: 6044179
    Abstract: Document image thresholding using foreground and background is disclosed. A document (16) is scanned and a region (30) and a sub-region (32) of the document is selected. The intensity value of a pixel in the region is compared to an average intensity value of pixels in a foreground cluster and to an average intensity value of pixels in a background cluster (50). The pixel is assigned to the foreground cluster (53) if the intensity value of the pixel is closer to the average intensity of the foreground cluster, or to the background cluster (54) if the pixel intensity is closer to the average intensity value of the background cluster. A new average intensity value is calculated for the foreground cluster (55) and the background cluster (56). A new pixel is compared to the new average intensity values for the foreground and background clusters and the process is repeated until all pixels in the region have been compared (57).
    Type: Grant
    Filed: November 26, 1997
    Date of Patent: March 28, 2000
    Assignee: Eastman Kodak Company
    Inventor: Andreas E. Savakis
  • Patent number: 6021230
    Abstract: An improved interpolation method in which a threshold value used for determining a pixel value of a pixel generated by interpolation according to a context (state value of adjacent pixels). In the interpolation method, the ambiguity between the interpolation value and the threshold value is removed by using the context (state value of the reference pixels around the interpolated pixel), thereby reducing the blocking and smoothing phenomena in the restored binary image.
    Type: Grant
    Filed: November 26, 1997
    Date of Patent: February 1, 2000
    Assignee: Samsung Electronics Co., Ltd.
    Inventors: Dae-sung Cho, Jae-seob Shin
  • Patent number: 6018601
    Abstract: An interpolation method in which a threshold value used for determining a pixel value of a pixel generated by interpolation according to a context (state value of adjacent pixels). In the interpolation method, the ambiguity between the interpolation value and the threshold value is removed by using the context (state value of the reference pixels around the interpolated pixel), thereby reducing the blocking and smoothing phenomena in the restored binary image.
    Type: Grant
    Filed: May 29, 1998
    Date of Patent: January 25, 2000
    Assignee: Samsung Electronics Co., Ltd.
    Inventors: Dae-sung Cho, Jae-seob Shin
  • Patent number: 6014465
    Abstract: According to the invention there is provided a method for transforming a gray-level image, divided into pixels, into a black-and-white image, comprising the steps of: dividing the gray-level image into a number of generally square sub images which comprise more than one pixel; calculating and storing, for each sub image, at least one measurement value representing the gray-level of the sub image; calculating, for each sub image, a threshold value based on the measurement values of the sub image, and a number of sub images that are adjacent the sub image; and transforming, for each sub image, each pixel in the sub image to either a white or a black pixel depending upon whether the gray-level of the pixel exceeds the threshold value of the sub image or not. Preferably, parts of the gray-level image, the measurement value or values that is/are calculated, for each sub image, and the threshold value that is calculated, for each sub image, are temporarily stored in one or more memory buffers.
    Type: Grant
    Filed: September 17, 1997
    Date of Patent: January 11, 2000
    Assignee: Christian Bjorn Stefan
    Inventors: Christian Bjorn Stefan Blixt, Stefan Sven Blixt
  • Patent number: 6002812
    Abstract: An improved interpolation method in which a threshold value used for determining a pixel value of a pixel generated by interpolation according to a context which is a state value of adjacent pixels. In the interpolation method, the ambiguity between the interpolation value and the threshold value is removed by using the context, thereby reducing the blocking and smoothing phenomena in the restored binary image.
    Type: Grant
    Filed: November 26, 1997
    Date of Patent: December 14, 1999
    Assignee: Samsung Electronics Co., Ltd.
    Inventors: Dae-sung Cho, Jae-seob Shin
  • Patent number: 6002813
    Abstract: An improved interpolation method in which a threshold value used for determining a pixel value of a pixel generated by interpolation according to a context which is a state value of adjacent pixels. In the interpolation method, the ambiguity between the interpolation value and the threshold value is removed by using the context, thereby reducing the blocking and smoothing phenomena in the restored binary image.
    Type: Grant
    Filed: May 29, 1998
    Date of Patent: December 14, 1999
    Assignee: Samsung Electronics Co., Ltd.
    Inventors: Dae-sung Cho, Jae-seob Shin
  • Patent number: 5995640
    Abstract: A fingerprint image is divided into blocks of pixels. The blocks are also determined to be within the foreground or background of the image. A dryness process determines a mean intensity of pixels within each foreground block, a second mean intensity of pixels for those pixels whose intensities are smaller than the mean intensity, a standard deviation of intensities of all pixels within the respective foreground block, and a contrast measure being a function of a first ratio of the second mean intensity to the standard deviation. A comparator that determines that the foreground block is a dry block if the contrast measure is larger than a dryness threshold and that the image is a dry image if a second ratio of the number of dry blocks to total number of foreground blocks is larger than a third dryness threshold.
    Type: Grant
    Filed: October 23, 1996
    Date of Patent: November 30, 1999
    Assignee: International Business Machines Corporation
    Inventors: Rudolf Maarten Bolle, Sharathchandra Umapatirao Pankanti, Yi-Sheng Yao
  • Patent number: 5987156
    Abstract: A facility is provided for correcting fixed column noise that may appear in a fingerprint image acquired from a capacitive fingerprint sensor. In particular, corrective gain and offset values are determined for each column of pixel signals generated by the sensor and are applied to such signals to greatly diminish the fixed column noise that may be present in that column.
    Type: Grant
    Filed: November 25, 1996
    Date of Patent: November 16, 1999
    Assignee: Lucent Technologies
    Inventors: Bryan David Ackland, Andrew John Blanksby
  • Patent number: 5982946
    Abstract: A method of identifying defective pixels included in a digital image. The method includes the steps of designating a pixel adjacent the defective pixels in the digital image, setting an evaluation area, setting a defective pixel candidate, computing, as a line average, an average pixel value of each of lines above, below, leftward and rightward of the defective pixel candidate, diminishing the evaluation area by selecting an upper line, a lower line, a left line and a right line, computing a threshold pixel value for determining the defective pixels, from an average pixel value of each line, and comparing values of all pixels with the threshold pixel value to determine the defective pixels.
    Type: Grant
    Filed: September 5, 1997
    Date of Patent: November 9, 1999
    Assignee: Dainippon Screen Mfg. Co., Ltd.
    Inventor: Shigeo Murakami
  • Patent number: 5982508
    Abstract: In processing an image represented by binary data and an image represented by multivalue data, multivalue picture information is converted into a binary pattern corresponding to a value of the multivalue picture information, and stored in a memory. A binary pattern corresponding to multivalue picture information is detected from binary picture information stored in the memory to recover the original multivalue picture information.
    Type: Grant
    Filed: May 21, 1996
    Date of Patent: November 9, 1999
    Assignee: Canon Kabushiki Kaisha
    Inventor: Atsushi Kashihara
  • Patent number: 5978098
    Abstract: An image compression method for encoding gradation image data for use in, for example, a printer or a copying machine handling the gradation image. When a difference between two representative values in one block E)f the image data is less than a predetermined amount, a block code made up of a single piece of gradation data and one pixel array pattern is generated. When the difference is not less than the predetermined amount, the representative values are replaced by any of sixteen substitute values, and a block code is formed to include two gray scale data each of four bits and a single pixel array pattern, thereby realizing coding compression of the image information.
    Type: Grant
    Filed: March 31, 1997
    Date of Patent: November 2, 1999
    Assignee: Matsushita Electric Industrial Co., Ltd.
    Inventors: Noriko Takeuchi, Yukihiro Nishida, Seiichiro Hiratsuka
  • Patent number: 5966678
    Abstract: A computer software program for replacing drop-out pixels and erroneous re values in the range channel of a laser detection and ranging system with a median pixel value in a moving square window centered about a pixel being processed whenever a co-registered intensity pixel value in the intensity channel falls below an intensity threshold. During the processing of each range pixel of the target, the computer software program will not alter the range value of the pixel if its corresponding intensity pixel has an intensity value above the intensity threshold. When the intensity value of the corresponding intensity pixel is below the threshold, the intensity guided filter replaces the range value with the median value of all the "good" pixels within a moving window the size of a kernel having X and Y dimensions. This results in the intensity guided filter smoothing out noisy pixels in the range channel of while retaining edge pixel values for the image.
    Type: Grant
    Filed: May 18, 1998
    Date of Patent: October 12, 1999
    Assignee: The United States of America as represented by the Secretary of the Navy
    Inventor: Chi-Kin Lam
  • Patent number: 5963669
    Abstract: A method of processing a matrix of gray scale picture elements derived from lifting an image of a document to extract strokes from the image of the document comprises the steps of (a) calculating a global average value of the gray scale picture elements, (b) placing a window over a portion of the matrix of gray scale picture elements, (c) calculating a local average value of the gray scale picture elements contained in the window of step (b), (d) comparing the global average value of step (a) with the local average value of step (c), (e) calculating a relative figure of importance (RFI) value for each gray scale picture element contained in the window of step (b) when the local average value calculated in step (c) is less than the global average value calculated in step (a), (f) increasing the size of the window of step (b) and replacing the window of step (b) with this increased sized window when the local average value calculated in step (c) is greater than the global average value calculated in step (a), a
    Type: Grant
    Filed: January 2, 1997
    Date of Patent: October 5, 1999
    Assignee: NCR Corporation
    Inventors: Slawomir B. Wesolkowski, Khaled S. Hassanein, Raymond L. Higgins
  • Patent number: 5956430
    Abstract: An image information coding apparatus includes a block generator for dividing image information into pixel blocks, each of which consists of a predetermined number of pixels. A block selector selects a pixel block in a position different from that of a pixel block selected in a preceding block line in a main scanning direction from the pixel blocks generated by the block generator. A parameter setting device sets a coding parameter to a predetermined value. A first variable-length coding device conducts variable-length coding of the pixel block selected by the block selector using the coding parameter. A code amount controller changes a value of the coding parameter so that the code amount of the pixel block selected by the block selector and coded by the first variable-length coding device is not more than a predetermined code amount, and a second variable-length coding device conducts variable-length coding of all of the pixel blocks using a coding parameter changed by the code amount controller.
    Type: Grant
    Filed: October 3, 1996
    Date of Patent: September 21, 1999
    Assignee: Fuji Xerox Co., Ltd.
    Inventors: Setsu Kunitake, Shun-ichi Kimura, Taro Yokose, Yutaka Koshi, Koh Kamizawa
  • Patent number: 5956432
    Abstract: In an image processing apparatus and method for effectively removing noise from an input image signal, a mean-value calculation unit calculates the mean value of pixels within a predetermined region in the vicinity of a target pixel, for each color component. A binary-coding unit performs binary-coding processing of the values of pixels within the predetermined region, for each color component, based on the mean value for each color component. A correlation-coefficient calculation unit calculates a correlation coefficient from characteristics between binary image data of respective color components. A smoothing unit performs smoothing processing by adding the value of the target pixel and the mean value using the calculated correlation coefficient, for example as a weight.
    Type: Grant
    Filed: May 31, 1996
    Date of Patent: September 21, 1999
    Assignee: Canon Kabushiki Kaisha
    Inventor: Kenichi Ohta
  • Patent number: 5956421
    Abstract: An image processor determines a binarization threshold value used for binarizing a multi-valued image, and performs binarization processing on the multi-valued image. The multi-valued image is input line-sequentially, the binarization threshold values are determined sequentially in units of predetermined size blocks each including a plurality of pixels, and the multi-valued image data is binarized line-sequentially. The inputting of data, determining the threshold value, and binarization of the multi-value image data is performed by pipeline processing.
    Type: Grant
    Filed: February 27, 1997
    Date of Patent: September 21, 1999
    Assignee: Canon Kabushiki Kaisha
    Inventors: Tetsuomi Tanaka, Osamu Yamada
  • Patent number: 5933545
    Abstract: A decimation device for digital data sequences includes a multiplexer mounted in cascade with a calculator producing, alternately, during a first calculation cycle, the mean M.sub.i of at least two data sequences representing the pixels P(i,j) and P(i,j+1) in a line L.sub.i, and during a following calculation cycle, the mean M.sub.c. The mean M.sub.c is composed of the mean M.sub.i and of an intermediate sequence previously calculated and stored in a storage register arranged between an output for the calculation stage and at least one of the inputs to the multiplexer. The intermediate sequence represents the mean M.sub.i-1 of at least two data sequences representing pixels P(i-1,j) and P(i-1,j+1) in a line L.sub.i-1, where i varies from 0 to N-1 and j varies from 0 to M-1.
    Type: Grant
    Filed: November 25, 1996
    Date of Patent: August 3, 1999
    Assignee: Thomson multimedia S.A.
    Inventors: Farid Kazi, Alain Pirson
  • Patent number: 5926579
    Abstract: Density data produced by an image reading unit is input to a surface density detection unit, which detects a surface density by averaging density data of pixels within a predetermined density range. A period setting unit sets a period of sampling density data of pixels to be used for calculation of the surface density. A surface reference density generation unit generates a surface reference density by adding an offset to the detected surface density. A surface color elimination unit corrects density data of a pixel lower than the surface reference density to the white level to eliminate a surface color.
    Type: Grant
    Filed: November 21, 1995
    Date of Patent: July 20, 1999
    Assignee: Fuji Xerox Co., Ltd.
    Inventors: Hiroyoshi Uejo, Yoshiyuki Hirayama
  • Patent number: 5920655
    Abstract: An appropriate binarization threshold can be automatically set between the object density and the background density in a multi-level input image, by determining the frequencies of the luminance levels of the entire image, then calculating the average and deviation of the frequencies, then specifying a region containing the optimum threshold for separating the object and the background in the image, by judging the magnitude of the deviation, and taking the average luminance of the specified region as the binarization threshold. Also in processing an image containing objects of three or more luminance levels, highly precise binarization according to the luminance hierarchy allows exact separation of the image regions, enabling precise character recognition process according to the hierarchic luminance levels.
    Type: Grant
    Filed: February 7, 1996
    Date of Patent: July 6, 1999
    Assignee: Canon Kabushiki Kaisha
    Inventors: Takeshi Makita, Osamu Yamada, Hiroshi Mori
  • Patent number: 5915039
    Abstract: Fixed-pitch, fixed-font characters embedded in a noisy gray-scale image of picture elements (pels) within a complex background can be extracted prior to execution of any recognition operations by first deriving a normalized Boolean-coded image from the gray-scale image. Then, a subset of at least three uncontaminated character triples is formed by filtering the Boolean-coded image. Next, an affine transform is approximated from locations in the Boolean-coded image of at least three noncollinear ones of the uncontaminated character triples. Lastly, the locations in a logical matrix array of all possible character triples are estimated according to the affine transform.
    Type: Grant
    Filed: November 12, 1996
    Date of Patent: June 22, 1999
    Assignee: International Business Machines Corporation
    Inventors: Raymond Amand Lorie, Jianchang Mao, Kottappuram Mohamedali Mohiuddin
  • Patent number: 5909514
    Abstract: An image processing method and device computes the image quality as an evaluation value, determine the image quality based on this evaluation value, and employ a restoration process in accordance with image quality when this image quality is poor.
    Type: Grant
    Filed: June 7, 1995
    Date of Patent: June 1, 1999
    Assignee: Seiko Epson Corporation
    Inventors: Yasuhiko Murayama, Ayako Kobayashi, Naoki Kuwata
  • Patent number: 5883971
    Abstract: A fingerprint image is divided into blocks of pixels. The blocks are determined to be within the foreground or background of the image. Poor quality images are examined to determine if the imaging process is corrupted, e.g. by a wet finger, by determining if a smudginess measure is above a smudginess threshold. For each foreground block, a mean intensity (.mu.) of pixels is computed for those pixels whose intensities are smaller than the mean intensity of all pixels within the respective foreground block. Further the standard deviation (.cuberoot.) of intensities of all pixels within the respective foreground block is computed. For a foreground block with good contrast, .mu. is small and .cuberoot. is large. But for a block with low contrast due to smudginess, .mu. is small and .cuberoot. is small. Subsequently, to measure the contrast (a contrast measure) within a block, a function of the product (C.sub.S) of corresponding .mu. and corresponding .cuberoot. is determined.
    Type: Grant
    Filed: October 23, 1996
    Date of Patent: March 16, 1999
    Assignee: International Business Machines Corporation
    Inventors: Rudolf Maarten Bolle, Sharathchandra Umapatirao Pankanti, Yi-Sheng Yao
  • Patent number: 5870505
    Abstract: A method for adjusting the luminance IM.sub.HI of pixels in a high resolution image includes first forming a low resolution image of the original by grouping pixels into superpixels such as 8.times.8 blocks. A low resolution luminance correction value .delta..sub.LO is determined for each superpixel by comparing the luminance of the superpixel to both a predetermined darkness threshold T.sub.D and a predetermined brightness threshold T.sub.B. The low resolution luminance correction value .delta..sub.LO is modified to yield .delta.'.sub.LO for each superpixel by forming islands of the superpixels and smoothing .delta..sub.LO between superpixels within each island. Finally, a high resolution luminance correction value .delta..sub.HI is calculated for each pixel of the original high resolution image by comparing the luminance IM.sub.HI of each pixel to both T.sub.D and T.sub.B, keeping in mind that .delta..sub.
    Type: Grant
    Filed: March 14, 1996
    Date of Patent: February 9, 1999
    Assignee: Polaroid Corporation
    Inventors: Munib A. Wober, Ibrahim Hajjahmad
  • Patent number: 5841882
    Abstract: A process for the maceral analysis of a sample of crushed coal coated with resin includes the steps of scanning the surface of the sample with a microscope and measuring the reflectance of the vitrinite. The process further includes the steps of forming a digitized image having gray levels for each field of the microscope and eliminating those fields having a high resin content. In those fields which are not eliminated, the distribution of gray levels and gradients are determined, a binary image is formed by thresholding the gray gradients to determine zones of vitrinite, the distribution of the gray levels of the obtained zones of vitrinite are then determined and the reflectance of the vitrinite is calculated.
    Type: Grant
    Filed: December 9, 1994
    Date of Patent: November 24, 1998
    Assignee: Sollac
    Inventor: Jean-Claude Celeski
  • Patent number: 5825940
    Abstract: An object of the present invention is to provide an image processing apparatus capable of, at high speed, forming a half tone image exhibiting excellent linearity and gradation expressing characteristics while requiring only a simple structure. The image processing apparatus including a mean density calculating circuit for calculating a mean density in a predetermined region, a random number generator for generating random number data, an adder for adding, at a ratio corresponding to a level of input multivalue image data, the mean density obtained by said mean density calculating circuit and the random number data supplied from the random number generator, and a comparator for binary-coding the multivalue image data in such a manner that a value obtained by said adder is used as a threshold.
    Type: Grant
    Filed: January 17, 1996
    Date of Patent: October 20, 1998
    Assignee: Canon Kabushiki Kaisha
    Inventors: Shigeo Yamagata, Hiroshi Tanioka
  • Patent number: 5805723
    Abstract: An object of the present invention is to provide an image processing apparatus that reads density unevenness contained in the image, based on the base density of the image data and performs density data correction.
    Type: Grant
    Filed: February 26, 1996
    Date of Patent: September 8, 1998
    Assignee: Minolta Co., Ltd.
    Inventor: Yoko Fujiwara
  • Patent number: 5798948
    Abstract: A method and apparatus for video filtering filters video frames by determining a set of frames to be used to generate a single filtered frame. This set of frames is then combined to generate a single combined image. In one embodiment, proportions of the luminances for each of four fields from two consecutive frames in an NTSC video signal are combined to generate the single combined frame.
    Type: Grant
    Filed: June 20, 1995
    Date of Patent: August 25, 1998
    Assignee: Intel Corporation
    Inventors: Oleg Rashkovskiy, Jeffrey N. Kidder
  • Patent number: 5764811
    Abstract: An image processing apparatus 30, which can solve the problems of delay in dot generation in beginning portions of areas of low or high density and tailing after finishing areas of low or high density and carry out speedy binary coding image processing without accompanying side effects of quality depletion and without the need to utilize a complicated processing circuit: includes error correction means 34 which corrects multigradation image data 200 and outputs it, threshold error setting means which sets a binary coding threshold value based on the gradation value of said target pixel multigradation image data 200 and binary coding means 36 which, based on the set threshold value, converts the previously mentioned corrected pixel data into the previously mentioned bigradation image data and outputs it; the gradation value of the previously mentioned target pixel multigradation image data being data, the median value of the previously mentioned first gradation value and second gradation value being m and the
    Type: Grant
    Filed: June 4, 1996
    Date of Patent: June 9, 1998
    Assignee: Seiko Epson Corporation
    Inventor: Toshiaki Kakutani
  • Patent number: 5764813
    Abstract: An image processing method and device computes the image quality as an evaluation value, determine the image quality based on this evaluation value, and employ a restoration process in accordance with image quality when this image quality is poor.
    Type: Grant
    Filed: June 7, 1995
    Date of Patent: June 9, 1998
    Assignee: Seiko Epson Corporation
    Inventors: Yasuhiko Murayama, Mikio Aoki, Naoki Kuwata
  • Patent number: 5760918
    Abstract: In an image processing apparatus in which digital data of a certain number (m) of levels are converted into digital data of a larger number (n) of levels, then subjected to certain desired editing processing, and again digitized to data of the original number (m) of levels. The redigitization to m levels is conducted by determining the average density of a predetermined area, utilizing data of pixels already redigitized to m levels, and redigitizing the data of n levels into m levels, utilizing the average value. This process significantly reduces the amount of data processing required without formation of an unpleasant texture on the image resulting from errors in digitization.
    Type: Grant
    Filed: January 21, 1994
    Date of Patent: June 2, 1998
    Assignee: Canon Kabushiki Kaisha
    Inventors: Hiroshi Tanioka, Yasuhiro Yamada
  • Patent number: 5745262
    Abstract: An image read-out and processing apparatus comprises an image read-out section, which carries out a preliminary readout and a final readout, and an image processing section. In the final readout, the amount of light irradiated to an image storage sheet, on which an image has been recorded, and/or the light accumulation time of a photoelectric conversion device is adjusted appropriately in accordance with preliminary read-out image information obtained from the preliminary readout. The image processing section is provided with a color and density correcting device for correcting the final read-out image information such that the color and the density of the image may become appropriate, and for determining the degree of correction, which is carried out on the final read-out image information, in accordance with a parameter, which is set in accordance with the preliminary read-out image information. A parameter correcting device corrects the parameter in accordance with the final read-out image information.
    Type: Grant
    Filed: October 16, 1996
    Date of Patent: April 28, 1998
    Assignee: Fuji Photo Film Co., Ltd.
    Inventor: Setsuji Tatsumi
  • Patent number: 5745660
    Abstract: An image rendering system, for generating discrete tone image data representing a continuous-tone image for rendering by a rendering device, the image rendering system includes a stochastic threshold array generating arrangement and an image data processing section. The stochastic threshold array generating arrangement generates a plurality of stochastic threshold arrays from a random seed pattern that have been subsequently optimized to reduce image artifacts in the rendering of tones. Each pattern is optimized to reflect (i) a selected trade-off between grain and possible mottle in the rendered image, (ii) distortions introduced by the rendering device in rendering an image defined by the pattern and an observer in viewing the image, and (iii) boundary effects so that the patterns, when tiled together, have optimal visual characteristics proximate their respective edges.
    Type: Grant
    Filed: April 26, 1995
    Date of Patent: April 28, 1998
    Assignee: Polaroid Corporation
    Inventors: Bernd W. Kolpatzik, Jay E. Thornton
  • Patent number: 5706355
    Abstract: A method and system of analyzing sequences of road images taken by a camera carried on board of a vehicle. A luminance signal of the road images from which contours of the road are extracted is generated. An analysis of color video signals based on the fact that the colorimetric components of a road region in an image do not include a green or red dominant is then combined with the luminance signal processing, in order to confirm, with good reliability, the limits of the road in the image on the basis of the contours. A mask of the road is then established. This method and system are applicable, in particular, to detecting obstacles on the road, and the information which it generates may be combined with information originating from other detectors in an obstacle detection system applicable to motor vehicle traffic.
    Type: Grant
    Filed: September 19, 1996
    Date of Patent: January 6, 1998
    Assignee: Thomson-CSF
    Inventors: Stephane Raboisson, Gilles Even
  • Patent number: 5669382
    Abstract: The present invention determines the epicardial boundary, being a closed curve dividing the myocardium from the tissue and blood surrounding the left ventricle. A mean and standard deviation is determined for pixels of a medical image of the subject's myocardial tissue. These are used to define a "goodness function" over the image which is positive for pixels statistically likely to be myocardial tissue, and negative for other pixels. An initial curve for modeling the epicardium in radial coordinates starts with a curve of inner myocardial boundary obtained my conventional imaging techniques. This curve is then iteratively updated to maximize the total "goodness function" of the region encompassed.
    Type: Grant
    Filed: November 19, 1996
    Date of Patent: September 23, 1997
    Assignee: General Electric Company
    Inventors: Rupert William Meldrum Curwen, Richard Ian Hartley
  • Patent number: 5657401
    Abstract: In a method of measuring noise in image signals, a number of noise estimates (SAD) is calculated (1). Subsequently, it is determined (3-9) which noise estimation interval [A, B] out of a plurality of predetermined noise estimation intervals [A, B] contains at least a predetermined number of noise estimates (SAD) and has at the same time the lowest upper interval boundary. The output noise measurement value depends on the determined noise estimation interval.
    Type: Grant
    Filed: February 24, 1995
    Date of Patent: August 12, 1997
    Assignee: U.S. Philips Corporation
    Inventors: Gerard De Haan, Tatiana G. Kwaaitaal-Spaasova, Olukayode A. Ojo