Variable Thresholding Technique Patents (Class 358/466)
-
Patent number: 7881553Abstract: An image processing apparatus includes a threshold selecting unit that selects a threshold based on an input gray-scale value of the target pixel. When a degree of flexibility is defined as representing a degree of the number of pixels that can take different output values as a result of threshold processing on the pixels with the same input gray-scale value, the threshold selecting unit selects a threshold from at least two types of thresholds associated with pixel positions and having the same period and different degrees of flexibility.Type: GrantFiled: December 6, 2006Date of Patent: February 1, 2011Assignee: Ricoh Company, Ltd.Inventor: Hiroshi Ishii
-
Patent number: 7817876Abstract: A noisy signal analysis in which a threshold value is set to evaluate the presentation of the display device. The analysis can produce the range of noise level of the image for measuring the distortion block of image caused by the display devices. Furthermore, the apparatus includes a step function generator for producing step functions, a transforming unit for changing threshold value in step functions, and a display for showing the image corresponding to both the high value and low value.Type: GrantFiled: April 12, 2006Date of Patent: October 19, 2010Assignee: Etron Technology, Inc.Inventor: Ming-Sung Huang
-
Patent number: 7724955Abstract: Methods and apparatus for segmenting image data into windows and rendering a best-estimate outline delineating document windows may include adjusting a background white threshold differently than adjusting a white threshold normally used to classify pixels as white for video processing purposes. Such an independently arrived at threshold may be more suitable for the different task of differentiating between document background and document content.Type: GrantFiled: May 31, 2005Date of Patent: May 25, 2010Assignee: Xerox CorporationInventors: David Jon Metcalfe, Jeng-Nan Shiau
-
Patent number: 7705802Abstract: A method for diffusing errors in a display device. Each frame of an input video signal is separated into at least two independent subframes. An error diffusion process is applied to each subframe of at least two independent subframes. The errors transmitted reciprocally from subframes are partially mixed, and the error diffusion process is applied to the mixed errors at each independent subframe.Type: GrantFiled: August 5, 2004Date of Patent: April 27, 2010Assignee: Samsung SDI Co., Ltd.Inventor: Seung-Ho Park
-
Patent number: 7701623Abstract: An image reading device includes: a first light source that irradiates light on a first side of an object; a memory that stores a plurality of parameters for controlling an intensity of the light emitting devices, each of the plurality of parameters corresponding to one of a plurality of groups; a controller that controls an intensity of the light emitting devices in response to one of the plurality of parameters stored in the memory; a first image reading unit that reads reflected light from the first side and generates monochrome image data on the basis of the read reflected light; and a second image reading unit that reads reflected light from the second side and generates monochrome image data on the basis of the read reflected light.Type: GrantFiled: June 13, 2007Date of Patent: April 20, 2010Assignee: Fuji Xerox Co., Ltd.Inventors: Mitsuo Shimizu, Norikazu Sakai
-
Patent number: 7672525Abstract: An image processing method for executing a quantization process of image data by error diffusion, executes a step of generating first image data by adding a quantization error to input image data, a step of generating second image data by quantizing the first image data by comparing the first image data with a predetermined threshold value, a step of generating third image data by dequantizing the second image data, a calculation step of calculating a quantization error for each pixel on the basis of the difference between the first and third image data, a storage step of storing information indicating a positive/negative sign of the calculated quantization error for a predetermined number of pixels in a storage unit, and a correction value generation step of generating a correction value used to correct at least one of the first image data and the threshold value on the basis of the information which is stored in the storage unit and indicates the positive/negative sign.Type: GrantFiled: July 23, 2004Date of Patent: March 2, 2010Assignee: Canon Kabushiki KaishaInventor: Hisashi Ishikawa
-
Patent number: 7646502Abstract: A driver program is provided for causing a host apparatus to execute a processing of generating color-converted image data and transferring it to a printing apparatus, this program making it possible to decrease the volume of image data to be stored in the host apparatus and to conduct data transfer without delaying the printing completion. A driver program causes a host apparatus to execute a processing of generating image data comprising data of a plurality of colors and transferring it to a printing apparatus. When the transfer of the image data of one plane is conducted, the driver program causes the host apparatus to execute a transfer processing conducted by intermingling a step of transferring by each band of the bands obtained by dividing the image data of one plane at the prescribed height, and a step of transferring by each color of the plurality of colors.Type: GrantFiled: March 29, 2005Date of Patent: January 12, 2010Assignee: Seiko Epson CorporationInventor: Tetsuya Suzuki
-
Publication number: 20090323132Abstract: Input image data is converted into a brightness component to obtain a difference between the brightness component and a threshold. A count variation is determined based on the obtained difference, and the counter is used to follow up and change the threshold. The threshold obtained by the follow-up and change is used to execute a background color removal process in each pixel by executing a signal conversion process.Type: ApplicationFiled: June 5, 2009Publication date: December 31, 2009Applicant: CANON KABUSHIKI KAISHAInventors: Takaaki Yano, Hirokazu Tamura, Atsushi Matsumoto
-
Patent number: 7616340Abstract: The image processing method comprises: a recording failure position determination step of determining a recording failure position on an image corresponding to a malfunctioning recording element; a basic threshold value matrix storage step of storing a basic threshold value matrix set with threshold values used for halftoning of converting multiple-value input image data into dot data of a number of tonal graduations smaller than that of the multiple-value input image data by quantizing the multiple-value input image data; a sub-matrix storage step of storing a plurality of sub-matrices in association with recording failure positions in the basic threshold value matrix, each of the sub-matrices being set with threshold values which are substituted for the threshold values in a partial region of the basic threshold value matrix, the partial region including a pixel position corresponding to the recording failure position and having a width of a prescribed number of pixels; a replacement region determination stType: GrantFiled: March 23, 2006Date of Patent: November 10, 2009Assignee: Fujifilm CorporationInventor: Yoshirou Yamazaki
-
Patent number: 7574069Abstract: A method retargets an image to a different size. An input image is segmented into regions. Selected regions are cut from the input image to construct a background image. The background image is scaled to a predetermined size, and the selected regions are pasted back into the scaled background image to produce an output image.Type: GrantFiled: August 1, 2005Date of Patent: August 11, 2009Assignee: Mitsubishi Electric Research Laboratories, Inc.Inventors: Vidya Setlur, Michael Gleicher, Bruce Gooch, Saeko Takagi, Ramesh Raskar
-
Patent number: 7557969Abstract: In the present invention, a front-side focal distance L2 is changed without changing a rear-side focal distance L1 so as to bring an MTF value D2 and brightness fluctuation D3 into an MTF balance range, so that collapse of color balance can be improved, and life of optical members such as a light source can be extended.Type: GrantFiled: March 22, 2004Date of Patent: July 7, 2009Assignees: Kabushiki Kaisha Toshiba, Toshiba Tec Kabushiki KaishaInventor: Toshihiro Sone
-
Publication number: 20090161172Abstract: An image processing device has a main unit, a storage unit, a first processing unit, a second processing unit, a first determination unit, and a first replacement unit. The storage unit is provided in the main unit that stores a color image having ground color and different color from the ground color, the color image being formed by color-pixels including a ground color pixel and a different color pixel, the ground color pixel having the ground color, the different color pixel having the different color. The first processing unit scales down the color image to produce a first gray-scale image which is simply represented by brightness having a plurality of brightness values, the first gray-scale image being formed by first gray-scale pixels. The second processing unit determines the brightness value of each of the color pixels to produce a histogram showing a distribution of the color pixels with respect to the brightness.Type: ApplicationFiled: December 20, 2007Publication date: June 25, 2009Applicant: BROTHER KOGYO KABUSHIKI KAISHAInventor: Shunsuke Mizutani
-
Patent number: 7545435Abstract: In some embodiments, images for the video conference may be white balanced and/or exposure controlled. White balancing may include dividing an image's pixels into multiple ranges according to their luminance and chrominance values. In some embodiments, blue and red analog gains may be modified to bring red and blue accumulations closer to green accumulations. In some embodiments, luminance values for an image may be adjusted by increasing or decreasing exposure. The decision whether to increase or decrease the exposure may be made by looking at statistics for luminance values of skin colored regions if there are sufficient skin colored regions on the image. Otherwise, luminance values for the entire image may be analyzed to determine whether to increase or decrease exposure.Type: GrantFiled: April 15, 2005Date of Patent: June 9, 2009Assignee: LifeSize Communications, Inc.Inventors: Michael V. Jenkins, Bradley Richard Ree
-
Patent number: 7525703Abstract: An image reading apparatus includes an abnormal pixel detection device configured to examine a value of standard white image data, which is acquired by reading a white image to be a standard for a shading correction, on a pixel-by-pixel basis, to determine whether or not pixels are abnormal, wherein a previously specified value is stored for use as the standard white image data for pixels which are determined to be abnormal by the abnormal pixel detection device. As a result, costs of the image reading apparatus can be reduced because a special memory device for memorizing the positions of abnormal pixels is not required.Type: GrantFiled: November 12, 2001Date of Patent: April 28, 2009Assignee: Ricoh Company, Ltd.Inventor: Naohiro Yasuda
-
Publication number: 20090091802Abstract: To render the comparison of image patches more efficient, the data of an image patch can be projected into a smaller-dimensioned subspace, resulting in a descriptor of the image patch. The projection into the descriptor subspace is known as a linear discriminant embedding, and can be performed with reference to a linear discriminant embedding matrix. The linear discriminant embedding matrix can be constructed from projection vectors that maximize those elements that are shared by matching image patches or that are used to distinguish non-matching image patches, while also minimizing those elements that are common to non-matching image patches or that distinguish matching image patches. The determination of such projection vectors can be limited such that only orthogonal vectors comprise the linear discriminant embedding matrix. The determination of the linear discriminant embedding matrix can likewise be constrained to avoid overfitting to training data.Type: ApplicationFiled: October 9, 2007Publication date: April 9, 2009Applicant: Microsoft CorporationInventors: Matthew Alun Brown, Gang Hua, Simon A. J. Winder
-
Patent number: 7480078Abstract: A method and system for performing error diffusion are disclosed. An ordered set of pixels, including a pixel intensity value for each pixel, is received. Each pixel intensity value includes a value within a range from a low value to a high value, inclusive. An initial error value is also received. Based on the pixel intensity values and the initial error value, a pixel value for each pixel and an updated error value are computed substantially simultaneously with each other.Type: GrantFiled: April 28, 2005Date of Patent: January 20, 2009Assignee: Xerox CorporationInventors: Yungran Choi, Xing Li, Daniel A. Mohabir
-
Publication number: 20080062473Abstract: An image processing device is provided which comprises an input unit and an analog front end circuit with DC inputs. According to the invention, no capacitor is installed in the input unit and no clamper is installed in the AFE circuit with DC inputs. By appropriately selecting a comparing voltage and adding a level shifter or a compensation circuit, the invention can still generate an accurate digital signal.Type: ApplicationFiled: August 22, 2007Publication date: March 13, 2008Inventor: Jui-Yuan Tsai
-
Patent number: 7342696Abstract: The amount of moiré in halftone printed images is reduced using unique moiré intensity functions and moiré vectors in a halftoner. In various embodiments, moiré phase angle zones are determined over the full field of an image and high addressability units in the full-field moiré phase angle zones of the image are adjusted, including in an iterative manner, until they significantly reduce the moiré. A useful relationship between halftoner memory locations and moiré phase angle zones in a full field image is determined. The moiré that occurs in a halftone image is quantified and moiré compensation values obtained are then used to generate an inverse moire amount which is used to compensate for the moiré.Type: GrantFiled: August 25, 2003Date of Patent: March 11, 2008Assignee: Xerox CorporationInventors: Douglas Curry, David Goldberg
-
Patent number: 7330600Abstract: A character area is extracted from an original image, which is a digital image, according to a feature value calculated with respect to the original image. Pixels belonging to the extracted character area are classified into a first class and a second class according to colors, in each of blocks divided from the original image. A black character color and a ground color on the original image are estimated according to the classification of the pixels belonging to the extracted character area into the first and second classes. A tone correction is performed to the original image according to the estimated black character color and the estimated ground color so as to adjust a contrast of the black character and the ground in an output image.Type: GrantFiled: August 28, 2003Date of Patent: February 12, 2008Assignee: Ricoh Company, Ltd.Inventor: Hirobumi Nishida
-
Patent number: 7262884Abstract: A white background determination section performs a white background determination on the basis of a white threshold calculated by a white threshold calculation section and an area size selected by an area size determination section. A character discrimination section executes character recognition such that a condition for character discrimination is relaxed when the white background determination section determines that a pixel of interest belongs to a white background, and the condition for character discrimination is made stricter in other cases.Type: GrantFiled: November 22, 2002Date of Patent: August 28, 2007Assignees: Kabushiki Kaisha Toshiba, Toshiba Tec Kabushiki KaishaInventor: Haruko Kawakami
-
Patent number: 7236643Abstract: In order to render information contained in images more detectable in the presence of noise, the present invention discloses a system and method to binarize the images in the presence of noise. The method of this invention comprises the steps of applying a dynamic range reducing filter to the digitized image values, obtaining a range reduced image; applying an edge detecting filter to the range reduced image, obtaining a filtered image; and then, adaptively binarizing the digitized image utilizing the corresponding filtered image to obtain an adaptive threshold.Type: GrantFiled: March 22, 2002Date of Patent: June 26, 2007Assignee: Lockheed Martin CorporationInventors: Lawrence E. Albertelli, David L. Ii, Nina Kung
-
Patent number: 7145693Abstract: In ink-jet printing apparatuses having a monochrome head which is longer than a color head, if a monochrome image is processed as a color image, the printing speed cannot be improved. Accordingly, the color attribute is determined by pixel based on a luminance signal indicating a color multivalue image, and the number of color attributes and the number of array attributes in a first line group are counted. Based on these count values, a parameter indicating an image characteristic of second line group including the first line group is calculated. The image attribute of the second line group is determined in correspondence with the respective count values and the parameter. Then, based on the results of determination about adjacent second line groups, the image attribute of third line group included in the second line groups is determined. Thus attribute determination can be appropriately performed in predetermined band units of image data.Type: GrantFiled: August 6, 2002Date of Patent: December 5, 2006Assignee: Canon Kabushiki KaishaInventor: Hidetsugu Kagawa
-
Patent number: 7142325Abstract: A document management device obtains thumbnail information as to a requested document out of an image transmitted via a public network, judges as to whether the thumbnail information is correct with respect to the requested document, and returns the requested document when correct. This prevents a person having no knowledge of the thumbnail information from obtaining a document from a device main body, thereby tightening security for document management in the main body and providing the document management device capable of fully managing even a document requiring higher security.Type: GrantFiled: December 5, 2000Date of Patent: November 28, 2006Assignee: Sharp Kabushiki KaishaInventor: Yoshinori Nagata
-
Patent number: 7139105Abstract: An image reading apparatus for optically reading an image comprises an LED for lighting a predetermined region including an object to be read, an image pickup element for receiving reflected light from the predetermined region lit by the LED and outputting an corresponding image pickup signal, a CPU for controlling an amount of light emitted by the LED in a predetermined range such that the image pickup signal output from the image pickup element is at the proper level, and a dark image pickup detecting circuit for determining a dark image pickup state on the basis of the image pickup signal output from the image pickup element. When the dark image pickup detecting circuit determines the dark image pickup state, the CPU controls an amount of light emitted by the LED to be low.Type: GrantFiled: December 3, 2001Date of Patent: November 21, 2006Assignee: Olympus Optical Co., Ltd.Inventor: Takeshi Mori
-
Patent number: 7062104Abstract: The ability of the visual system to detect contrast in an image is a function of the frequency of the contrasting pattern and the distortion of the image. The visual system is more sensitive to contrasting patterns of lower frequency. When the image is significantly distorted, the visual system is even more sensitive to lower frequencies than higher frequencies. An image encoder employs lossy data compression processes producing a distorted reconstructed image. A method of quantizing image data including the step of varying the magnitude of a quantization step as a function of the distortion of an image is disclosed for further visually optimizing image quantization. Another method utilizes distortion adaptive weighting to vary the limit of code block truncation during embedded bitstream coding to visually optimize image compression by increasing relative lossiness of compression at higher frequencies.Type: GrantFiled: October 2, 2003Date of Patent: June 13, 2006Assignee: Sharp Laboratories of America, Inc.Inventors: Wenjun Zeng, Shawmin Lei
-
Patent number: 7006703Abstract: An implementation of a technology, described herein, for facilitating the recognition of content of digital goods. At least one implementation, described herein, derives a probabilistic mirror distribution of a digital good (e.g., digital image or audio signal). It uses the resulting data to derive weighting factors (i.e., coefficients) for the digital good. Based, at least in part on such weighting factors, it determines statistics of the good and quantizes it. The scope of the present invention is pointed out in the appending claims.Type: GrantFiled: June 28, 2002Date of Patent: February 28, 2006Assignee: Microsoft CorporationInventors: Ramarathnam Venkatesan, Mark C. Johnson
-
Patent number: 7006692Abstract: An image processing apparatus, method and computer program product, wherein a luminance histogram of input image data is generated by the histogram generating section and a polarization degree of the luminance histogram is evaluated by the polarization degree evaluating section in order to determine whether the input image data is in a true backlight condition or in a halation condition. An optimum dynamic range correction and tone curve correction are performed on the input image data based on a result of the above-described determination.Type: GrantFiled: February 24, 2005Date of Patent: February 28, 2006Assignee: Ricoh Company, Ltd.Inventor: Yuki Matsushima
-
Patent number: 6987879Abstract: Characters or image portions are extracted from a background whose color is similar to that of the characters or the image portions. In order to chromatically isolate the characters and the image portions, a threshold value used for binarization is adjusted as the binarization is repeated as necessary or for a predetermined number of times. The adjusted threshold value allows the chromatic isolation of similar colors.Type: GrantFiled: May 18, 2000Date of Patent: January 17, 2006Assignee: Ricoh Co., Ltd.Inventor: Tooru Suino
-
Patent number: 6965696Abstract: An image processing device of the present invention is provided with four kinds of sub masks in total including two kinds in a main scanning direction and two kinds in a sub scanning direction, in a main mask constituted by a plurality of pixels including a target pixel. In the image display device, when determining a target pixel of an inputted image data, a difference in a total density of the two kinds of sub masks in a main scanning direction is added to a normalized difference in total density of the two kinds of sub masks in a sub scanning direction, and a resultant value is compared with a threshold value so as to determine if the target pixel is an edge area or not.Type: GrantFiled: October 6, 2000Date of Patent: November 15, 2005Assignee: Sharp Kabushiki KaishaInventors: Mitsuru Tokuyama, Masatsugu Nakamura, Mihoko Tanimura, Masaaki Ohtsuki, Norihide Yasuoka
-
Patent number: 6873731Abstract: The present invention concerns an image processing device and an image processing method for processing a decoded image, and its objective is to optimally binarize a decoded original. After the respective density histograms of colors R, G, and B have been drawn, the hierarchical relationship between the low-density-side peak value and high-density-side peak value is investigated. A color component which is to become a binarization object is determined based on the comparison results on the number of color components whose high-density-side peak value is/are higher and the number of color components whose low-density-side peak value is/are higher, and the color of the pixel to be outputted is determined based on the comparison of the pixel with a threshold value.Type: GrantFiled: February 7, 2001Date of Patent: March 29, 2005Assignee: Fujitsu LimitedInventors: Hiroyuki Takakura, Nobuyasu Yamaguchi, Kenichiro Sakai, Hirotaka Chiba, Tsugio Noda
-
Patent number: 6873729Abstract: An image processing apparatus, method and computer program product, wherein a luminance histogram of input image data is generated by the histogram generating section and a polarization degree of the luminance histogram is evaluated by the polarization degree evaluating section in order to determine whether the input image data is in a true backlight condition or in a halation condition. An optimum dynamic range correction and tone curve correction are performed on the input image data based on a result of the above-described determination.Type: GrantFiled: July 13, 2001Date of Patent: March 29, 2005Assignee: Ricoh Company, Ltd.Inventor: Yuki Matsushima
-
Patent number: 6822765Abstract: After a display on a display unit is changed to a copy stand by screen, until an operation regarding a copy function is performed by use of an operation unit, the apparatus status regarding a facsimile function and the apparatus status regarding the copy function are displayed on the copy stand by screen to be displayed on the display unit. After the operation regarding the copy function is performed by use of the operation unit, only the apparatus status regarding the copy function is displayed on the copy standby screen.Type: GrantFiled: November 16, 2000Date of Patent: November 23, 2004Assignee: Canon Kabushiki KaishaInventor: Seiji Ohmori
-
Patent number: 6751358Abstract: A system for simulating grayscales in a digital printer, such as an ink-jet printer, exploits a modified error diffusion technique. When a datum for a particular pixel in an image is 0, the datum is substituted with a low-level artificial datum such as 4 on a scale from 0 to 255. The addition of the artificial datum in the error diffusion algorithm avoids artifacts caused by the presence of large number of zeros in the error diffusion algorithm.Type: GrantFiled: June 21, 1999Date of Patent: June 15, 2004Assignee: Xerox CorporationInventors: David A. Mantell, James B. Kuwik
-
Patent number: 6744532Abstract: A method for enhancing printing quality to process the picture and textual data in an image properly such that both the picture and textual data can be clearly printed. The inventive method can treat the image data to be printed in a real time fashion and while the entire image data is not required. In the inventive method, the difference of gray level is reallocated by error diffusion method to render the edge more smooth and clear.Type: GrantFiled: August 31, 1999Date of Patent: June 1, 2004Assignee: Lite-On Technology CorporationInventor: Cheng Chong Chen
-
Patent number: 6721458Abstract: Adaptive filtering techniques for hardware or software implementation, which selectively use median and low-pass filters to reduce artifacts based on local document features, are disclosed. Specific techniques for low- and high-resolution documents are provided. A fast and memory efficient algorithm for computing the median on a 3×3 pixel neighborhood is also disclosed, and is used in the filtering technique for high-resolution documents.Type: GrantFiled: April 14, 2000Date of Patent: April 13, 2004Assignee: Seiko Epson CorporationInventor: Hakan Ancin
-
Patent number: 6714322Abstract: ROM stores an 8×8 base matrix of 64 sequential threshold values (1-64), hexadecimal data for a specified pattern to be rendered on an output image, and a threshold address table in which the thresholds of the base matrix are arranged in ascending order of threshold value. The MPU generates a second threshold matrix used to render the specified pattern when the matrix is used by dithering unit to dither a source image having a wide range of gray-scale levels.Type: GrantFiled: November 19, 1999Date of Patent: March 30, 2004Assignee: Murata Kikai Kabushiki KaishaInventor: Katsushi Minamino
-
Patent number: 6683702Abstract: A method of reproducing a document including halftoned regions therein scans the document to generate scanned image data comprising a digitized representation of said document. The scanned image data that corresponds to the halftoned regions is then rendered using a compact rendering process that includes positioning an observation window about a target pixel and a neighboring pixel; selecting a fill-order based upon a result of the analyzing step; and generating a high addressability pixel as a function of the selected fill-order.Type: GrantFiled: July 7, 1999Date of Patent: January 27, 2004Assignee: Xerox CorporationInventors: Robert P. Loce, Michael Branciforte, Yeqing Zhang, Leon C. Williams
-
Patent number: 6671071Abstract: A circuit for generating a threshold bias signal for processing n color separations representing a color image includes a threshold bias register which holds and outputs the current threshold bias signal.Type: GrantFiled: October 19, 1999Date of Patent: December 30, 2003Assignee: Xerox CorporationInventor: Doron Kletter
-
Patent number: 6661929Abstract: An imaging system that uses an array controller which is adapted to imaging arrays having black cells to control an imaging array not having black cells. The imaging system includes an array controller that is adapted to process a scan line that includes one or more black pixels. The imaging system includes an imaging array not having black cells that generates a series of pixel data samples in response to light from an image. The imaging system includes circuitry for generating the scan line by synthesizing the black level pixels and combining the black pixels with the series of pixel data samples.Type: GrantFiled: July 14, 1999Date of Patent: December 9, 2003Assignee: Hewlett-Packard Development Company, L.P.Inventor: Mark T. Smith
-
Patent number: 6625327Abstract: An image forming apparatus capable of solving problems in error diffusion method is provided. An input pixel value is thresholded using a corrected threshold value Th (x), and a binarized pixel value is output. The corrected threshold value Th (x) is subtracted from the output value, multiplied by a feed back coefficient &bgr;, and thereafter, the result is diffused to threshold values of pixels around the pixel of interest.Type: GrantFiled: September 20, 1999Date of Patent: September 23, 2003Assignee: Minolta Co., Ltd.Inventors: Seiji Ohshima, Toshitsugu Yamamoto
-
Patent number: 6608929Abstract: An image segmentation apparatus divides an image into plural regions according to feature quantities of pixels for composing the image, by a programmed computer. A divider divides the image into plural regions by using the separation degree of feature quantities of pixels for composing the image. A separation degree operator determines the separation of feature quantities between interior and exterior region, according to the dissimilarity of feature quantities of pixels for enclosing the boundary of plural regions divided by the divider. A changer changes the alienation degree of feature quantities of pixels enclosing the boundary between the interior and exterior region in a specific condition, by using the alienation degree of feature quantities between interior and exterior region calculated by the alienation degree operator. The divider divides the image into plural regions by using changed separation degree.Type: GrantFiled: May 26, 2000Date of Patent: August 19, 2003Assignee: Olympus Optical Co., Ltd.Inventor: Fumiyuki Shiratani
-
Patent number: 6597805Abstract: A visual inspecting method for an electronic device, comprising steps of: photographing an image of a surface of the electronic device; dividing the photographed image into a plurality of unit regions and obtaining a distribution of gradation levels for each unit region; subtracting a predetermined offset value from the gradation level of the highest frequency selected from the gradation levels for each unit region so as to obtain a binarization level for each unit region; interpolating the binarization levels for unit regions so as to obtain a binarization level at each coordination position of the photographed image; and comparing the gradation level at each coordination position of the photographed image with the binarization level at each coordination position and determining that a defect is present at a coordination position where the gradation level thereat is lower than the binarization level thereat.Type: GrantFiled: November 24, 1999Date of Patent: July 22, 2003Assignee: NEC CorporationInventor: Masahiko Nagao
-
Patent number: 6529629Abstract: A method and apparatus are provided for classifying image data. A neighborhood average gray value may be determined for the input image data. A threshold value may then be determined based on the neighborhood average gray value. Pixels are evaluated to determine if a gray level difference between the pixel and the neighborhood average gray level is greater than the threshold.Type: GrantFiled: September 23, 1998Date of Patent: March 4, 2003Assignee: Xerox CorporationInventors: Xing Li, Michael E. Meyers, Francis K. Tse
-
Patent number: 6466693Abstract: The present invention is an image processing apparatus comprising: dividing means for dividing an image signal obtained by scanning an original document into predetermined local blocks and output a predetermined including a target pixel; a binary coding processing section which converts the image signal in the predetermined block into binary code information; means for calculating each area (dimension) of the binary values; means for calculating number of times that the binary values are changed; a threshold processing section for performing threshold processing by properly and selectively using a threshold of the maximum density difference in the predetermined area, each area (dimension) value after binary coding and number of counts as a parameter; and a judgement processing section for judging the image signal in the predetermined area.Type: GrantFiled: May 27, 1999Date of Patent: October 15, 2002Assignee: Sharp Kabushiki KaishaInventors: Makoto Otsu, Yasushi Adachi, Toshihiro Kanata
-
Patent number: 6359702Abstract: Image data for a margin around the image area of a book form original can be erased and image data for a book center portion are obtained without loss. In a photograph mode, a low threshold value is set in first binary conversion means 4, and image data having been input are binary converted by using this value. Based on the image data having been converted, a first coercion signal generating unit 6 judges a margin around the original image. A high threshold value is set to second binary conversion means 5 and image data having been input are binary converted by using this value. Based on the image data having been converted, a second coercion signal generating unit 7 judges a margin around the original and a portion including a book center portion. A character processing binary conversion unit 3 carries out binary conversion on input image data for the portion within the original, and outputs whitening data which erase the margin around the original.Type: GrantFiled: May 12, 1998Date of Patent: March 19, 2002Assignee: Riso Kagaku CorporationInventors: Yukio Irie, Shinya Okada, Yoshiyuki Okada
-
Patent number: 6351566Abstract: A method for binarizing a gray-level input image including a plurality of pixels having respective gray-level values. A lower threshold and an upper threshold are determined. A first binary value is assigned to the pixels in the gray-level image having gray-level values above the upper threshold, and a second binary value is assigned to the pixels in the gray-level image having gray-level values below the lower threshold. The pixels in an intermediate group having gray-level values between the lower and upper thresholds are processed so as to determine optimal assignments of the pixels in the intermediate group to the first and second binary values.Type: GrantFiled: March 2, 2000Date of Patent: February 26, 2002Assignee: International Business MachinesInventor: Aviad Zlotnick
-
Patent number: 6333993Abstract: A method and device for an object detectable and background removal and storage media for storing program thereof enable automatic detection of an object to be executed minutely and high precisely for outline. A sectional image statistic calculation measure calculates a mean value and standard deviation of characteristic value of brightness and so forth of the sectional image with input image being subjected to division processing into sectional image. A background sectional image selection measure causes a sectional image whose standard deviation is the smallest value in the sectional images to be taken as the sectional image with high probability of including only the background. A background statistic estimation measure investigates the sectional image including only the background and another sectional image under the relationship between the mean value and the standard deviation.Type: GrantFiled: October 5, 1998Date of Patent: December 25, 2001Assignee: NEC CorporationInventor: Shizuo Sakamoto
-
Patent number: 6320981Abstract: Block representative values are set adaptively based on the feature amount concerning the distribution state of a prepared histogram of input image data. Thus, if block truncation coding is executed based on an input image having mixed CG image and scanned image areas, efficient coding can be performed and a high-quality decomposed image can be provided. Further, when the histogram is divided into image data groups, the image data groups can be again divided to provide a high-quality decomposed image, thus efficient coding can be performed and a high-quality decomposed image can be provided more reliably.Type: GrantFiled: August 18, 1998Date of Patent: November 20, 2001Assignee: Fuji Xerox Co., Ltd.Inventor: Shinichi Yada
-
Publication number: 20010028468Abstract: There is provided an image processing apparatus, operating as described below, employing an error distribution method to perform a halftone process intensively providing dots to achieve high resolution and a high level of tone representation simultaneously. The image processing apparatus, employing the error distribution method to convert an image represented by multiple values into an image provided in binary representation, employs a distribution weighting coefficient to distribute an error caused at a target pixel to a neighboring pixel. The distribution weighting coefficient simply decreases and ultimately attains zero as the distance from the target pixel increases, and the distance extending to attain zero is also set to vary with direction. Such a distribution weighting coefficient allows a halftone process providing dots intensively.Type: ApplicationFiled: March 27, 2001Publication date: October 11, 2001Applicant: Minolta Co., Ltd.Inventor: Toshitsugu Yamamoto
-
Patent number: 6285464Abstract: A half-tone image is produced by scanning a plurality of input points of an original, outputting a screened image having a plurality of black and white dots and transmitting signals representing the screened image to a marking device. The size of each plurality of dots is determined from a recursive relationship between a value of a current input point, a previous output and an error representing a difference between a value of a previous input point and the previous output.Type: GrantFiled: October 8, 1992Date of Patent: September 4, 2001Assignee: Canon Kabushiki KaishaInventors: Akihiro Katayama, Hidefumi Ohsawa, Akiko Fukuhara