Drop-out Color In Image (i.e., Color To Be Removed) Patents (Class 382/163)
-
Patent number: 7421126Abstract: A method of and system for identifying a target form for increased efficiency in an automated data capture process is described. Forms are scanned and stored as digitized images. Regions are defined on the form relative to corresponding reference points between the form and the digitized image. The regions are defined in areas that contain anticipated digitized data from data fields of the form. Digitized data is recognized through such means as optical character recognition (OCR) and the resulting string variable is compared in form to a plurality of formats expected for that data. Scoring systems are used to obtain a resultant score for a number of string variables which is compared to a predetermined confidence number. If said confidence number is reached, the form is flagged as a target form and used in the data capture process. A first step identification of certain graphical features can be added as an initial determination as to the source of the form.Type: GrantFiled: March 31, 2005Date of Patent: September 2, 2008Assignee: Cardiff Software, Inc.Inventor: Emily Ann Deere
-
Publication number: 20080205751Abstract: A method for removing unwanted form color content from a scanned document by segmenting the image into two or more tiles (14). Each tile (14) is classified into at least a first and second set according to its combination of background and color content. A background color is identified from the first set of tiles (14). At least one form color is identified from the second set of tiles. A transform is applied that shifts form color image data values toward background color data values.Type: ApplicationFiled: February 26, 2007Publication date: August 28, 2008Inventor: Gregory S. Mischler
-
Publication number: 20080205752Abstract: An image processor, includes: a gradation direction determination unit that determines a gradation direction existing in an image in which a color or density changes; a reference area setting unit that sets a shape of a reference area based on a determination result by the gradation direction determination unit; and a color estimation unit that estimates a color in which a non-target image superimposition does not occur based on a pixel value within the reference area set by the reference area setting unit and substitute an input pixel value with the estimated color.Type: ApplicationFiled: October 3, 2007Publication date: August 28, 2008Applicant: FUJI XEROX CO., LTD.Inventor: Atsushi Itoh
-
Patent number: 7415612Abstract: An image decrypting apparatus derives spectral reflectance of the face of an original on the basis of obtained original image data, built-in light source data and basis function data, and obtains weighted coefficients of each pixel as object color component data. The apparatus stores a file including the basis function data used at the time of obtaining the spectral reflectance as a key file, and stores a file including the object color component data as an encrypted file. From each of the key file and the encrypted file, the original image data cannot be reproduced. By using the key file and the encrypted file in a correct combination, the original image data can be reproduced. In such a manner, the original image data can be protected.Type: GrantFiled: May 1, 2003Date of Patent: August 19, 2008Assignee: Minolta Co., Ltd.Inventor: Fumiko Uchino
-
Patent number: 7400763Abstract: Methods and apparatus, including computer program products, for erasing in a digital image. A method includes identifying a plurality of tip regions on the image, establishing an erasure color, and completely erasing pixels in the tip region that have a color matching the erasure color. Pixels having partially matching colors are partially erased and color decontaminated.Type: GrantFiled: July 30, 2004Date of Patent: July 15, 2008Assignee: Adobe Systems IncorporatedInventor: Mark Hamburg
-
Publication number: 20080144892Abstract: Converting a digital image from color to gray-scale. In one example embodiment, a method for converting a digital image from color to gray-scale is disclosed. First, an unconverted pixel having red, green, and blue color channels is selected from the color digital image. Next, the red color channel of the pixel is multiplied by ?. Then, the green color channel of the pixel is multiplied by ?. Next, the blue color channel of the pixel is multiplied by ?. Then, the results of the three multiplication operations are added together to arrive at a gray-scale value for the pixel. Finally, these acts are repeated for each remaining unconverted pixel of the color digital image to arrive at a gray-scale digital image. In this example method, ?+?+?1 and ?>?.Type: ApplicationFiled: November 30, 2007Publication date: June 19, 2008Inventors: Juwei Lu, Mohanaraj Thiyagarajah, Hui Zhou
-
Patent number: 7382502Abstract: An image processing apparatus for recovering reading faults produced in time of scanning photographic film due to imperfections present on the film such as scratches, dust or stains. The apparatus comprises a defective pixel detecting unit (11) for detecting defective pixels influenced by the imperfections, an interpolating unit (12) for performing an interpolating process for the defective pixels to create corrected pixel values for the defective pixels, a standard deviation calculating unit (13) for calculating standard deviations of pixel values forming image data, and determining granularity of an input image based on the standard deviations, and a graininess adding unit (14) for adding a value obtained by multiplying the granularity by a random number to the corrected pixel values for each defective pixel.Type: GrantFiled: February 27, 2004Date of Patent: June 3, 2008Assignee: Noritsu Koki Co., Ltd.Inventor: Koji Kita
-
Patent number: 7375853Abstract: A separating unit determines, for an image data, whether there exists black data, and generates density data from the black data when the black data exists, and generates color data from data other than the black data. A multinarizing unit converts the color data into multinary data. A magnification varying unit varies the density data and the color data multinarized, using a cubic function convolution method. A binarizing unit binarizes the color data varied, based on a predetermined threshold. An image forming unit prints the color data binarized and the density data varied, onto a recording medium.Type: GrantFiled: September 12, 2003Date of Patent: May 20, 2008Assignee: Ricoh Company, LimitedInventor: Yukari Nozaki
-
Patent number: 7372469Abstract: The present invention provides a method for rotating YUV4:2:0 image in a digital display device, such as TV image system. A YUV4:2:0 image is separated to a Y division matrix and a U and V division matrix. Then the Y division is performed a rotation matrix calculation. And the U and V division matrix is performed a reverse rotation matrix calculation. A rotated YUV4:2:0 image is obtained by combining the processed Y division matrix and the processed U and V division matrix.Type: GrantFiled: April 12, 2006Date of Patent: May 13, 2008Assignee: Arcadyan Technology CorporationInventor: Ming-Te Chou
-
Patent number: 7369699Abstract: Methods and apparatuses for color image restoration and enhancement. In at least one embodiment, color signals for individual channels of an image (e.g., red, green, or blue) are adjusted based on a weighted set of averages (e.g., of the entire image, the center portion, the surrounding portion, or other portions). In one example, pixels with extreme values of color signals (e.g., pure black or white pixels) are ignored for the purposes of restoring color; and, the different averages are weighted according to the pixel location (e.g., the distance from the pixel to a center point). In one example, after color restoration for individual channels, the luminance of each pixel is adjusted back to their original levels; and the range of luminance of the image is further adjusted to provide improved brightness and contrast, where in determining the luminance the red, green and blue color channels are given an equal weight.Type: GrantFiled: August 29, 2003Date of Patent: May 6, 2008Assignee: Apple Inc.Inventor: Greg Christie
-
Patent number: 7359100Abstract: An image correction method of this invention includes a step of identifying a first pixel that satisfies one of predetermined conditions as to a pixel level, which are set for each color component, among pixels included in a specific image; a step of identifying a second pixel that satisfies the plural aforementioned predetermined conditions as to the pixel level, which are set for each color component, among pixels included in the specific image; a step of calculating an evaluation value relating to a duplication degree of the first pixel and the second pixel; and a correction step of correcting the specific image based on the evaluation value. As a result, it becomes possible to avoid a wrong correction for an object having the chromatic color, and an appropriate image correction is carried out.Type: GrantFiled: March 10, 2006Date of Patent: April 15, 2008Assignee: Fujitsu LimitedInventor: Masayoshi Shimizu
-
Patent number: 7355745Abstract: A document-to-printer color gamut matching system enables comparison of at least two color maps in a manner that allows selection of the printer that will result in the best print output. Information related to the document to be printed and information describing the color gamut(s) that each available printer is capable of printing is compared. Each color gamut is evaluated to determine suitability for use with the document. The document-to-printer gamut matching system may provide the author of the document with a number of candidate printers best matched to the printing of the document depending on the rendering intent of the author; may select a printer based on a measurement of best fit; or may generate a custom color map to result in a color gamut that is satisfactory.Type: GrantFiled: April 13, 2001Date of Patent: April 8, 2008Assignee: Hewlett PackardInventors: Kevin R. Hudson, Huanzhoa Zeng
-
Publication number: 20080069440Abstract: In general, this disclosure relates to processing techniques for processing images captured by an image capture device. More particularly, the techniques relate to automatic color removal in digitally captured images. In accordance with this disclosure, an image processing apparatus dynamically determines whether a color component of an image is likely to be considered important by a human viewer based on color information associated with the image, and removes at least a portion of the color component of the image during image processing when it is not likely to be considered important.Type: ApplicationFiled: September 20, 2006Publication date: March 20, 2008Applicant: QUALCOMM IncorporatedInventor: Babak Forutanpour
-
Patent number: 7345786Abstract: A method for color cast removal in a scanned image in L*a*b* space includes generating a first color cast correction curve for mapping L* to a first color correction, ?a*, (or ?b*) wherein the first correction curve provides a desired a* shift in midtone regions and is modulated as a function of L* such that black and white points are unaffected; for each pixel n in the scanned image, passing L*n through the first color cast correction curve for obtaining a value of ?a*n; and adding the value of ?a*n to the scanned image's original a*n component. To ensure that the color corrected a* remains within gamut, a second correction curve for applying a clipping factor to the mapped ?a* may be generated with the a*n passing through the second correction curve for obtaining a clipping factor Cn; and modifying the a*n value by Cn(?a*n).Type: GrantFiled: February 18, 2003Date of Patent: March 18, 2008Assignee: Xerox CorporationInventors: David E. Rumph, Charles M. Hains
-
Patent number: 7333653Abstract: Systems and methods of detecting and correcting redeye in an image are described. In one aspect, pixels of the input image are segmented based on projections of color values of the pixels onto two-dimensional thresholding planes. Candidate redeye pixel areas are identified in the input image based on the segmented pixels of the input image.Type: GrantFiled: August 29, 2003Date of Patent: February 19, 2008Assignee: Hewlett-Packard Development Company, L.P.Inventors: Huitao Luo, Jonathan Yen, Daniel Tretter
-
Publication number: 20080019588Abstract: An image sensor may selectively produce an effect, such as simulating a night vision scope, by controlling existing hardware to vary anti-vignetting and gamma.Type: ApplicationFiled: January 11, 2007Publication date: January 24, 2008Applicant: STMicroelectronics (Research & Development) LimitedInventor: James Kevan Gallagher
-
Publication number: 20070297668Abstract: An image-processing apparatus configured to perform a background-color-removal process on color image data. The image-processing apparatus includes a determination unit configured to determine whether a pixel value of the color image data is highlight information to be reproduced using a light color material, and also includes a processing unit configured to perform a background-color-removal process, using a highlight background color level, on a pixel having a pixel value determined by the determination unit to be the highlight information, and to perform a background-color-removal process, using a background color level that is lower in luminance than the highlight background color level, on a pixel having a pixel value determined not to be the highlight information.Type: ApplicationFiled: May 31, 2007Publication date: December 27, 2007Applicant: CANON KABUSHIKI KAISHAInventor: Masanori Matsuzaki
-
Patent number: 7307766Abstract: A method and apparatus for classifying an input image as black and white or color is described. The method calculates a first ratio of a color pixel portion to a total pixel portion in the input image. Next, the method calculates a second ratio of the color pixel portion to a combined pixel portion in the input image, where the combined pixel portion comprises the color pixel portion and a dark black and white pixel portion. Finally, the method returns an indication the input image is black and white if the first ratio is less than a first threshold and the second ratio is less than a second threshold.Type: GrantFiled: April 4, 2003Date of Patent: December 11, 2007Assignee: Good News Enterprises LimitedInventors: Hanqiang Huang, Yung-Kai Lai
-
Publication number: 20070273769Abstract: This invention can more accurately correct a region in the screen, which suffers a red-eye effect. An image processing apparatus including a processing circuit which executes correction processing for correcting a region in a target image, which satisfies a condition that defines a correction target, comprises a determination circuit which determines whether the target image has already undergone the correction processing, and a correction suppression circuit which suppresses execution of the correction processing for the target image when said determination circuit determines that the target image has already undergone the correction processing.Type: ApplicationFiled: March 8, 2007Publication date: November 29, 2007Applicant: CANON KABUSHIKI KAISHAInventor: Kenji Takahashi
-
Patent number: 7289664Abstract: The red eye detecting and correcting method detects red eye that occurred in an image during photographing and correcting the thus detected red eye to a specified color of pupil. Parameters employed in red eye detection and correction are altered in accordance with at least one of conditions as follows: type of the image, a camera model with which the image was recorded, a processing space for image data on the image, image processing steps to which the image is to be subjected before red eye detection and correction, format of the image, and scan condition.Type: GrantFiled: January 16, 2003Date of Patent: October 30, 2007Assignee: Fujifilm CorporationInventor: Jun Enomoto
-
Patent number: 7286702Abstract: A saturation detecting means (200) detects saturation at every pixel in a digital color image or at every coordinate point in an analog color image. A saturation conversion control means (300) determines the saturation conversion condition for the pixel or coordinate point based on the detected saturation. A saturation conversion processing means (400) implements saturation conversion in such a manner that saturation is reduced for the areas with low saturations in the color image, so as to enlarge the difference in saturation relative to the areas with high saturations, thus achieving improved saturation contrast. Further, the distribution of saturations in the input image is automatically extracted, so as to determine the threshold for deciding a saturation suppressed area based on the distribution of saturations. In this way, in order to obtain a color image improved in vividness and presenting feeling of sharpness, the saturation contrast is automatically improved.Type: GrantFiled: November 5, 2002Date of Patent: October 23, 2007Assignee: Sharp Kabushiki KaishaInventor: Akemi Oohara
-
Patent number: 7283665Abstract: A method of encoding data comprising: a) converting a first data set, representing pixels of a first image in an RGB format, to a second data set, representing pixels of the first image in an intensity-color format; b) discarding color data from the second data set to create a reduced second data set; c) converting a third data set, representing pixels of a second image in an RGB format, to a fourth data set, representing pixels of the second image in the intensity-color format; d) discarding color data from the fourth data set to create a reduced fourth data set; and e) combining the reduced second data set and the reduced fourth data set. A method of decoding to produce 3D image data and a method of decoding to produce 2D image data.Type: GrantFiled: April 15, 2003Date of Patent: October 16, 2007Assignee: Nokia CorporationInventor: Nobuyuki Suzuki
-
Patent number: 7245396Abstract: This invention has as its object to efficiently encode an image. To this end, for example, an image undergoes a color reduction process using a dither matrix with a predetermined size. A print control command is output. A compression parameter designation command that designates an up copy vertical offset value (a value according to the matrix size), a near left copy horizontal offset value (a value according to the matrix size), and a far left copy horizontal offset value (a value according to the period of background patterns), which are used in encoding, is output. Image data is encoded according to an encoding sequence.Type: GrantFiled: December 6, 2002Date of Patent: July 17, 2007Assignee: Canon Kabushiki KaishaInventor: Yoichi Sakamoto
-
Patent number: 7227990Abstract: The present invention provides a color image processing device and a color image processing method which is In order to perform natural and excellent sharpness processing to image data, the color image processing device of invention comprises: a color space converter (1) for converting image signals (RGB) to luminance signals (L), first chromaticity signals (C1) and second chromaticity signals (C2); a luminance signal correcting unit for correcting the luminance signal (L) of a target pixel based on an average luminance signal (LA) obtained from the luminance signals of the target pixel and predetermined pixels surrounding the target pixel and the saturation signal (S) of the target pixel; a chromaticity signal correcting unit for correcting the first chromaticity signal (C1) and the second chromaticity signal (C2) of the target pixel based on the first and second average chromaticity signals (C1A, C2A) obtained from the chromaticity signals of the target pixel and the predetermined pixels surrounding the tarType: GrantFiled: February 6, 2002Date of Patent: June 5, 2007Assignee: NEC CorporationInventor: Koichiro Hirao
-
Patent number: 7196817Abstract: A method for modifying an input digital image having an (x,y) array of image pixels, each image pixel having an input code value for each of four or more color channels, to produce a depleted digital image subject to a total colorant amount limit. The method includes determining depleted code values for each color channel such that the depleted code values produce substantially the input perceived color according to a device color model.Type: GrantFiled: December 12, 2002Date of Patent: March 27, 2007Assignee: Eastman Kodak CompanyInventors: Douglas W. Couwenhoven, Kevin E. Spaulding
-
Patent number: 7190485Abstract: A method for modifying an input digital image having an (x, y) array of pixels, each pixel having an input code value for one or more color channels, wherein said input code value has a nonlinear relationship to colorant amount, to form an output digital image containing output code values for each pixel subject to a total colorant amount limit.Type: GrantFiled: June 14, 2001Date of Patent: March 13, 2007Assignee: Eastman Kodak CompanyInventors: Douglas W. Couwenhoven, Kevin E. Spaulding, Rodney L. Miller
-
Patent number: 7190486Abstract: An image processing apparatus and an image processing method of the present invention improves image quality during monochrome output by adaptively executional conversion from a color image signal to a monochrome image signal during monochrome image output, and by using outputs from color and monochrome sensors at the same time. Moreover, it lowers the cost of compressing a color signal by using a color sensor with a lower resolution than that of the monochrome sensor.Type: GrantFiled: January 25, 2002Date of Patent: March 13, 2007Assignees: Kabushiki Kaisha Toshiba, Toshiba Tec Kabushiki KaishaInventors: Sunao Tabata, Hiroki Kanno
-
Patent number: 7177474Abstract: A method for converting video from a first format into a second format, the method including decoding into a series of frames video that is encoded in a first format, mapping the colors represented in the frames into a palette having fewer colors than the number of colors represented in the frames, removing noise from the frames, selectably removing at least one frame from the sequence, and re-encoding the sequence using the fewer colors into a second video format.Type: GrantFiled: November 10, 2004Date of Patent: February 13, 2007Assignee: Mobixell Networks Inc.Inventors: Yair Hougui, Vladislav Novikov
-
Patent number: 7147801Abstract: Disclosed is an ink composition suitable for ink jet printing comprising a luminescent compound, a solvent, and an energy active compound, and optionally a non-luminescent colorant. The energy active compound, when exposed to energy, generates one or more active species that can react with the luminescent compound to alter one or more of the characteristics of the luminescent compound. The luminescent compound can be colored or colorless. Also disclosed is a method for marking substrates comprising providing a mark comprising a luminescent compound and an energy active compound. Further disclosed is a jet ink composition suitable for printing on substrates authentication or security marks which can be rendered unreadable. The luminescence of the mark is quenched and the visible color is changed when irradiated with a light.Type: GrantFiled: March 12, 2004Date of Patent: December 12, 2006Assignee: Videojet Technologies Inc.Inventors: Michael Kozee, Steven D. Looman, John P. Folkers
-
Patent number: 7136522Abstract: Methods and apparatus for spectrally-encoding plural source images and for providing the spectrally-encoded plural source images in a composite image, for rendering the composite image in a physical form, or for recovering at least one of the encoded source images from the rendered composite image such that the recovered source image is made distinguishable. The rendered composite image may be subjected to a varying field of illumination, generated, for example, by a switched sequence of individually activated, differing illuminants. This sequenced array of illuminants causes a corresponding sequence of source images to be recovered in rapid succession, thus imparting a sense of change, such as motion, between or within the recovered source images.Type: GrantFiled: October 9, 2002Date of Patent: November 14, 2006Assignee: Xerox CorporationInventors: Steven J. Harrington, Robert P. Loce, Gaurav Sharma
-
Patent number: 7110595Abstract: Data containing at least a chroma component is obtained from an image data. Monochrome image data is generated from the chroma component image data. Which hue is to be output as it is specified, for example, by an operator. From the monochrome image data, the monochrome image data that corresponding to a portion of the colored image that has the specified hue is removed to obtain image eliminated data. The image eliminated data and the image data corresponding to a portion of the colored image that has the specified hue are combined to obtain an image processed data. The image processed data is converted into data that can be printed with a color printer.Type: GrantFiled: December 5, 2002Date of Patent: September 19, 2006Assignee: Ricoh Company, Ltd.Inventor: Yuuki Inoue
-
Patent number: 7110600Abstract: The invention relates to a document discriminating apparatus and a discriminating method for use in processing documents at financial institutions. A characteristic portion inherent in an optional format is cut out from image data read from a document in the optional format. Color constituents of the cut out image data are analyzed, and a color constituent exhibiting characteristics is selected from the constituents, and a color separation parameter is set for the selected color constituent. Data information is prepared which is related to the image data cut out based upon the color separation parameter. On the other hand, data information is prepared from image data obtained by reading a document to be discriminated based on the color separation parameter. Then, the data information is compared for determination with the data information stored in the document discriminating dictionary unit, whereby the document is discriminated.Type: GrantFiled: September 30, 1999Date of Patent: September 19, 2006Assignee: Fujitsu LimitedInventors: Takayuki Matsui, Yutaka Katsumata, Kazunori Yamamoto, Shinichi Eguchi
-
Patent number: 7085413Abstract: A method and apparatus for processing an input image to remove background color from the input image is described. The method includes the step of creating a histogram to calculate a dominant color of the input image. Next, the method determines if a threshold luminance is less than a luminance of the dominant color. If so, the method sets the output space values for RGB entries in a CMS table that match the dominant color to white. Finally, the method converts the input image to an output image by referencing the updated CMS table.Type: GrantFiled: April 4, 2003Date of Patent: August 1, 2006Assignee: Good News Enterprises LimitedInventors: Hanqiang Huang, Yung-Kai Lai
-
Patent number: 7054031Abstract: A method of color printing is described in which only two transparent inks are used to reproduce a source image The original digitally encoded image in red, green and blue colors may be initially adjusted for contrast, brightness, color balance, and tonal value. This is then converted to cyan, magenta and yellow encoding. The two of these channels which best represent the dominant colors of original image are then selected. The critical colors of the original image to be reproduced with reasonable accuracy are determined and spot colors that best represent these are selected from an ink palette The spot colors are assigned to the selected channels to which they have the closest color relationship. These two channels are next superimposed to form a composite image and their greyscale values are adjusted to produce an image most closely resembling the desired final image. New positive separations are then made and inverted to negative images from which printing plates can be prepared.Type: GrantFiled: June 22, 2001Date of Patent: May 30, 2006Assignee: Weyerhaeuser CompanyInventors: David L. Lee, Hugh West
-
Patent number: 7038702Abstract: A frame memory 105 stores the original image data received from a higher-level device 102 via an interface 103. Color reduction processing means receives color reduction rate data through a transfer from an upper-level device 102 or manual setting means such as a switch or jumper settings. Based on this color reduction rate data, the number of colors in the gradation data of the original image is reduced, and the color count of the original image is simulated using the reduced color count. Also included are a timing generating circuit 106 and a gradation voltage generating circuit 107. A gradation voltage selector 108 performs a partial halting of driver operations based on the color reduction rate.Type: GrantFiled: February 25, 2003Date of Patent: May 2, 2006Assignee: Renesas Technology Corp.Inventors: Yasuyuki Kudo, Akihito Akai, Kazuo Okado, Toshimitsu Matsudo, Atsuhiro Higa
-
Patent number: 7020328Abstract: A method for electronic color dropout utilizing spatial context to enhance accuracy comprises scanning a document to produce a color digital image. A thresholding apparatus is applied to the color digital image to produce a bitonal image. A region of the color digital image is selected corresponding to a feature of the bitonal image. An average color for the region is computed and compared to a predetermined dropout color. If the average color matches the predetermined dropout color, the region is erased from the bitonal image. Once it is determined that all features of the bitonal image have been examined, the process is complete. If all the features of the bitonal image have not been examined a region of the color digital image is selected corresponding to a feature of the bitonal image.Type: GrantFiled: September 4, 2002Date of Patent: March 28, 2006Assignee: Eastman Kodak CompanyInventor: Mark A. Barton
-
Patent number: 6972869Abstract: A method for mapping a color specification to colorant amounts when a first and a second colorant have a similar hue involves the division of portions of color space into regions. Colors of the similar hue are rendered with a first colorant, a second colorant or a blend of the first and second colorants depending on which region of a color specification space the color specification is related. An image processor operative to map color descriptions via the method includes a colorant splitters operative to map a color description to colorant amounts for colorants of similar hue. In a xerographic environment, such an image processor includes a xerographic printer.Type: GrantFiled: December 18, 2000Date of Patent: December 6, 2005Assignee: Xerox CorporationInventor: Steven J. Harrington
-
Patent number: 6970271Abstract: The invention provides a method and computer program of instructions for specifying a device independent trap color in a color space for a color boundary. The method includes obtaining a first color value (C1), representing a first color in a color space associated with the color boundary, having a first darkness and first chromaticity and obtaining a second color value (C2), representing a second color in the color space associated with the color boundary, having a second darkness and second chromaticity. The method includes generating a trap color value, representing a color in the color space, having substantially a same darkness as a lighter of the first and second color value, and a chromaticity that is a function of the first and second chromaticities of the first and second color values.Type: GrantFiled: August 3, 2001Date of Patent: November 29, 2005Assignee: Adobe Systems IncorporatedInventors: James J. Estrada, John P. Felleman
-
Patent number: 6956964Abstract: An apparatus is provided to produce a real-time anaglyph, comprising a graphics engine, a memory and an anaglyph generator. The graphics engine provides a sync signal and generates a left eye image and a right eye image in accordance with a horizontal offset calculated from a 3D graphic animation, wherein the horizontal offset between the left and the right eye images creates illusion of depth. The left eye image and the right eye image are temporarily stored in the memory. The anaglyph generator then fetches the left eye image and the right eye image from the memory in response to the sync signal, for producing a filtered left image and a filtered right image. As such, each filtered image is respectively tinted with one of the complementary colors. By viewing through a pair of anaglyph glasses, the filtered left and the filtered right images can thus create perception of depth.Type: GrantFiled: November 8, 2001Date of Patent: October 18, 2005Assignee: Silicon Intergrated Systems Corp.Inventors: Ruen-Rone Lee, Hsi-Jou Deng, Chin Sung Lee
-
Patent number: 6950553Abstract: The invention is a method of and system for identifying a target form for increased efficiency in an automated data capture process. Forms are scanned and stored as digitized images. Regions are defined on the form relative to corresponding reference points between the form and the digitized image. The regions are defined in areas that contain anticipated digitized data from data fields of the form. Digitized data is recognized through such means as optical character recognition (OCR) and the resulting string variable is compared in form to a plurality of formats expected for that data. Scoring systems are used to attain a resultant score for a number of string variables which is compared to a predetermined confidence number. If said confidence number is reached, the form is flagged as a target form and used in the data capture process. A first step identification of certain graphical features can be added as an initial determination as to the source of the form.Type: GrantFiled: September 7, 2000Date of Patent: September 27, 2005Assignee: Cardiff Software, Inc.Inventor: Emily Ann Deere
-
Patent number: 6937744Abstract: The present invention is embodied in a system and process for automatically learning a reliable color-based tracking system. The tracking system is learned by using information produced by an initial object model in combination with an initial tracking function to probabilistically determine the configuration of one or more target objects in a temporal sequence of images, and a data acquisition function for gathering observations relating to color in each image. The observations gathered by the data acquisition function include information that is relevant to parameters desired for a final color-based object model. A learning function then uses probabilistic methods to determine conditional probabilistic relationships between the observations and probabilistic target configuration information to learn a color-based object model automatically tailored to specific target objects.Type: GrantFiled: June 13, 2000Date of Patent: August 30, 2005Assignee: Microsoft CorporationInventor: Kentaro Toyama
-
Patent number: 6873728Abstract: A vertical black line removal system (VBLR) is adapted to remove unwanted vertical lines produced on scanned document images by dust or other particles on the imaging apparatus. The VBLR system, placed in a document scanner after the binarization equipment, creates a stored histogram table including the difference values of “1” or “0” for the first and second image data. A vertical black line search processor compares each histogram value in the histogram table with a predetermined threshold value such that when the histogram value is greater than the threshold value the histogram value and the image address indicating the location of defect are stored in memory.Type: GrantFiled: January 16, 2002Date of Patent: March 29, 2005Assignee: Eastman Kodak CompanyInventors: Lawrence J. Bernstein, Yongchun Lee
-
Patent number: 6839151Abstract: A system and method of processing an image including black text data and non-black text data are described. The system and method use a parametric analysis for discrimination of halftones, texts, and photographs. The parametric analysis provides results that track measurable image metrics without the inherent risk of errant decision making during classification. The creation of symbolic representations is intrinsically a classification process that is subject to error. It represents a fundamental departure from fuzzy logic image segmentation. In the parametric analysis, no pattern matching, no auto-correlation, no screening parameter calculation, and no conventional edge detector (such as a high pass filter) are used.Type: GrantFiled: February 2, 2000Date of Patent: January 4, 2005Assignee: Zoran CorporationInventors: Fred Andree, Steve Pratt, Shenbo Yu, Craig Cook
-
Patent number: 6823081Abstract: A method for performing color dropout on a digitized document, the method comprises the steps of obtaining color values from the digitized document for background and a color of interest to a user; transforming the color values of the background and the color of interest into an identical gray scale value according to a color dropout function; obtaining a gray scale value different from the identical gray scale value for the remaining portion of the image according to the color dropout function; and thresholding the gray scale values obtained from the previous steps to obtain a binary image that substantially eliminates color classification error which retains character integrity by a functional transformation that suppresses color fringe artifacts.Type: GrantFiled: April 30, 2001Date of Patent: November 23, 2004Assignee: Eastman Kodak CompanyInventors: Yongchun Lee, George O. Simmons
-
Patent number: 6816289Abstract: The present invention relates to an effect color extracting method of an image and an image original color recovering method which are capable of automatically extracting an effect color of an image pictured in accordance with an environment of a certain illumination and a color lens (or filter) and a feature of a camera, adjusting the extracted effect color and recovering an original image color of the image for thereby enhancing a performance of an image search.Type: GrantFiled: February 3, 2000Date of Patent: November 9, 2004Assignee: LG Electronics Inc.Inventors: Hyeon Jun Kim, Jin Soo Lee
-
Patent number: 6813381Abstract: In the document identification apparatus, a ruled line feature extraction section determines a black pixel ratio of a document to be identified, and adds the black pixel ratio for each block to extract a ruled line feature. A ruled line feature verification section verifies the ruled line feature with a ruled line feature already registered in a ruled line feature dictionary to thereby identify the document. If identification is not possible with this procedure, a details judgment section verifies the image data in a specific area with the image data (characters or the like) registered in a specific area dictionary.Type: GrantFiled: March 19, 2001Date of Patent: November 2, 2004Assignee: Glory Ltd.Inventors: Masatoshi Ohnishi, Hirofumi Kameyama
-
Patent number: 6791573Abstract: Methods and apparatus, including computer program products, for erasing in a digital image. A method includes identifying a plurality of tip regions on the image, establishing an erasure color, and completely erasing pixels in the tip region that have a color matching the erasure color. Pixels having partially matching colors are partially erased and color decontaminated.Type: GrantFiled: June 4, 2002Date of Patent: September 14, 2004Assignee: Adobe Systems IncorporatedInventor: Mark Hamburg
-
Patent number: 6788812Abstract: By automatically compensating for unwanted lighting effects caused by varying ambient light sources, digital still images and video are made to appear more naturally realistic. A set of correction factors based upon an ascertained ambient lighting conditions, such as color temperature, provides for selectively color correcting only those pixels requiring correction. In this way, only those portions of a digital image having excessive color due to ambient light conditions are improved without affecting those portions of the digital image not requiring correction.Type: GrantFiled: September 21, 1999Date of Patent: September 7, 2004Assignee: Eastman Kodak CompanyInventor: David C. Wilkins
-
Patent number: 6763122Abstract: Colored images are divided into color planes and watermarks are inserted into the individual color planes. One or more watermarks can be inserted into one or more of the color planes. In order to print a color image the image is divided into color planes corresponding to the colors of ink used for printing. A separate plate is used to print each color. The different plates must be precisely aligned. Any misalignment will cause blurring in the image and may make it difficult or impossible to read a watermark in the image. Misalignment of the plates can cause the watermark data in one color plane to, in effect, cancel out the watermark data in a different color plane. With the present invention a watermark is inserted into a selected color plane only, thus there is no cancellation due to misalignment of color plates. The watermark detection and reading can be done after the image is divided into color planes.Type: GrantFiled: October 23, 2000Date of Patent: July 13, 2004Inventors: Tony Rodriguez, Ammon Gustafson, Marc Miller, Alastair M. Reed, Geoffrey B. Rhoads
-
Patent number: 6763144Abstract: Method and apparatus for performing halftoning of an image, using two 2-dimensional look up tables (LUTS). The first LUT receives coordinates of an image value and outputs a screen reference value which then serves, together with the image value as address for the second LUT. The output of the second LUT is the halftone value.Type: GrantFiled: June 1, 2000Date of Patent: July 13, 2004Assignee: Creo IL, Ltd.Inventor: Moshe Gershony