Drop-out Color In Image (i.e., Color To Be Removed) Patents (Class 382/163)
-
Patent number: 8014599Abstract: A color processing device performs a quantitative evaluation not influenced by the experience and sensitivity of a user, upon adjustment of a profile. The adjustment of first conversion data for converting device independent data included in a profile describing characteristics of a device into device dependent data is achieved by inputting sample data, which is the device independent data, converting the sample data into the device dependent data using the first conversion data, converting the converted device dependent data into the device independent data using second conversion data which is conversion data included in the profile and which is conversion data for converting the device dependent data into the device independent data, and calculating the color difference between the sample data and the device independent data.Type: GrantFiled: January 17, 2008Date of Patent: September 6, 2011Assignee: Canon Kabushiki KaishaInventors: Manabu Ohga, Kenichi Naito, Hayato Kubo
-
Patent number: 8004718Abstract: Image data representing an image is obtained, raster image processing is performed on the image data, and then trapping is performed on the image data after raster image processing. The trapping may be performed based on a tag plane generated during the raster image processing, or the determination of which pixels to trap may be performed after the raster image processing.Type: GrantFiled: January 12, 2009Date of Patent: August 23, 2011Assignee: Xerox CorporationInventors: Michael C. Lacagnina, Guo-Yau Lin
-
Patent number: 7999978Abstract: The matrix coefficient determining process of the present invention can determine linear matrix and color-difference matrix coefficients appropriate for a given type of light source at the same time. The coefficients can be used to perform color correction of RAW data to ensure good color reproduction. Furthermore, by performing the matrix coefficient determining process for a number of types of light sources, optimum color reproduction coefficients and for each of the light sources can be obtained.Type: GrantFiled: October 27, 2005Date of Patent: August 16, 2011Assignee: Fujifilm CorporationInventors: Tomokazu Nakamura, Makoto Oishi
-
Publication number: 20110182503Abstract: A method performed by a software process executing on a computer system, includes accessing a digital image having a plurality of pixels encoded in a color space that defines hue as a pair of Cartesian coordinates. The method also includes calculating a chroma value for a specified pixel by determining a distance between a point corresponding to a hue coordinate pair value for the specified pixel and a Cartesian origin point. The calculated chroma value is compared to a predetermined threshold and an image processing operation is performed on the digital image based on a result of the comparison.Type: ApplicationFiled: January 25, 2010Publication date: July 28, 2011Applicant: APPLE INC.Inventor: Robert Mikio Free
-
Patent number: 7986447Abstract: A color image scanning system, method and medium that generates look-up tables for color data correction based on the type of printing paper and the kind of image on the printing papers, thereby improving color reproducibility upon scanning. A color image scanning system may include a storage unit to store look-up tables having correction values of first color data, obtained by scanning a first printing paper having a plurality of color patches, each of the look-up tables corresponding to a type of printing paper, and a final image generation unit to correct second color data, obtained by scanning a second printing paper, with reference to a look-up table of the look-up tables, the look-up table corresponding to the type of printing paper used by the second printing paper.Type: GrantFiled: September 13, 2007Date of Patent: July 26, 2011Assignee: Samsung Electronics Co., Ltd.Inventors: Yousun Bang, Min-ki Cho, Se-eun Kim, Heui-keun Choh
-
Publication number: 20110176726Abstract: Provided are a color to grayscale image conversion method of converting a color image into a grayscale image while maintaining original features of the color image, and a recording medium storing a program for performing the same. When an original color image is input, a target gradient with the features of the input original color image is acquired, and a global mapping function for converting the original color image into a grayscale image is determined based on the acquired target gradient. Thereafter, the original color image is converted into a grayscale image using the determined global mapping function. Therefore, it is possible to quickly convert a color image into a grayscale image, and to acquire a high-quality grayscale image with features of color difference included in the original color image.Type: ApplicationFiled: December 29, 2009Publication date: July 21, 2011Applicant: POSTECH ACADEMY - INDUSTRY FOUNDATIONInventors: Seung-Yong Lee, Yong-Jin Kim, Cheol-Hun Jang
-
Publication number: 20110158514Abstract: A method for removing color fringe is presented. Separated luminance and chrominance (YCbCr) signals of a digital image are analyzed through specific color detection, luminance detection, and gradient color detection, so as to determine whether color fringe occurs to each pixel in the digital image, thereby correcting pixels with color fringe.Type: ApplicationFiled: April 26, 2010Publication date: June 30, 2011Applicant: ALTEK CORPORATIONInventors: Che Lun Chuang, Chung Ta Wu
-
Publication number: 20110158515Abstract: A method for removing color fringe is presented. First, detection and correction of color fringe are performed on an original-size image and a small-size image respectively, so as to generate respective corrected images and corresponding color fringe maps. Then, the corrected small-size image and its corresponding color fringe map are enlarged to the same resolution as the original-size image. Finally, the two corrected images are blended according to the respective corresponding color fringe maps.Type: ApplicationFiled: April 26, 2010Publication date: June 30, 2011Applicant: ALTEK CORPORATIONInventors: Che-Lun Chuang, Chung-Ta Wu
-
Patent number: 7961941Abstract: Dropping out of color form backgrounds from images of completed forms to obtain color form dropout images retaining only the respondent information. In one embodiment, a color form image processing method (100) includes retrieving (102) a template image, retrieving (104) a respondent image, registering (106) the images against one another to establish correspondence between pixels in the respondent and template images, dilating (108) the template image, and performing (110) a color form dropout including comparing (112) corresponding pixels in the respondent and dilated template images, and determining (114) whether to keep corresponding pixels by applying (116) a geometric solid threshold comparison to assess both color similarity and relative darkness, and removing (118) pixels from the respondent image based on such comparison.Type: GrantFiled: March 26, 2010Date of Patent: June 14, 2011Assignee: Lockheed Martin CorporationInventors: Timothy O. Withum, Kurt P. Kopchik, Frederic Highland, Supreeth Hebbal, Summer C. Dasch, Stephanie M. Graham
-
Patent number: 7949180Abstract: A computer readable medium stores a program causing a computer to execute image process, wherein the image process includes accepting image information, accepting a searching condition, specifying colored regions in an image produced by the image information, searching the specified regions for a region satisfying the searching condition, and outputting information on the region satisfying the searching condition.Type: GrantFiled: April 6, 2007Date of Patent: May 24, 2011Assignee: Fuji Xerox Co., Ltd.Inventors: Aki Maeda, Yasuaki Mitobe, Fumio Takatani, Kazuya Hashimoto, Kazunori Kurokawa
-
Patent number: 7940988Abstract: Properties of pixels in a digital image are sampled within different subdivisions of an editing tool impression to produce different property distributions. The different subdivisions can automatically alter their size, geometry, and/or location, based on image content within one or more of the subdivisions, in order to encompass a set of pixels having a substantially uniform distribution of a pixel property. Uniformity can be defined relative to the editing operation or context of the image. The property distributions from each region are classified to identify different edit classes within the property space, which are then used to apply an edit effect to the digital image within the tool impression. The edit classes may be represented by an edit profile in two or more dimensions.Type: GrantFiled: October 26, 2009Date of Patent: May 10, 2011Assignee: Corel CorporationInventors: Krzysztof Antoni Zaklika, Mikhail Ivanovich Trifonov, Leonid Borisovich Lalyko
-
Publication number: 20110102823Abstract: An image processing apparatus carries out a combining process in which a part of an original image is whitened and a target image to be combined is superimposed over the whitened part. The image processing apparatus receives a command to specify a color of an unnecessary region of the stamp image including the target image to be combined which region is not to be superimposed over the original image in the combining process. Then, the image processing apparatus receives a command to define a necessary region of a specified color region of the stamp image which necessary region should not be defined as the unnecessary region, the specified color region being constituted by pixels indicating the color specified by the command.Type: ApplicationFiled: November 1, 2010Publication date: May 5, 2011Inventor: Kenji ONOGI
-
Patent number: 7936375Abstract: An image processor for lowering data transfer speed. A JPEG compression circuit performs two-dimensional compression process on data output from a YCbCr conversion circuit to generate compressed image data. A timing signal generator changes the frequency of a transfer clock signal in accordance with the compressed image data. An output circuit outputs the compressed image data in accordance with the transfer clock signal.Type: GrantFiled: February 27, 2006Date of Patent: May 3, 2011Assignee: Fujitsu Semiconductor LimitedInventor: Kiichiro Iga
-
Publication number: 20110091100Abstract: An image processing method and apparatus is provided, with which a size of a filter window may be decreased by determining an edge direction of each of the pixels constituting an image and by vertically applying an anisotropic filter window to the determined edge direction.Type: ApplicationFiled: August 20, 2010Publication date: April 21, 2011Applicant: SAMSUNG ELECTRONICS CO., LTD.Inventors: Ho Jin LEE, Young Su MOON, Shi Hwa LEE
-
Patent number: 7929807Abstract: The invention relates to a method for reducing the pixel resolution of a digital image by binning pixels together to form macro pixels. The digital image comprises pixels arranged in a color mask of at least three different colors. The color mask can be a Bayer mask comprising one red pixel, two green pixels and one blue pixel. The pixel binning method comprises selecting a number of pixels of each color. For example, in order to obtain a factor two resolution reduction, four red pixels can be binned for generating a red macro pixel and eight green pixels can be binned for generating two green macro pixels. By selecting for example only one blue pixel and using that pixel for generating a blue macro pixel the optical centers of the macro pixels will be evenly distributed over the image.Type: GrantFiled: February 27, 2007Date of Patent: April 19, 2011Assignee: Phase One A/SInventor: Thomas Andersen
-
Patent number: 7924284Abstract: A process for rendering highlighter ink strokes and non-highlighter ink strokes in a non-rastering environment is described. Strokes may be grouped under a node having a predefined opacity. The strokes inherit the opacity from the node. Additionally, visuals containing highlighter strokes of the same color are grouped into collections of visuals (one collection per each highlighter color), and change the opacity of the collection (parent) visual to semi-transparent (or any other transparency value defined for the highlighter effect).Type: GrantFiled: August 29, 2005Date of Patent: April 12, 2011Assignee: Microsoft CorporationInventors: Brian J. Ewanchuk, Koji Kato, Stefan Wick, Vladimir V. Smirnov, Sam J. George, Shawn Van Ness
-
Publication number: 20110074975Abstract: A method of filtering a red-eye phenomenon from an acquired digital image including a multiplicity of pixels indicative of color, the pixels forming various shapes of the image, includes analyzing meta-data information, determining one or more regions within the digital image suspected as including red eye artifact, and determining, based at least in part on the meta-data analysis, whether the regions are actual red eye artifact. The meta-data information may include information describing conditions under which the image was acquired, captured and/or digitized, acquisition device-specific information, and film information.Type: ApplicationFiled: December 1, 2010Publication date: March 31, 2011Applicant: TESSERA TECHNOLOGIES IRELAND LIMITEDInventors: Michael J. DeLuca, Yury Prilutsky, Eran Steinberg, Peter Corcoran, Petronel Bigioi, Alexei Pososin
-
Publication number: 20110074985Abstract: A method for digital image eye artifact detection and correction include identifying one or more candidate red-eye defect regions in an acquired image. For one or more candidate red-eye regions, a seed pixels and/or a region of pixels having a high intensity value in the vicinity of the candidate red-eye region is identified. The shape, roundness or other eye-related characteristic of a combined hybrid region including the candidate red-eye region and the region of high intensity pixels is analyzed. Based on the analysis of the eye-related characteristic of the combined hybrid region, it is determined whether to apply flash artifact correction, including red eye correction of the candidate red-eye region and/or correction of the region of high intensity pixels.Type: ApplicationFiled: December 4, 2010Publication date: March 31, 2011Applicant: TESSERA TECHNOLOGIES IRELAND LIMITEDInventors: Mihai Ciuc, Adrian Capata, Florin Nanu, Eran Steinberg, Peter Corcoran
-
Patent number: 7903869Abstract: 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: GrantFiled: September 20, 2006Date of Patent: March 8, 2011Assignee: Qualcomm IncorporatedInventor: Babak Forutanpour
-
Patent number: 7903872Abstract: 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: GrantFiled: May 31, 2007Date of Patent: March 8, 2011Assignee: Canon Kabushiki KaishaInventor: Masanori Matsuzaki
-
Publication number: 20110038533Abstract: An image processing apparatus includes a definition reducing section, a color region extracting section, a concealing image generating section and an image combining section. The definition reducing section, based on a received image, generates an image having a lower definition than the received image. The color region extracting section extracts a color region from the low definition image generated by the definition reducing section. The concealing image generating section, based on the color region extracted by the color region extracting section, converts the color region into a concealing region for concealing a part of the received image and, generates a concealing image including the concealing region. The image combining section combines the received image with the concealing image generated by the concealing image generating section.Type: ApplicationFiled: March 16, 2010Publication date: February 17, 2011Applicant: FUJI XEROX CO., LTD.Inventor: Teruka SAITO
-
Publication number: 20110038534Abstract: A method of and a system for finding similarities between major boundaries of images using a wavelet detector is described herein. Unimportant edges of the image are disregarded by eliminating Gaussian wavelet coefficients and Haar wavelet coefficients of lower significance. Comparison between the images is made on the basis of quantized color, sign and magnitude of the Haar wavelet coefficients. The method performs the comparison between images in two steps. First, the method checks for exact matches between the Haar wavelet coefficients to determine whether the images are very similar. This is followed by binning of the coefficients into nine spatial bins in the image. A representative is assigned to each of the bins in terms of color, orientation and sign. Each bin of one image is compared with all the bins of the other image. Thus, images that are similar but not identical are still detected.Type: ApplicationFiled: October 25, 2010Publication date: February 17, 2011Applicants: SONY CORPORATION, SONY ELECTRONICS INC.Inventor: Hawley Rising
-
Publication number: 20110019910Abstract: An image processing system capable of reducing an operation time required to generate a high image quality image, includes an image obtaining section that obtains an input image having been captured; a characteristic region information obtaining section that obtains information indicating a characteristic region in the input image; a model storage section that stores a model representing an object by a character parameter; an image generating section that converts an image of an object included in the characteristic region in the input image into a high image quality image having an image quality higher than an image quality of the input image, by adapting the image of the object included in the characteristic region in the input image to the model; and an output section that outputs an image including the high image quality image and an image other than the characteristic region.Type: ApplicationFiled: October 6, 2010Publication date: January 27, 2011Applicant: FUJIFILM CORPORATIONInventor: Hirokazu KAMEYAMA
-
Patent number: 7869088Abstract: Methods and apparatus for determining a preferred size for a Link LUT as used in conversion from an input color space defined by an input ICC profile into an output color space defined by an output ICC profile. The Link LUT may be incorporated within a device link structure as generally defined in the ICC specification or within a Link Color Conversion CMR in an AFP architecture system. The preferred size is determined from the size of an input LUT associated with the input ICC profile and the size of an output LUT associated with the output ICC profile. In AFP architecture systems, the input and output LUTs and profiles may each be incorporated in appropriate Color Conversion CMRs. The preferred size is determined as a reduced size that requires less computation to generate but does not cause loss of accuracy in conversion between the input and output color spaces.Type: GrantFiled: December 28, 2007Date of Patent: January 11, 2011Assignee: Infoprint Solutions Company, LLCInventor: Yue Qiao
-
Publication number: 20110001842Abstract: A method suitable for processing a digital image is disclosed. The method comprises, for each picture element of the digital image, processing an achromatic intensity level of the picture element using a first adaptation procedure featuring a first effective saturation function of the achromatic intensity, to provide a first intermediate intensity level. The method further comprises processing the achromatic intensity level using a second adaptation procedure featuring a second effective saturation function of the achromatic intensity, to provide a second intermediate intensity level. The method further comprises combining the first and the second intermediate intensity levels to provide a new achromatic intensity level associated with the picture-element.Type: ApplicationFiled: December 15, 2008Publication date: January 6, 2011Applicant: Ramot At Tel Aviv University LtdInventors: Hedva Spitzer, Yossi Yatir
-
Patent number: 7864364Abstract: A color transformation method which accounts for colorant interactions includes establishing a plurality of tone reproduction curves (TRCs), for one or more of the color separations forming a digital image. Each TRC accounts for colorant interactions between a primary colorant with which the first color separation is to be rendered and at least one secondary colorant with which at least a second of the plurality of color separations is to be rendered. The TRCs include input values and their corresponding modified input values. In a given TRC, the input values of the second and optionally other color separations are fixed. For a pixel of the digital image having a given input values for the first and second color separation one or more of the TRCs are selected which bound the fixed input value for the second color separation and a modified input value is determined therefrom.Type: GrantFiled: August 9, 2005Date of Patent: January 4, 2011Assignee: Xerox CorporationInventors: Yeqing Zhang, Robert P. Loce, Raja Bala
-
Patent number: 7860306Abstract: The present invention presents a framework for separating specular and diffuse reflection components in images and videos. Each pixel of the an M-channel input image illuminated by N light sources is linearly transformed into a new color space having (M?N) channels. For an RGB image with one light source, the new color space has two color channels (U,V) that are free of specularities and a third channel (S) that contains both specular and diffuse components. When used with multiple light sources, the transformation may be used to produce a specular invariant image. A diffuse RGB image can be obtained by applying a non-linear partial differential equation to an RGB image to iteratively erode the specular component at each pixel. An optional third dimension of time may be added for processing video images. After the specular and diffuse components are separated, dichromatic editing may be used to independently process the diffuse and the specular components to add or suppress visual effects.Type: GrantFiled: February 12, 2010Date of Patent: December 28, 2010Assignee: The Regents of the University of CaliforniaInventors: Satya P. Mallick, David J. Kriegman, Todd E. Zickler, Peter N. Belhumeur
-
Patent number: 7855807Abstract: An electronic portable document format (PDF) file contains different combinations of gradient blends between spot color and process color. Each gradient blend is represented as both rasterized bitmap and vector images. The rasterized bitmap and vector images can be used to quickly assess the capability of any digital front end (DFE) to process the color gradient blends. The PDF file contains two sets of spot color and process color blended combinations. The first set contains four types of color gradient blends: spot-to-spot, process-to-spot, spot-to-process, and process-to-process, each of which represent the intended design. The second set contains the same four types of color gradient blends, except here the CMYK colors associated with the spot colors are intentionally manipulated. By printing the PDF file using different DFEs, one may compare the output from the two sets and immediately identify any color gradient handling problem, providing a quick benchmarking tool.Type: GrantFiled: April 12, 2007Date of Patent: December 21, 2010Assignee: Xerox CorporationInventors: Louis Omer Joseph Pepin, David C. Brownhill
-
Patent number: 7853074Abstract: 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: GrantFiled: February 26, 2007Date of Patent: December 14, 2010Assignee: Eastman Kodak CompanyInventor: Gregory S. Mischler
-
Publication number: 20100303346Abstract: An image processing unit is configured to include a monotone image generator which generates a monotone image from a color image and a color reducer which reduces a color of an image by reducing chroma of the image in accordance with brightness of the image. The color reducer adjusts a tone of the monotone image generated by the monotone image generator by reducing a color of a high brightness portion of the image at a higher level than a low brightness portion of the image.Type: ApplicationFiled: May 19, 2010Publication date: December 2, 2010Inventor: HIROSHI SUITO
-
Publication number: 20100303345Abstract: A computer-implemented method for detecting a red-eye artifact that includes receiving an image depicting a first eye and a second eye corresponding to a human face, and coordinates corresponding to a location of the first eye and the second eye in the image; calculating a distance between the first eye and the second eye using the received coordinates; obtaining a skin tone sample from the image based on the calculated distance and the received coordinates; generating a skin tone color region in a color space based on the obtained skin tone sample; classifying a pixel corresponding to the first eye as a red-eye pixel by comparing the pixel with the generated skin tone color region and a predetermined red-eye color region; and storing an indication of the classifying relative to the pixel.Type: ApplicationFiled: June 1, 2009Publication date: December 2, 2010Applicant: Apple, Inc.Inventors: Russell Reid, Joshua Fagans, Tim Cherna
-
Publication number: 20100303347Abstract: A red-eye reduction technique includes converting a multi-channel image to a hue, saturation, value color space. The hue channel, the saturation channel, and the value channel are processed to identify the location of the red-eye within the image, if any.Type: ApplicationFiled: March 30, 2010Publication date: December 2, 2010Inventor: A. Mufit Ferman
-
Patent number: 7835572Abstract: A red-eye reduction technique includes converting a multi-channel image to a hue, saturation, value color space. The hue channel, the saturation channel, and the value channel are processed to identify the location of the red-eye within the image, if any.Type: GrantFiled: September 30, 2003Date of Patent: November 16, 2010Assignee: Sharp Laboratories of America, Inc.Inventor: A. Mufit Ferman
-
Patent number: 7835045Abstract: An image processing device detects a candidate area of a background color in a chromaticity plane with respect to an original scanned document. A background color area is determined based on the candidate area of the detected background color. Boundary lines extending from the determined background color area to an achromatic-color area are generated. The background color area and an area surrounded by the background color area and the boundary lines are set as a mask, and the background color of the original document is deleted.Type: GrantFiled: April 22, 2008Date of Patent: November 16, 2010Assignee: Murata Machinery, Ltd.Inventor: Naoki Nishioka
-
Patent number: 7826668Abstract: Properties of pixels of a digital image are sampled within different subdivisions of an editing tool impression to produce different property distributions. The subdivisions may be differently-located within the tool impression. The property distributions from each region are classified to identify different edit classes within the property space, which are then used to apply an edit effect to the digital image within the tool impression. The edit classes may be represented by an edit profile in two or more dimensions (e.g., applying to one or more pixel properties).Type: GrantFiled: February 17, 2004Date of Patent: November 2, 2010Assignee: Corel CorporationInventors: Krzysztof Antoni Zaklika, Mikhail Ivanovich Trifonov, Leonid Borisovich Lalyko, Viktor Antol'eylch Nesterov, Pavel Vladimirovich Gruzdev
-
Patent number: 7821688Abstract: An original document is scanned, an arbitrary color area in a chromaticity plane is extracted with respect to the scanned original document, coordinate conversion is performed on the extracted color area in the chromaticity plane, and a mask area is determined to be masked, in accordance with the converted color area on which the coordinate conversion has been performed.Type: GrantFiled: April 23, 2008Date of Patent: October 26, 2010Assignee: Murata Machinery, Ltd.Inventor: Naoki Nishioka
-
Patent number: 7821659Abstract: When there is an object of a color plate which is different than a process color, it is confirmed whether or not Color (n), which corresponds to that color name Spot (n), is a spot color. If Color (n) is a spot color, CMYK value conversion is carried out from a LUT of that spot color, and CMYK values are composed in a region for output. If Color (n) is a process color, CMYK values thereof are stored in a region for CMYK color correction. After color correction is carried out on the CMYK values of the region for CMYK color correction, they are composed with CMYK values of the region for CMYK output. Color information when a color plate different than a process color is included, is generated.Type: GrantFiled: January 14, 2005Date of Patent: October 26, 2010Assignee: Fuji Xerox Co., Ltd.Inventors: Mari Kodama, Ryuichi Ishizuka, Yasushi Nishide
-
Publication number: 20100245616Abstract: An image processing device captures a normal light image of an observed region via a plurality of color filters having different spectral characteristics, respectively, generates a uniform image having low contrast by extracting each picture signal corresponding to a picture signal in a wavelength band for which light absorption characteristic of a contrast region in the observed region becomes low, and corrects each picture signal of a fluorescence image of the observed region by using the uniform image.Type: ApplicationFiled: March 24, 2010Publication date: September 30, 2010Applicant: OLYMPUS CORPORATIONInventors: Koichiro YOSHINO, Hiroshi SUZUKI
-
Patent number: 7792357Abstract: A chromatic aberration (CA) correction technique is presented that substantially removes CA from an image captured by a digital camera. In general, the effects of any in-camera sharpening are reversed by applying a blurring kernel. The image is then super-sampled to approximate its state prior to the application of in-camera sampling. One of the color channels is designated as a reference channel, and an objective function is established for each of the non-reference channels. The reference color channel is assumed to be CA-free, while the objective functions are used to compute the unknown CA parameters for each non-reference channel. These sets are used in a CA removal function to substantially remove the CA associated with each of the non-reference channels. The image is then sampled to return it to its original resolution, and a sharpening filter is applied if needed to undo the effects of the previously applied blurring kernel.Type: GrantFiled: May 30, 2007Date of Patent: September 7, 2010Assignee: Microsoft CorporationInventor: Sing Bing Kang
-
Patent number: 7791649Abstract: An automatic white balance control image apparatus, medium, and method. The automatic white balance control imaging apparatus may include a color space conversion unit converting the input image data into color space data having a chromatic component, a gray region extraction unit extracting a gray region for the input image data based on gray regions for light sources, the gray regions being detected based on plural light sources and a predetermined color checker, a detection unit extracting initial light source information using a color gamut average value and a color gamut center value, and adjusting the initial light source information in order for a chromatic component introduced into the extracted gray region to be excluded, a gain control unit calculating gains to scale the input image data based on the adjusted initial light source information, and controlling a white balance by applying the calculated gains to the input image data.Type: GrantFiled: February 17, 2006Date of Patent: September 7, 2010Assignee: Samsung Electronics Co., Ltd.Inventors: Sung-su Kim, Ho-young Lee, Du-sik Park, Chang-yeong Kim
-
Patent number: 7782384Abstract: A digital camera is provided, comprising an image system having a unique combination of features that aid in generating creative, high-quality images. The system presents a variety of overlays, each having prescribed attributes, e.g., ranging in size, opacity, and functionality, and from iconic overlays to full-scale overlays having varied opacity. The overlays can be used as an aid in composing a live image for digital capture, either as a constant or intermittent presence on the view-screen of the camera. In an exemplary embodiment, the camera can create a composite photograph in which a live image and the overlay are combined together. In an independent aspect, the camera can include an auto-compositing feature that aids in creating images free of improperly exposed regions. Thus, a photographer can create and combine images “on location” in a unique manner.Type: GrantFiled: November 5, 2004Date of Patent: August 24, 2010Inventor: Douglas J. Kelly
-
Patent number: 7782338Abstract: Properties of pixels of a digital image are sampled within different subdivisions of an editing tool impression to produce different pixel property distributions. The property distributions from each region may be automatically classified to identify different edit classes within the property space, which are then used to apply an edit effect to the digital image within the tool impression. The edit classes are represented by an edit profile, the generation of which may be completely automated based on selection of a tool impression, or partially automated using the selection of the tool impression and receipt of classification guidance input, such as one or more parameters received from user input or a configuration file. The edit classes may also be generated without reference to the pixel property distributions, such as via user input.Type: GrantFiled: September 30, 2004Date of Patent: August 24, 2010Inventors: Krzysztof Antoni Zaklika, Mikhail Ivanovich Trifonov, Leonid Borisovich Lalyko, Viktor Antol'evich Nesterov, Pavel Vladimirovich Gruzdev
-
Patent number: 7782491Abstract: In a color pair selecting section, a color pair which is used for 2-color printing is selectively inputted from a plurality of colors. In a print data separating section, print data is separated into data in different printing forms. In a print data developing section, one of the data in the different printing forms is color converted and developed by using one of the color pair and the other data in the different printing forms is color converted and developed by using the other one of the color pair. In an image drum up/down section, image drums to form images by colors other than the color pair are discriminated and held inoperative. Deterioration of expressing ability in the 2-color printing is prevented and a decrease in lives of the image drums which are not used is prevented.Type: GrantFiled: September 2, 2004Date of Patent: August 24, 2010Assignee: Oki Data CorporationInventor: Hisashi Ishizuka
-
Publication number: 20100208985Abstract: A method and apparatus for processing an image to create a grayscale image are provided. The method includes converting, in a color image consisting of a plurality of pixels, a pixel value of each pixel in a RGB color space into a pixel value in a new color space through color space conversion, extracting color information using the pixel value in the new color space, calculating a luminance change amount of each pixel using the extracted color information, calculating a luminance value for the grayscale image by combining an original luminance value of each pixel and the luminance change amount, and creating the grayscale image according to the calculated luminance value. In converting color image into grayscale image and representing the grayscale image, the luminance change amount is set according to a property of each color perceived by humans and added to original luminance value, thereby explicitly discriminating among objects.Type: ApplicationFiled: November 10, 2009Publication date: August 19, 2010Applicant: Postech Academy - Industry FoundationInventors: Tae-Hee Lee, Byoung-Kwang Kim, Woo-Jin Song
-
Patent number: 7769231Abstract: A method and apparatus for enhancing the quality of images using complementary color contrast are provided. The method includes (a) extracting color information of each of a plurality of pixels of an input image, (b) determining whether the input image includes both a first pixel belonging to a first group and a second pixel belonging to a second group with reference to the extracted color information, (c) converting a first hue of the first pixel into an optimum point of the first group, and (d) converting a second hue of the second pixel into an optimum point of the second group, wherein the first hue corresponding to the optimum point of the first group and the second hue corresponding to the optimum point of the second group are complementary to each other.Type: GrantFiled: January 17, 2007Date of Patent: August 3, 2010Assignee: Samsung Electronics Co., Ltd.Inventors: Ji-young Hong, Dae-su Chung, Du-sik Park, Young-shin Kwak
-
Publication number: 20100177958Abstract: In image processing in which each small area included in color image data, which is represented by C, M, Y, and K, is expressed by a predetermined number of representative colors, values of color parameters are obtained for a small area from the values of the color parameters for C, M, Y, and K for each pixel in the small area, so that the values of the color parameters have degrees of variation being compensated to become smaller in the group as the value for black becomes larger. One color parameter to be targeted is selected (#104) based on the degree of variation in the values of individual color parameters in the group. A reference value to be used for grouping the pixels is obtained based on the relationship between the values of the color parameter to be targeted in the group and the quantities of pixels in the group. Based on the reference value, the pixels are divided into groups (#106), and a representative color for each group is obtained (#109).Type: ApplicationFiled: June 24, 2008Publication date: July 15, 2010Applicant: Konica Minolta Business Technologies, Inc.Inventor: Toshitsugu Yamamoto
-
Publication number: 20100177959Abstract: Dropping out of color form backgrounds from images of completed forms to obtain color form dropout images retaining only the respondent information. In one embodiment, a color form image processing method (100) includes retrieving (102) a template image, retrieving (104) a respondent image, registering (106) the images against one another to establish correspondence between pixels in the respondent and template images, dilating (108) the template image, and performing (110) a color form dropout including comparing (112) corresponding pixels in the respondent and dilated template images, and determining (114) whether to keep corresponding pixels by applying (116) a geometric solid threshold comparison to assess both color similarity and relative darkness, and removing (118) pixels from the respondent image based on such comparison.Type: ApplicationFiled: March 26, 2010Publication date: July 15, 2010Applicant: LOCKHEED MARTIN CORPORATIONInventors: Timothy O. Withum, Kurt P. Kopchik, Frederic Highland, Supreeth Hebbal, Summer C. Dasch, Stephanie M. Graham
-
Patent number: 7751615Abstract: An image processing apparatus includes a detector for detecting a first color of eyes of a subject included in a first image, based on the first image that is generated by photography, and a changer for changing the first color of eyes into a second color different from the first color, wherein the changer changes to the second color based on characteristic information indicative of a characteristic of the subject, the characteristic information being generated from the first image.Type: GrantFiled: June 7, 2005Date of Patent: July 6, 2010Assignee: Canon Kabushiki KaishaInventor: Eiichiro Ikeda
-
Publication number: 20100150424Abstract: The present invention relates to automated document processing and more particularly, to methods and systems for document image capture and processing using mobile devices. In accordance with various embodiments, methods and systems for document image capture on a mobile communication device are provided such that the image is optimized and enhanced for data extraction from the document as depicted. These methods and systems may comprise capturing an image of a document using a mobile communication device; transmitting the image to a server; and processing the image to create a bi-tonal image of the document for data extraction. Additionally, these methods and systems may comprise capturing a first image of a document using the mobile communication device; automatically detecting the document within the image; geometrically correcting the image; binarizing the image; correcting the orientation of the image; correcting the size of the image; and outputting the resulting image of the document.Type: ApplicationFiled: March 3, 2010Publication date: June 17, 2010Applicant: MITEK SYSTEMSInventors: Grigori Nepomniachtchi, James DeBello
-
Patent number: 7738696Abstract: An image processing apparatus and method include providing a same label number to adjacent black pixels that form a group of black pixels, the label number provided to each group of black pixels being unique, the black pixels being included in binary read data, determining, when the number of black pixels in a group of black pixels counted on the basis of the unique label number is less than a predetermined number, that the black pixels with the unique label number are noise and removing the black pixels from targets to be processed, acquiring coordinate information on at least one of black pixels that remain after noise has been removed, and extracting a document area on the basis of the acquired coordinate information.Type: GrantFiled: August 24, 2006Date of Patent: June 15, 2010Assignee: Canon Kabushiki KaishaInventor: Nobuyuki Bannai