Image Segmentation Using Color Patents (Class 382/164)
-
Publication number: 20130251250Abstract: An image processing apparatus includes a representative color calculation unit, a color displacement calculation unit, and a similarity calculation unit. The representative color calculation unit calculates a representative color which is representative of colors in a first region having a predetermined size in an image. The color displacement calculation unit calculates, as a color displacement, a difference between the representative color calculated by the representative color calculation, unit and a color in a target second region in the first region. The similarity calculation unit calculates similarity between the color displacement calculated by the color displacement calculation unit and a predetermined color displacement in an information image representing information embedded in the image.Type: ApplicationFiled: October 31, 2012Publication date: September 26, 2013Applicant: FUJI XEROX CO., LTD.Inventor: Atsushi ITOH
-
Patent number: 8542918Abstract: Some embodiments of the invention provide a non-linear image-enhancement method to enhance an image that includes a number of picture elements. The non-linear enhancement method adjusts the brightness value of each pixel in the image and adjusts at least one chromatic value of each pixel in the image based on the adjustment to the brightness value of that pixel.Type: GrantFiled: September 28, 2010Date of Patent: September 24, 2013Assignee: Apple Inc.Inventors: Andrew Bryant, Adriana Dumitras
-
Patent number: 8542401Abstract: An image processing apparatus includes a printing unit to print an image on a sheet, a reading unit to read the sheet, a conversion unit to convert a background image stored in a storage medium into a reference image that represents the background image and has a luminance value higher than that of the background image, a print control unit to cause the printing unit to print the reference image obtained by the conversion unit, as an entry area for a user, on the sheet, an extraction unit to extract an image of an area that has a luminance value lower than a first threshold and a color-difference value greater than a second threshold from an image corresponding to the entry area included in the image read by the reading unit after an entry by the user in the entry area, and a combining unit to combine the image extracted by the extraction unit with the background image.Type: GrantFiled: August 6, 2009Date of Patent: September 24, 2013Assignee: Canon Kabushiki KaishaInventor: Keiko Hanawa
-
Patent number: 8542909Abstract: There is provided a method of measuring 3D depth of a stereoscopic image, comprising providing left and right eye input images, applying an edge extraction filter to each of the left and right eye input images, and determining 3D depth of the stereoscopic image using the edge extracted left and right eye images. There is also provided an apparatus for carrying out the method of measuring 3D depth of a stereoscopic image.Type: GrantFiled: April 6, 2011Date of Patent: September 24, 2013Assignee: Tektronix, Inc.Inventors: Antoni Caceres, Martin Norman
-
Patent number: 8542916Abstract: A system and method of analyzing at least one dataset having temporal and spatial content is provided. A method includes the steps of applying a colorimetric mapping to the dataset based on the spatial content (500), segmenting the dataset (618) into one of a plurality of patterns based on a spatio-temporal analysis of the dataset (604, 606), and analyzing characteristics of each of the plurality of patterns (612-622).Type: GrantFiled: July 9, 2009Date of Patent: September 24, 2013Assignee: Florida Atlantic UniversityInventors: Emmanuelle Tognoli, J. A. Scott Kelso
-
Patent number: 8542929Abstract: Provided is an image processing method and apparatus for improving image quality and enhancing a three-dimensional effect. By extracting an interest feature index from an input image based on a depth sensation estimation cue existing in the image, calculating an interest feature index integration map based on the interest feature index and importance of interest of the depth sensation estimation cue, and performing discrimination processing of the image based on the interest feature index integration map, three-dimensional effect and true sensation enhancement processing can be performed based on the probability of the existence of a depth sensation estimation cue, without segmentation of an object of interest, correct depth information, or an object model.Type: GrantFiled: July 31, 2007Date of Patent: September 24, 2013Assignee: Samsung Electronics Co., Ltd.Inventors: Yoon-kyung Kim, Young-su Moon, Jun-mo Kim, Yong-seok Yoo
-
Patent number: 8542245Abstract: An image processing apparatus includes: an amount-of-feature detection section configured to determine an amount of features of a first image and an amount of features of a second image, the first image and the second image containing the same subject; an elimination-area detection section configured to eliminate, from the second image, an area in which the amount of features extracted by the amount-of-feature detection section is larger than a predetermined threshold and to provide the second image in which the eliminated area is transparent; and an image combination section configured to superimpose the second image in which the eliminated area is transparent on the first image.Type: GrantFiled: March 27, 2009Date of Patent: September 24, 2013Assignee: Sony CorporationInventors: Tetsujiro Kondo, Tetsushi Kokubo, Kenji Tanaka, Hitoshi Mukai, Hirofumi Hibi, Kazumasa Tanaka, Takuro Ema, Hiroyuki Morisaki
-
Patent number: 8542923Abstract: Methods, systems, and apparatus, including computer program products, feature receiving user input defining a sample of pixels from an image, the image being defined by a raster of pixels. While receiving the user input, the following actions are performed one or more times: pixels are coherently classified in the raster of pixels as being foreground or background based on the sample of pixels; and a rendering of the image is updated on a display to depict classified foreground pixels and background pixels as the sample is being defined.Type: GrantFiled: June 11, 2012Date of Patent: September 24, 2013Assignee: Adobe Systems IncorporatedInventors: Gregg D. Wilensky, Scott D. Cohen, Jen-Chan Chien
-
Publication number: 20130243312Abstract: A color distance measurement apparatus includes: a first transformation section that transforms first color pixel data and second color pixel data in a predetermined color space into a deformed HSV color space; a second transformation section that transforms the first color pixel data and the second color pixel data transformed into the deformed HSV color space into a three-dimensional x, y, z coordinate representation; and a color distance measurement section that measures a relative color distance between the first color pixel data and the second color pixel data on the basis of the first color pixel data and the second color pixel data transformed into the x, y, z coordinate representation. In the deformed HSV color space, maximum saturation is larger than maximum saturation in an HSV color space for a cone model at lightness between maximum lightness and minimum lightness, and the saturation is 0 at the minimum lightness.Type: ApplicationFiled: February 27, 2013Publication date: September 19, 2013Applicant: Sony CorporationInventor: Yoichiro Sato
-
Publication number: 20130242130Abstract: An entered image is divided into a plurality of windows and it is determined, on a per-window basis, whether the image data within an applicable window is indicative of the color white, based upon the position of each window in the image and the continuity to its surrounding divided windows. A white balance method is performed based upon data of a window determined to be indicative of the color white. The present invention conducts a white balance process through the addition of determining the light source type weight and calculating the continuity of each divided window and its surrounding divided windows. In order the white balance process to accurately obtain the colors of an entered image even under the conditions of specific scenes with distinctive colors.Type: ApplicationFiled: July 17, 2012Publication date: September 19, 2013Applicant: ALTEK CORPORATIONInventors: Shih-Yuan Peng, Hsin-Te Wang, Hong-Long Chou
-
Publication number: 20130243311Abstract: Systems and methods for counting and processing pliable objects are disclosed. A vision system may capture an inspection image of a plurality of pliable objects. The inspection image may be partitioned into a plurality of windows traversing the inspection image. For each individual window of the plurality of windows, a blob extraction process is performed to determine a plurality of blobs corresponding to regions within the inspection image having substantially the second luminance value range such that the plurality of blobs correspond to the plurality of pliable objects. The blobs are counted for each window to determine a total number of pliable objects in the plurality of pliable objects.Type: ApplicationFiled: March 13, 2012Publication date: September 19, 2013Inventors: Christopher van de Vrande, Guillaume Carrier, Rajesh Kumar Singh
-
Publication number: 20130243313Abstract: The method comprises: generating a set of cost functions for foreground, background and shadow segmentation classes or models, where the background and shadow segmentation models are a function of chromatic distortion and brightness and colour distortion, and where said cost functions are related to probability measures of a given pixel or region to belong to each of said segmentation classes; and applying to pixel data of an image said set of generated cost functions; The method further comprises defining said background and shadow segmentation cost functionals introducing depth information of the scene said image has been acquired of. The system comprises camera means intended for acquiring, from a scene, colour and depth information, and processing means intended for carrying out said foreground segmentation by hardware and/or software elements implementing the method.Type: ApplicationFiled: August 11, 2011Publication date: September 19, 2013Applicant: TELEFONICA, S.A.Inventors: Jaume Civit, Oscar Divorra
-
Publication number: 20130243314Abstract: The method comprises: generating a set of cost functions for foreground, background and shadow segmentation classes or models, where the background and shadow segmentation costs are based on chromatic distortion and brightness and colour distortion; and applying to the pixels of an image said set of generated cost functions; The method further comprises, in addition to a local modelling of foreground, background and shadow classes carried out by said cost functions, exploiting the spatial structure of content of at least said image in a local as well as more global manner; this is done such that local spatial structure is exploited by estimating pixels' costs as an average over homogeneous colour regions, and global spatial structure is exploited by the use of a regularization optimization algorithm. The system is adapted to implement at least part of the method.Type: ApplicationFiled: August 11, 2011Publication date: September 19, 2013Applicant: TELEFONICA, S.A.Inventors: Jaume Civit, Oscar Divorra
-
Patent number: 8538152Abstract: Disclosed is a processor-implemented method for processing image data using an image processing apparatus. The processor is configured to receive a PDL file of image data and raster image process (RIP) the PDL file to determine at least pixels representing text of a predetermined colorant. The ripped file is then segmented to determine at least any text pixels of the predetermined colorant not initially indicated by the ripped file. The results are combined to determine text pixels of the predetermined colorant for marking onto a substrate using marking material (e.g., ink). In some instances, pixels of the predetermined colorant can be tagged during segmenting using a tag plane to determine text pixels for marking by the output device.Type: GrantFiled: September 12, 2011Date of Patent: September 17, 2013Assignee: Xerox CorporationInventors: David Robinson, Katherine Loj
-
Patent number: 8538149Abstract: A data processing apparatus for registering image data includes a network processing unit configured for acquiring image data through a network, an image correction unit for analyzing the image data, extracting a background image and a subject image from the image data, and correcting the extracted background image according to a correction condition, and a database unit for storing the corrected image data such that the image data is associated with the corrected image data.Type: GrantFiled: November 26, 2007Date of Patent: September 17, 2013Assignee: Ricoh Company, Ltd.Inventor: Masajiro Iwasaki
-
Publication number: 20130236092Abstract: Embodiments disclosed include methods and systems for assigning one or more labels to one or more segments of data received in an incoming segment to a line buffer for propagated component labeling, including preventing repeated labels in each line of the line buffer by assigning a different label for each of the one or more segments of data received in each line; labeling the incoming segment of the one or more segments of data by adopting a label of an overlapping segment on a prior received line when the overlapping segment does not overlap any other segment of data; labeling the incoming segment of the one or more segments of data by adopting a label of an overlapping segment on a prior received line when the overlapping segment overlaps more than one segment on the incoming segment when the segment is a first segment in the line buffer; and labeling the incoming segment of the one or more segments of data by adopting a label of a last overlapping segment when more than one segment overlaps the incoming sType: ApplicationFiled: April 12, 2013Publication date: September 12, 2013Applicant: eyeP, Inc.Inventor: Craig Sullender
-
Publication number: 20130235231Abstract: A method of coding High Definition (HD) color pictures is described. The method divides the HD picture into individual bit planes of the three colors. The method then interleaves the bit planes such that bit planes of the three colors having the same significance are coded together. The method codes a block of the picture based on the bit distribution in corresponding groups of the corresponding bit planes of the three colors. The method performs a first level grouping of bits in a bit plane of an image and a second level grouping of the first level grouping bits of different color components within a group.Type: ApplicationFiled: April 19, 2013Publication date: September 12, 2013Applicant: SONY CORPORATIONInventors: Wei Liu, Mohammad Gharavi-Alkhansari
-
Patent number: 8532435Abstract: In various example embodiments, a system and associated method to automatically adapt images is provided. A request to render a stored image is received. The request comprises an output parameter indicative of a display constraint to be applied in the rendering of the stored image, while the stored image has region characteristics associated therewith. An adaptation process to apply to the stored image is determined using the output parameter. An output image is then rendered using the adaptation process and the region characteristics. The output image is then provided to a display device.Type: GrantFiled: August 18, 2009Date of Patent: September 10, 2013Assignee: Adobe Systems IncorporatedInventors: Abhishek N. Hegde, Herbert Wolfram
-
Patent number: 8532385Abstract: An image processing apparatus includes a region analysis unit configured to generate a quantized region by integrating regions that are included in an input multivalued image and have similar colors and to determine an attribute of a connected component included in the generated quantized region, and a character portion filling unit configured to determine a color used for filling a connected component that has been determined by the region analysis unit to have a character attribute and to execute processing for filling the connected component that has been determined to have the character attribute. In the image processing apparatus, the character portion filling unit is configured to change a method for determining the color used for filling based on the quantized region existing adjacent to the connected component determined to have the character attribute.Type: GrantFiled: June 18, 2010Date of Patent: September 10, 2013Assignee: Canon Kabushiki KaishaInventor: Taeko Yamazaki
-
Patent number: 8532374Abstract: Disclosed is a method of classifying segmented contents of a scanned image of a document. The method comprise partitioning the scanned image into color segmented tiles at pixel level. The method then generates superpositioned segmented contents, each segmented content representing related color segments in at least one color segmented tile. Statistics are then calculated for each segmented content using pixel level statistics from each of the tile color segments included in segmented content, and then determines a classification for each segmented content based on the calculated statistics. The segmented content may be macroregions. The macroregions may form part of a multi-layered document representation of the document.Type: GrantFiled: December 3, 2008Date of Patent: September 10, 2013Assignee: Canon Kabushiki KaishaInventors: Yu-Ling Chen, Steven Richard Irrgang, Eric Wai-Shing Chong
-
Publication number: 20130230238Abstract: Separations or images relating to film or other fields may be registered using a variety of features, such as, for example: (1) correcting one or more film distortions; (2) automatically determining a transformation to reduce a film distortion; (3) applying multiple criteria of merit to a set of features to determine a set of features to use in determining a transformation; (4) determining transformations for areas in an image or a separation in a radial order; (5) comparing areas in images or separations by weighting feature pixels differently than non-feature pixels; (6) determining distortion values for transformations by applying a partial distortion measure and/or using a spiral search configuration; (7) determining transformations by using different sets of features to determine corresponding transformation parameters in an iterative manner; and (8) applying a feathering technique to neighboring areas within an image or separation.Type: ApplicationFiled: March 18, 2013Publication date: September 5, 2013Applicants: AOL INC., Warner Bros. Entertainment Inc.Inventors: Keren O. Perlmutter, Sharon M. Perlmutter, Eric Wang, Paul R. Klamer, Christopher J. Cookson, Massimiliano Gasparri
-
Publication number: 20130230237Abstract: A method and an apparatus for bi-layer segmentation of an image or a sequence of images are described. A classifier is derived based on depth data of the image and another classifier is derived based on color data of the image. The image is then segmented by maximizing a weighted sum of matching scores derived from the classifiers based on depth data and color data of the image. The classifier based on color data of the image is derived using color sampling subsequent to generating an initial segmentation of the image.Type: ApplicationFiled: March 4, 2013Publication date: September 5, 2013Applicant: Thomson LicensingInventors: Markus Schlosser, Lorenzo Sorgi
-
Publication number: 20130230239Abstract: Techniques for segmenting an object at a self-checkout are provided. The techniques include capturing an image of an object at a self-checkout, dividing the image into one or more blocks, computing a confidence value for each of the one or more blocks, and eliminating one or more blocks from consideration based on the confidence value for each of the one or more blocks, wherein the one or more blocks remaining map to a region of the image containing the object.Type: ApplicationFiled: April 17, 2013Publication date: September 5, 2013Applicant: International Business Machines CorporationInventors: Rogerio S. Feris, Charles A. Otto, Sharathchandra Pankanti, Duan D. Tran
-
Patent number: 8526061Abstract: An image processing apparatus includes an object type determining unit that determines whether a drawing object in the input image data includes a color character group; a background area extracting unit that extracts the background area on which the color character group is formed in the drawing object; a monochromatic conversion unit that, when the drawing object is determined to include the color character group, generates monochromatic image data by performing monochromatic conversion of the input image data with minimum luminance of a main color; a pattern generating unit that, when the drawing object is determined to include the color character group, generates, according to the hue of the color character group, pattern image data to be added to the background area of the post-monochromatic-conversion color character group; and a synthesizing unit that synthesizes the monochromatic image data and the pattern image data.Type: GrantFiled: December 10, 2010Date of Patent: September 3, 2013Assignee: Ricoh Company, Ltd.Inventor: Yasunobu Shirata
-
Patent number: 8526723Abstract: Preferred aspects of the present invention can include receiving a digital image at a processor; segmenting the digital image into a hierarchy of feature layers comprising one or more fine-scale features defining a foreground object embedded in one or more coarser-scale features defining a background to the one or more fine-scale features in the segmentation hierarchy; detecting a first fine-scale foreground feature as an anomaly with respect to a first background feature within which it is embedded; and constructing an anomalous feature layer by synthesizing spatially contiguous anomalous fine-scale features. Additional preferred aspects of the present invention can include detecting non-pervasive changes between sets of images in response at least in part to one or more difference images between the sets of images.Type: GrantFiled: October 25, 2012Date of Patent: September 3, 2013Assignee: Los Alamos National Security, LLCInventors: Lakshman Prasad, Sriram Swaminarayan
-
Patent number: 8526721Abstract: A method of processing image data, to obtain image data for printing a junction area connecting a circular pad having a radius R with a linear line pattern by forming ink blots having a radius r in an overlapping manner, includes: setting a base pitch P as a base distance between adjacent ink blots; arranging image data of the pad, line pattern, and junction area, which is defined by an extension of the line pattern, in an x-y coordinate system; selecting a first determination point, which corresponds to one side of the junction area; comparing a distance from a center of the pad to the first determination point with a value of (R?r+P); and storing coordinates of the first determination point as print data if the distance from the center of the pad to the first determination point is greater than or equal to the value of (R?r+P).Type: GrantFiled: June 25, 2009Date of Patent: September 3, 2013Assignee: Samsung Electro-Mechanics Co., Ltd.Inventors: Kwansoo Yun, Joshi Akshay, Sangdo Cho, Yongsik Kim, Jaewoo Joung
-
Patent number: 8526722Abstract: Provided are an apparatus and method for enhancing image quality of an input image captured by an image capturing device having an aperture with a plurality of openings employing different color filters. The image quality enhancing apparatus includes an ROI (region of interest) classifying unit classifying ROIs according to distances from the image capturing device of a captured input image by using a cluster-based image segmentation algorithm, a color channel registering unit determining motion vectors of color channels corresponding to the respective ROIs by analyzing a high frequency component of image data included in the ROIs, and moving the color channels based on the determined motion vectors to obtain a registered image of the respective ROIs, and an image fusing unit fusing the registered images of the respective ROIs to obtain a fused image.Type: GrantFiled: April 15, 2011Date of Patent: September 3, 2013Assignee: Chung-Ang University Industry-Academy Cooperation FoundationInventors: Joon-Ki Paik, Eun-Sung Lee
-
Patent number: 8526717Abstract: A method of finding targets in a color image applies ratio space rich colored filtering to identify a band of pixels that form a transition zone from one rich color to another. This pixel band is reduced to a rich color transition curve. A set of transition curves with simple geometric and color properties for the entire image, can be compared to a database of target properties to identify a target in an image.Type: GrantFiled: November 21, 2011Date of Patent: September 3, 2013Assignees: Vision Interface Technologies, LLC, Creative Lifestyles, Inc.Inventors: Peter Harmon Smith, Frank Meyer, John Frederick Cloyd, Bora Tekkanat
-
Publication number: 20130223729Abstract: Points of interest are identified in an image to characterise that image by dividing the image tiles, each tile including adjacent pixels. The position of a pixel with an extremum value is determined or located within each tile and that extremal value is ascribed to the tile. A tile with an extremal value which is more extreme than that of all adjacent tiles is identified; and the position within the image of the pixel with the extremum value in that identified tile is selected as the point of interest.Type: ApplicationFiled: February 28, 2013Publication date: August 29, 2013Applicant: SNELL LIMITEDInventor: Snell Limited
-
Patent number: 8520259Abstract: Graininess is suppressed while at the same time minimizing grayscale variations caused by inter-plane deviations. For this purpose, when a pixel is printed by M relative scans of a print head over a print medium or by a relative scans of M print heads over the print medium, M pieces of multivalued image data is created according to a division number or distribution ratio determined by a grayscale value of that pixel. The M pieces of multivalued image data are individually quantized and then the printing is performed according to the quantized pixel data. This process prevents dot generation delays and graininess from deteriorating in highlighted areas, thus realizing printed images highly robust against density variations.Type: GrantFiled: June 8, 2009Date of Patent: August 27, 2013Assignee: Canon Kabushiki KaishaInventors: Yasunori Fujimoto, Tomokazu Yanai, Shinichi Miyazaki
-
Patent number: 8520940Abstract: A computer implemented system and method are disclosed for segmenting aerial and satellite imagery according to pre-defined regions contained in the images such as city blocks. An example system comprises a feature mask generation module, a partition generation module, one or more color map generation modules, a color map reassignment module, and a bounding box generation module. The system and method take aerial image data and vector map data as input and generate a composite color map for a geographic region of interest, wherein the color map comprises a plurality of pre-defined regions in which each pre-defined region can be defined by enclosing road segments. The disclosed system and method provide a convenient and logical way of segmenting large data sets of aerial imagery for use in other applications such as the construction of computer models of surface features of the Earth.Type: GrantFiled: May 9, 2011Date of Patent: August 27, 2013Assignee: Google Inc.Inventors: Joshua Schpok, Jeremiah Childs, Tilman Reinhardt
-
Patent number: 8520939Abstract: An apparatus and method of reproducing a preferred color to eliminate or reduce errors caused when converting of colors of an input image in corresponding color regions of a color space, respectively, wherein the colors of an input image are included in a plurality of different color regions. The apparatus includes a region judging unit to judge whether pixels of an input image are included in one or more preset color regions, a color converting unit to execute a color conversion of the pixels in at least one conversion-desired color regions among one or more color regions that include the pixels, and an output unit to output an image formed by the color-converted pixels.Type: GrantFiled: August 13, 2007Date of Patent: August 27, 2013Assignee: Samsung Electronics Co., Ltd.Inventors: Ji-young Hong, Du-sik Park, Young-shin Kwak
-
Patent number: 8520894Abstract: Disclosed herein are a method, system, and computer program product for aligning an input video frame from a video sequence with a background model associated with said video sequence. The background model includes a plurality of model blocks (820, 830), each one of the plurality of model blocks (820, 830) being associated with at least one mode (821, 822, 823, 831, 832, 833, 834), wherein each mode (821, 822, 823, 831, 832, 833, 834) includes a plurality of frequency domain attributes. The method selects, for each one of the plurality of model blocks, a reference mode dependent upon a mode of the corresponding model block, generates a background reference image (840) comprising the plurality of selected reference blocks (841, 842), and then aligns the input frame with the background model (810), based on the background reference image (810).Type: GrantFiled: December 15, 2010Date of Patent: August 27, 2013Assignee: Canon Kabushiki KaishaInventor: Amit Kumar Gupta
-
Patent number: 8520941Abstract: A method of classifying an input image includes the initial steps of labeling an input image in accordance with a class and extracting at least one connected component from the input image. The method also includes the steps of calculating at least one feature of the input image and generating a model based on the at least one calculated feature. The method also includes the steps of repeating at least one of the previous steps for at least one other input image and comparing the at least one other input image with the model. The at least one other input image is classified in accordance with the class of the model if the at least one calculated feature of the at least one other input image is substantially similar to that of the model.Type: GrantFiled: December 9, 2008Date of Patent: August 27, 2013Assignee: Xerox CorporationInventors: Asghar Nafarieh, Alejandro E. Brito
-
Patent number: 8515171Abstract: A multi-resolution color image segmentation algorithm which takes advantage of gradient information in an adaptive and progressive framework is described. A gradient-based segmentation method is initiated with a dyadic wavelet decomposition scheme of an arbitrary input image, accompanied by a vector gradient calculation of its color converted counterpart. The resultant gradient map is used to automatically and adaptively generate thresholds for segregating regions of varying gradient densities, at different resolution levels of the input image pyramid. In combination with a confidence map and non-linear spatial filtering techniques, regions of high confidence are passed from one resolution level to another until the final segmentation at highest (original) resolution is achieved.Type: GrantFiled: January 11, 2010Date of Patent: August 20, 2013Assignees: Rochester Institute of Technology, Hewlett-Packard Development Company, LPInventors: Sreenath Rao Vantaram, Eli Saber, Sohail Dianat, Mark Shaw, Ranjit Bhaskar
-
Patent number: 8515169Abstract: An apparatus and method for removing red-eye in a 2D image, which can remove red-eye more naturally and apply a gain for a real-time correction on input pixels by differently performing a correction degree according to positions of pixels included in red-eye.Type: GrantFiled: September 14, 2012Date of Patent: August 20, 2013Assignee: Samsung Electro-Mechanics Co., Ltd.Inventors: Kang Joo Kim, Bong Soon Kang, Suk Chan Kim, Won Woo Jang, Sung Jin Lee, Jung Hwan Park, Hak Sun Kim, Won Tae Choi, Boo Dong Kwak
-
Publication number: 20130208979Abstract: A method for providing improved foreground/background separation in a digital image of a scene is disclosed. The method comprises providing a first map comprising one or more regions provisionally defined as one of foreground or background within the digital image; and providing a subject profile corresponding to a region of interest of the digital image. The provisionally defined regions are compared with the subject profile to determine if any of the regions intersect with the profile region. The definition of one or more of the regions in the map is changed based on the comparison.Type: ApplicationFiled: January 28, 2013Publication date: August 15, 2013Applicant: DIGITALOPTICS CORPORATION EUROPE LIMITEDInventor: DigitalOptics Corporation Europe Limited
-
Patent number: 8509529Abstract: A color that readily leaves an impression is adopted as the representative color of a color image. Pixels that form a color image are distributed in L*a*b* color space and are projected onto the a*b* plane. The pixels are grouped and the color at the centroid position of each group is adopted as a representative candidate color. A first score is calculated based upon the distance from the origin, which is indicative of gray, to the representative candidate color, and a second score is calculated from the number of pixels contained in the group. A final score is calculated from the first and second scores and representative candidate colors that provide the three highest final scores are decided upon as representative colors.Type: GrantFiled: April 16, 2010Date of Patent: August 13, 2013Assignee: FUJIFILM CorporationInventor: Hisashi Endo
-
Patent number: 8509531Abstract: The present invention provides an image processing apparatus, and an image processing method, which can reproduce an edge portion with a high resolution in a high resolution raster image, and suppress image degradation such as a jaggy, while suppressing processing cost. In the present invention, an image processing part divides image data of raster data into blocks of M×N pixels (M, N are integers of 1 or more and also at least one of M and N is an integer of 2 or more). Then, the part performs color rounding processing in the block and counts the number of colors in the block. Subsequently, when the number of colors existing in the block is two, the part acquires shape information about arrangement of the two colors. Then, the part stores the shape information and color information for a first color and color information for a second color.Type: GrantFiled: January 12, 2012Date of Patent: August 13, 2013Assignee: Canon Kabushiki KaishaInventor: Hirokazu Tamura
-
Patent number: 8509530Abstract: The compression processing unit 30 of the image processing apparatus makes the color conversion process section 50 to the layout analysis processing section 53 extract the text string region, and makes the foreground layer generating section 54 extract the foreground pixel from the text string region to generate the foreground layer. The line detection process section 52 extracts the line art from the input image data, and removes the pixel block configuring the line art from the foreground pixel-block mask generated by the foreground extracting section 51. The layout analysis processing section 53 estimates the direction of the text string in accordance with the distance of the foreground regions and the number of connected foreground regions, and merges the foreground regions connected in the estimated direction, to extract the text string region.Type: GrantFiled: November 23, 2011Date of Patent: August 13, 2013Assignee: Sharp Kabushiki KaishaInventor: Toyohisa Matsuda
-
Publication number: 20130201334Abstract: The present application provides a robust, illumination invariant apparatus and method for detecting and recognizing various traffic signs. A robust method for detecting and recognizing the traffic signs using images captured by a digital color and night vision camera, the said method characterized in being illumination invariant comprising the processor implemented steps of: transforming RGB image into HSV color model and subsequently extracting desired color components by using color quantization; filtering the noise components in the HSV color model based on object symmetrical shape property; detecting edges of the objects and subsequently detecting the distinct objects in the noise components filtered image; classifying the shapes of the traffic signs based on shape of the determined distinct objects; and recognizing the classified shapes of the traffic signs by template matching. Further, the method provides the provision for warning the driver by use of the recognized data of the traffic signs.Type: ApplicationFiled: June 10, 2011Publication date: August 8, 2013Inventors: Manoj R C, Pratap Pulugoru, Sachin Agsebagil, Aniruddha Sinha
-
Patent number: 8503782Abstract: Methods, systems, and apparatus including computer program products for using extracted image text are provided. In one implementation, a computer-implemented method is provided. The method includes receiving an input of one or more image search terms and identifying keywords from the received one or more image search terms. The method also includes searching a collection of keywords including keywords extracted from image text, retrieving an image associated with extracted image text corresponding to one or more of the image search terms, and presenting the image.Type: GrantFiled: January 13, 2012Date of Patent: August 6, 2013Assignee: Google Inc.Inventors: Luc Vincent, Adrian Ulges
-
Patent number: 8503815Abstract: The described methods and corresponding apparatus are for use in highlight recovery in a set of image data. The image data is inverted, treated by a digital lighting process, the subsequently inverted again. This allows the set of data image to be treated for dynamic range compression of detail in both the dark regions and the light regions by the same algorithm. In other words, the process applied to the dark regions can be performed by a correction algorithm and the process applied to the light regions performed by the same algorithm, but with the image data negated before and after the correction algorithm is applied.Type: GrantFiled: May 23, 2007Date of Patent: August 6, 2013Assignee: CSR Technology, Inc.Inventor: Itsik Dvir
-
Patent number: 8503781Abstract: Methods (1200), apparatuses, and computer program for finding a region containing text in a color bitmap image comprising pixels are provided. Connected components (CCs) are generated (1200) from the color bitmap image by grouping substantially similarly colored and adjacent pixels. Independently of color, which of the connected components are text connected components are determined (1212) dependent upon attributes of the generated connected components. For each text CC) a value is assigned (1214) to each tile that comprises at least a portion of the text connected component. The value indicates the presence of text overlapping the tile. Each tile comprises pixels of the color bitmap image. The region containing text in the color bitmap image is determined (1216) dependent upon the assigned values of the tiles.Type: GrantFiled: December 13, 2011Date of Patent: August 6, 2013Assignee: Canon Kabushiki KaishaInventors: Yu-Ling Chen, Kailash Nandish Ballu
-
Patent number: 8498480Abstract: A computationally efficient image segmentation method is provided that processes a grayscale digital image to more clearly show textures in the underlying object shown in the digital image. A grayscale digital image is converted to an intensity matrix based on the brightness of the pixels in the image, where each matrix element represents a pixel in the digital image and has a value corresponding to the intensity, i.e., the brightness, of that pixel. The value of each matrix element is compared to the value of its nearest neighbor matrix element, and the pixel represented by the matrix element is categorized as being “dark” or “bright” based on its value, and is categorized as being “smooth” or “rough” based on the values of the nearest neighbor matrix elements. As each pixel is categorized, it is assigned a shading level corresponding to the brightness/texture matrix element value.Type: GrantFiled: February 24, 2010Date of Patent: July 30, 2013Assignee: The United States of America, as represented by the Secretary of the NavyInventor: Frank W. Bentrem
-
Publication number: 20130188865Abstract: Briefly, in accordance with one aspect, a method of binarizing an image is provided. The method includes partitioning the image into a plurality of image segments, each image segment having a plurality of image pixels and partitioning each of the image segments into subsegments, each image subsegment having a plurality of image pixels. The method also includes estimating a grey membership parameter for each image pixel for each of the plurality of image segments and subsegments, combining the grey membership parameter for each of the plurality of image pixels from each of the plurality of image segments and subsegments to estimate a net grey membership parameter for each image pixel and assigning black or white color to each of the plurality of image pixels based on the estimated net grey membership parameter of the respective pixel.Type: ApplicationFiled: March 7, 2013Publication date: July 25, 2013Applicant: JADAVPUR UNIVERSITYInventor: JADAVPUR UNIVERSITY
-
Publication number: 20130188864Abstract: An MMR system for searching across multiple indexes comprises a plurality of mobile devices, a pre-processing server or MMR gateway, and an MMR matching unit, and may include an MMR publisher. The MMR matching unit receives an image query from the pre-processing server or MMR gateway and sends it to one or more of the recognition units to identify a result including a document, the page and the location on the page. The MMR matching unit includes a segmenter for segmenting received images by content type, a distributor for distributing the images to corresponding content type index tables, and an integrator for integrating recognition results. The result is returned to the mobile device via the pre-processing server or MMR gateway. The present invention also includes a number of novel methods including a method for processing content-type specific image queries and for processing queries across multiple indexes.Type: ApplicationFiled: December 28, 2012Publication date: July 25, 2013Inventors: Jorge Moraleda, Berna Erol, Jonathan J. Hull
-
Patent number: 8494263Abstract: An image processing system provides faster than real-time skin detection and localization. The system uses the highly optimized architecture of a graphics processing unit to quickly and efficiently detect and locate skin in an image. By performing skin detection and localization on the graphics processing unit, the image processing system frees the main system processor to perform other important tasks, including running general purpose applications. The speed with which the image processing system detects and localizes skin also facilitates subsequent processing steps such as face detection and motion tracking.Type: GrantFiled: August 31, 2011Date of Patent: July 23, 2013Assignee: Accenture Global Services LimitedInventors: Kelly L Dempski, Manoj Seshadrinathan
-
Patent number: 8494280Abstract: An automated method for extracting highlighted regions in a scanned text documents includes color masking of highlight regions, extracting text from highlighted regions, recognizing the characters in extracted text optically and inserting the recognized characters to new document in order to easily identify highlighted text in scanned images. Using a two-layer multi-mask compression technology configured in a scanned export image path, edges and text regions can be extracted and together with the use of mask coordinates and associated mask colors, all highlighted texts can be easily identified and extracted. Optical Character Recognition (OCR) can then be utilized to appropriate summarization of different extracted highlighted texts.Type: GrantFiled: April 27, 2006Date of Patent: July 23, 2013Assignee: Xerox CorporationInventors: Ramesh Nagarajan, Michael R. Campanelli, Isaiah Simmons
-
Patent number: 8493476Abstract: The present invention provides a video in which a subject image looks clear while reducing the amount of transmitted data. An image capturing apparatus includes: an image capturing section that successively captures a plurality of images under a plurality of image capturing conditions different from each other; an image generating section that generates an output image by overlapping the plurality of captured images captured under the plurality of image capturing conditions; and an output section that outputs the output image generated by the image generating section. The image capturing section may successively capture the plurality of images by means of exposure in different exposure time lengths from each other. The image capturing section may successively capture the plurality of images also by means of exposure in different aperture openings from each other.Type: GrantFiled: September 21, 2010Date of Patent: July 23, 2013Assignee: FUJIFILM CorporationInventors: Makoto Yonaha, Hirokazu Kameyama