Patents by Inventor Che-Bin Liu

Che-Bin Liu has filed for patents to protect the following inventions. This listing includes patent applications that are pending as well as patents that have already been granted by the United States Patent and Trademark Office (USPTO).

  • Patent number: 8243981
    Abstract: Disclosed are embodiments of systems and methods for embedding and/or extracting data from images. In embodiments, an image may be segmented into regions, and characters or other image groups within a segmented region may be determined to be embedding sites. A data vector may be embedded into a set of corresponding ordered embedding sites by representing each data element as different intensity values assigned to the pixels within one portion of an embedding site relative to the pixels in another portion of the embedding site. In embodiments, embedded data may be extracted from an image by extracting and decoding a set of bit values from a set of identified and ordered embedding sites.
    Type: Grant
    Filed: November 26, 2007
    Date of Patent: August 14, 2012
    Assignee: Seiko Epson Corporation
    Inventors: Ali Zandifar, Che-Bin Liu
  • Patent number: 8031905
    Abstract: Disclosed are embodiments of systems and methods for embedding and/or extracting data from images. In embodiments, an image may be segmented into regions, and characters or other image groups within a segmented region may be determined to be embedding sites. A data vector may be embedded into a set of corresponding ordered embedding sites by representing each data element as different intensity values assigned to the pixels within one portion of an embedding site relative to the pixels in another portion of the embedding site. In embodiments, embedded data may be extracted from an image by extracting and decoding a set of bit values from a set of identified and ordered embedding sites.
    Type: Grant
    Filed: November 21, 2007
    Date of Patent: October 4, 2011
    Assignee: Seiko Epson Corporation
    Inventors: Ali Zandifar, Che-Bin Liu, Jing Xiao
  • Patent number: 8009862
    Abstract: Disclosed are embodiments of systems and methods for embedding and/or extracting data from images. In embodiments, an image may be segmented into regions, and characters or other image groups within a segmented region may be determined to be embedding sites. A data vector may be embedded into a set of corresponding ordered embedding sites by representing each data element as different intensity values assigned to the pixels within one portion of an embedding site relative to the pixels in another portion of the embedding site. In embodiments, embedded data may be extracted from an image by extracting and decoding a set of bit values from a set of identified and ordered embedding sites.
    Type: Grant
    Filed: November 27, 2007
    Date of Patent: August 30, 2011
    Assignee: Seiko Epson Corporation
    Inventors: Ali Zandifar, Che-Bin Liu, Jing Xiao
  • Patent number: 7936923
    Abstract: Disclosed are embodiments of systems and methods for suppressing the background of an image. In embodiments, the number of foreground pixels or background pixels within a neighborhood of an identified background pixel may be compared against an aggressiveness threshold. Responsive to the number of foreground pixels within a neighborhood of an identified background pixel not exceeding an aggressiveness threshold, the color of the identified background pixel may be changed to an average local background color. Alternatively, responsive to the number of background pixels within a neighborhood of an identified background pixel exceeding an aggressiveness threshold, the color of the identified background pixel may be changed to an average local background color. In embodiments, additional processes may be performed on the image including, but not limited to, color adjusting, filtering, image enhancing, compression, format conversion, watermarking, special effects, video editing, etc.
    Type: Grant
    Filed: August 31, 2007
    Date of Patent: May 3, 2011
    Assignee: Seiko Epson Corporation
    Inventors: Che-Bin Liu, Jing Xiao
  • Patent number: 7899248
    Abstract: Systems, apparatuses, and methods are described for performing fast segmentation of an image. In embodiments, an image may be segmented by generating a background mask, generating an edge mask, dilating the edge mask, and refining that edge mask by applying refinement operations that remove edge pixels from the edge mask. In embodiments, the refined edge mask may be used to generate a foreground mask.
    Type: Grant
    Filed: August 30, 2007
    Date of Patent: March 1, 2011
    Assignee: Seiko Epson Corporation
    Inventor: Che-Bin Liu
  • Patent number: 7899258
    Abstract: Disclosed are embodiments of systems and methods to generate a composite image from an captured image, such as from a whiteboard, chalkboard, paper, card, poster, sign, or the like. Systems and methods are disclosed for generating a foreground image layer and mask layer, which enables high-quality and high-ratio document compression. In embodiments, a foreground image layer and mask layer may be generated by identifying non-background pixels in the captured image.
    Type: Grant
    Filed: March 26, 2007
    Date of Patent: March 1, 2011
    Assignee: Seiko Epson Corporation
    Inventors: Che-Bin Liu, Anoop K. Bhattacharjya
  • Patent number: 7894689
    Abstract: Disclosed are embodiments of systems and methods to stitch two or more images together into a composite image. By finding matching point pairs for a pair of images, a homography transform may be obtained for the pair of images. The homography transform may be used to generate a composite image of the image pair. In an embodiment, the process of identifying a homography transform may be iterated. In an embodiment, when forming the composite image, the transformed foreground regions may be selected such that there is no intersection of foreground pixel regions. In an embodiment, foreground pixel regions on the border of an image may be removed. The resulting composite image is a larger image generated from the selected regions from the input images. In embodiments, the process may be repeated for sets of images with more than two images.
    Type: Grant
    Filed: May 31, 2007
    Date of Patent: February 22, 2011
    Assignee: Seiko Epson Corporation
    Inventors: Che-Bin Liu, Jing Xiao
  • Patent number: 7783117
    Abstract: Disclosed are embodiments of systems and methods to generate background and foreground images for a document, which enables high-quality and high-ratio document compression. In embodiments, high-accuracy layer processing enables text enhancement, paper color removal, and many other advanced image analysis and processing. Embodiments of the systems support several operation modes and its many parameters, such as layer compression ratios, image segmentation, and modulized image processing, may be adjusted to generate optimal compressed files for different purposes.
    Type: Grant
    Filed: March 26, 2007
    Date of Patent: August 24, 2010
    Assignee: Seiko Epson Corporation
    Inventors: Che-Bin Liu, Anoop K Bhattacharjya
  • Publication number: 20090136082
    Abstract: Disclosed are embodiments of systems and methods for embedding and/or extracting data from images. In embodiments, an image may be segmented into regions, and characters or other image groups within a segmented region may be determined to be embedding sites. A data vector may be embedded into a set of corresponding ordered embedding sites by representing each data element as different intensity values assigned to the pixels within one portion of an embedding site relative to the pixels in another portion of the embedding site. In embodiments, embedded data may be extracted from an image by extracting and decoding a set of bit values from a set of identified and ordered embedding sites.
    Type: Application
    Filed: November 27, 2007
    Publication date: May 28, 2009
    Inventors: Ali Zandifar, Che-Bin Liu, Jing Xiao
  • Publication number: 20090136080
    Abstract: Disclosed are embodiments of systems and methods for embedding and/or extracting data from images. In embodiments, an image may be segmented into regions, and characters or other image groups within a segmented region may be determined to be embedding sites. A data vector may be embedded into a set of corresponding ordered embedding sites by representing each data element as different intensity values assigned to the pixels within one portion of an embedding site relative to the pixels in another portion of the embedding site. In embodiments, embedded data may be extracted from an image by extracting and decoding a set of bit values from a set of identified and ordered embedding sites.
    Type: Application
    Filed: November 26, 2007
    Publication date: May 28, 2009
    Inventors: Ali Zandifar, Che-Bin Liu
  • Publication number: 20090129625
    Abstract: Disclosed are embodiments of systems and methods for embedding and/or extracting data from images. In embodiments, an image may be segmented into regions, and characters or other image groups within a segmented region may be determined to be embedding sites. A data vector may be embedded into a set of corresponding ordered embedding sites by representing each data element as different intensity values assigned to the pixels within one portion of an embedding site relative to the pixels in another portion of the embedding site. In embodiments, embedded data may be extracted from an image by extracting and decoding a set of bit values from a set of identified and ordered embedding sites.
    Type: Application
    Filed: November 21, 2007
    Publication date: May 21, 2009
    Inventors: Ali Zandifar, Che-Bin Liu, Jing Xiao
  • Publication number: 20090060330
    Abstract: Systems, apparatuses, and methods are described for performing fast segmentation of an image. In embodiments, an image may be segmented by generating a background mask, generating an edge mask, dilating the edge mask, and refining that edge mask by applying refinement operations that remove edge pixels from the edge mask. In embodiments, the refined edge mask may be used to generate a foreground mask.
    Type: Application
    Filed: August 30, 2007
    Publication date: March 5, 2009
    Inventor: Che-Bin Liu
  • Publication number: 20090060331
    Abstract: Disclosed are embodiments of systems and methods for suppressing the background of an image. In embodiments, the number of foreground pixels or background pixels within a neighborhood of an identified background pixel may be compared against an aggressiveness threshold. Responsive to the number of foreground pixels within a neighborhood of an identified background pixel not exceeding an aggressiveness threshold, the color of the identified background pixel may be changed to an average local background color. Alternatively, responsive to the number of background pixels within a neighborhood of an identified background pixel exceeding an aggressiveness threshold, the color of the identified background pixel may be changed to an average local background color. In embodiments, additional processes may be performed on the image including, but not limited to, color adjusting, filtering, image enhancing, compression, format conversion, watermarking, special effects, video editing, etc.
    Type: Application
    Filed: August 31, 2007
    Publication date: March 5, 2009
    Inventors: Che-Bin Liu, Jing Xiao
  • Publication number: 20080298718
    Abstract: Disclosed are embodiments of systems and methods to stitch two or more images together into a composite image. By finding matching point pairs for a pair of images, a homography transform may be obtained for the pair of images. The homography transform may be used to generate a composite image of the image pair. In an embodiment, the process of identifying a homography transform may be iterated. In an embodiment, when forming the composite image, the transformed foreground regions may be selected such that there is no intersection of foreground pixel regions. In an embodiment, foreground pixel regions on the border of an image may be removed. The resulting composite image is a larger image generated from the selected regions from the input images. In embodiments, the process may be repeated for sets of images with more than two images.
    Type: Application
    Filed: May 31, 2007
    Publication date: December 4, 2008
    Inventors: Che-Bin Liu, Jing Xiao
  • Publication number: 20070217701
    Abstract: Disclosed are embodiments of systems and methods to generate a composite image from an captured image, such as from a whiteboard, chalkboard, paper, card, poster, sign, or the like. Systems and methods are disclosed for generating a foreground image layer and mask layer, which enables high-quality and high-ratio document compression. In embodiments, a foreground image layer and mask layer may be generated by identifying non-background pixels in the captured image.
    Type: Application
    Filed: March 26, 2007
    Publication date: September 20, 2007
    Inventors: Che-Bin Liu, Anoop Bhattacharjya
  • Publication number: 20070189615
    Abstract: Disclosed are embodiments of systems and methods to generate background and foreground images for a document, which enables high-quality and high-ratio document compression. In embodiments, high-accuracy layer processing enables text enhancement, paper color removal, and many other advanced image analysis and processing. Embodiments of the systems support several operation modes and its many parameters, such as layer compression ratios, image segmentation, and modulized image processing, may be adjusted to generate optimal compressed files for different purposes.
    Type: Application
    Filed: March 26, 2007
    Publication date: August 16, 2007
    Inventors: Che-Bin Liu, Anoop Bhattacharjya
  • Patent number: 7095401
    Abstract: A method for determining a gesture includes determining a change in a background of an image from a plurality of images, determining a object in the image, determining a trajectory of the object through the plurality of images, and classifying a gesture according to the trajectory of the object.
    Type: Grant
    Filed: October 31, 2001
    Date of Patent: August 22, 2006
    Assignee: Siemens Corporate Research, Inc.
    Inventors: Che-Bin Liu, Visvanathan Ramesh, Bernhard Geiger
  • Publication number: 20020118880
    Abstract: A method for determining a gesture includes determining a change in a background of an image from a plurality of images, determining a object in the image, determining a trajectory of the object through the plurality of images, and classifying a gesture according to the trajectory of the object.
    Type: Application
    Filed: October 31, 2001
    Publication date: August 29, 2002
    Inventors: Che-Bin Liu, Visvanathan Ramesh, Bernhard Geiger