Patents by Inventor Su Wang

Su Wang 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).

  • Publication number: 20130243308
    Abstract: An integrated interactive segmentation with spatial constraint method utilizes a combination of several of the most popular online learning algorithms into one and implements a spatial constraint which defines a valid mask local to the user's given marks. Additionally, both supervised learning and statistical analysis are integrated, which are able to compensate each other. Once prediction and activation are obtained, pixel-wised multiplication is conducted to fully indicate how likely each pixel belongs to the foreground or background.
    Type: Application
    Filed: March 17, 2012
    Publication date: September 19, 2013
    Applicant: SONY CORPORATION
    Inventors: Su Wang, Shengyang Dai, Xun Xu, Akira Nakamura, Takeshi Ohashi, Jun Yokono
  • Publication number: 20130243277
    Abstract: Fluorescence in situ hybridization (FISH) enables the detection of specific DNA sequences in cell chromosomes by the use of selective staining. Due to the high sensitivity, FISH allows the use of multiple colors to detect multiple targets simultaneously. The target signals are represented as colored dots, and enumeration of these signals is called dot counting. Using a two-stage segmentation framework guarantees locating all potential dots including overlapped dots.
    Type: Application
    Filed: March 17, 2012
    Publication date: September 19, 2013
    Applicant: SONY CORPORATION
    Inventors: Su Wang, Xun Xu, Akira Nakamura
  • Publication number: 20130243289
    Abstract: An interactive segmentation framework for 3-D teeth CT volumetric data enables a user to segment an entire dental region or individual teeth depending upon the types of user input. Graph cuts-based interactive segmentation utilizes a user's scribbles which are collected on several 2-D representative CT slices and are expanded on those slices. Then, a 3-D distance transform is applied to the entire CT volume based on the expanded scribbles. Bony tissue enhancement is added before feeding 3-D CT raw image data into the graph cuts pipeline. The segmented teeth area is able to be directly utilized to reconstruct a 3-D virtual teeth model.
    Type: Application
    Filed: March 17, 2012
    Publication date: September 19, 2013
    Applicant: SONY CORPORATION
    Inventors: Su Wang, Shengyang Dai, Xun Xu, Akira Nakamura
  • Patent number: 8472718
    Abstract: Systems and methods for implementing a superpixel image segmentation technique using a boundary preserving distance metric are disclosed. The disclosed technique segments a digital image into superpixels comprising contiguous pixel regions sharing similar characteristics. Superpixel image segmentation techniques presented herein utilize a boundary preserving distance metric. A boundary preserving distance metric presented herein measures the similarity between two pixels of a digital image at least partially based on a boundary probability values of the two pixels and surrounding pixels.
    Type: Grant
    Filed: August 5, 2011
    Date of Patent: June 25, 2013
    Assignee: Sony Corporation
    Inventors: Xutao Lv, Su Wang, Shengyang Dai, Xun Xu, Akira Nakamura
  • Patent number: 8379994
    Abstract: Systems and methods for implementing a multi-label image recognition framework for classifying digital images are provided. The provided multi-label image recognition framework utilizes an iterative, multiple analysis path approach to model training and image classification tasks. A first iteration of the multi-label image recognition framework generates confidence maps for each label, which are shared by the multiple analysis paths to update the confidence maps in subsequent iterations. The provided multi-label image recognition framework permits model training and image classification tasks to be performed more accurately than conventional single-label image recognition frameworks.
    Type: Grant
    Filed: October 13, 2010
    Date of Patent: February 19, 2013
    Assignee: Sony Corporation
    Inventors: Shengyang Dai, Su Wang, Akira Nakamura, Takeshi Ohashi, Jun Yokono
  • Patent number: 8351676
    Abstract: Systems and methods for implementing a multi-step image recognition framework for classifying digital images are provided. The provided multi-step image recognition framework utilizes a gradual approach to model training and image classification tasks requiring multi-dimensional ground truths. A first step of the multi-step image recognition framework differentiates a first image region from a remainder image region. Each subsequent step operates on a remainder image region from the previous step. The provided multi-step image recognition framework permits model training and image classification tasks to be performed more accurately and in a less resource intensive fashion than conventional single-step image recognition frameworks.
    Type: Grant
    Filed: October 12, 2010
    Date of Patent: January 8, 2013
    Assignee: Sony Corporation
    Inventors: Shengyang Dai, Su Wang, Akira Nakamura, Takeshi Ohashi, Jun Yokono
  • Patent number: 8345976
    Abstract: Methods and systems disclosed herein provide the capability to automatically process digital pathology images quickly and accurately. According to one embodiment, an digital pathology image segmentation task may be divided into at least two parts. An image segmentation task may be carried out utilizing both bottom-up analysis to capture local definition of features and top-down analysis to use global information to eliminate false positives. In some embodiments, an image segmentation task is carried out using a “pseudo-bootstrapping” iterative technique to produce superior segmentation results. In some embodiments, the superior segmentation results produced by the pseudo-bootstrapping method are used as input in a second segmentation task that uses a combination of bottom-up and top-down analysis.
    Type: Grant
    Filed: August 6, 2010
    Date of Patent: January 1, 2013
    Assignee: Sony Corporation
    Inventors: Su Wang, Shengyang Dai, Akira Nakamura, Takeshi Ohashi, Jun Yokono
  • Publication number: 20120275703
    Abstract: Systems and methods for implementing a superpixel image segmentation technique using a boundary preserving distance metric are disclosed. The disclosed technique segments a digital image into superpixels comprising contiguous pixel regions sharing similar characteristics. Superpixel image segmentation techniques presented herein utilize a boundary preserving distance metric. A boundary preserving distance metric presented herein measures the similarity between two pixels of a digital image at least partially based on a boundary probability values of the two pixels and surrounding pixels.
    Type: Application
    Filed: August 5, 2011
    Publication date: November 1, 2012
    Inventors: Xutao Lv, Su Wang, Shengyang Dai, Xun Xu, Akira Nakamura
  • Patent number: 8295204
    Abstract: According to a particular embodiment, a method for automatically assigning dynamic IP addresses without user interaction includes maintaining at least one pool of unused IP addresses. An advertisement message is transmitted from a first network element to at least one additional network element in a transport ring. The advertisement message identifies the first network element as providing IP address assignment services. The IP address request message from a second network element in the transport ring is received at the first network element. In response to the IP address request message, an IP address is dynamically assigned from the at least one pool of unused IP addresses. The dynamically assigned IP address is transmitted from the first network element to the second network element.
    Type: Grant
    Filed: February 22, 2008
    Date of Patent: October 23, 2012
    Assignee: Fujitsu Limited
    Inventors: Richard J. Dunsmore, Albert V. Smith, Jr., Man Wing Fong, Joseph K. Nguyen, Su Wang
  • Patent number: 8263402
    Abstract: The present invention is directed to a method of separating oligodendrocyte cells or progenitor cells thereof from a mixed population of cells. It comprises selecting a promoter which functions only in the oligodendrocyte cells or progenitor cells thereof, introducing a nucleic acid molecule encoding a fluorescent protein under control of that promoter into the mixed population cells, allowing the oligodendrocyte cells or progenitor cells thereof to express the fluorescent protein, and separating the fluorescent cells from the mixed population cells, where the separated cells are the oligodendrocyte cells or progenitor cells thereof. The invention also relates to the isolated and enriched human oligodendrocyte cells or progenitor cells thereof.
    Type: Grant
    Filed: March 31, 1999
    Date of Patent: September 11, 2012
    Assignee: Cornell Research Foundation, Inc.
    Inventors: Steven A. Goldman, Su Wang
  • Publication number: 20120128237
    Abstract: Systems and methods for implementing a superpixel boosted top-down image recognition framework are provided. The framework utilizes superpixels comprising contiguous pixel regions sharing similar characteristics. Feature extraction methods described herein provide non-redundant image feature vectors for classification model building. The provided framework differentiates a digitized image into a plurality of superpixels. The digitized image is characterized through image feature extraction methods based on the plurality of superpixels. Image classification models are generated from the extracted image features and ground truth labels and may then be used to classify other digitized images.
    Type: Application
    Filed: November 22, 2010
    Publication date: May 24, 2012
    Inventors: Su Wang, Shengyang Dai, Akira Nakamura, Takeshi Ohashi, Jun Yokono
  • Publication number: 20120123831
    Abstract: A content recognition system operates in conjunction with a media hosting service to identify hosted media content and ownership rights associated with the hosted content. By applying melody recognition, the content recognition system can identify compositions embodied in hosted media content even when these compositions do not precisely match any known sound recording. Thus, the content recognition system is beneficially able to detect, for example, recorded cover performances and recorded live performances embodied in hosted media content. Once identified, ownership information is determined and the media hosting service can carry out appropriate rights management policies associated with the content such as monetizing or blocking the protected content.
    Type: Application
    Filed: November 12, 2010
    Publication date: May 17, 2012
    Applicant: Google Inc.
    Inventors: David G. King, George Salem, Yiling Su Wang, Matthew Wiseman
  • Publication number: 20120093396
    Abstract: Systems and methods for implementing a multi-label image recognition framework for classifying digital images are provided. The provided multi-label image recognition framework utilizes an iterative, multiple analysis path approach to model training and image classification tasks. A first iteration of the multi-label image recognition framework generates confidence maps for each label, which are shared by the multiple analysis paths to update the confidence maps in subsequent iterations. The provided multi-label image recognition framework permits model training and image classification tasks to be performed more accurately than conventional single-label image recognition frameworks.
    Type: Application
    Filed: October 13, 2010
    Publication date: April 19, 2012
    Inventors: Shengyang Dai, Su Wang, Akira Nakamura, Takeshi Ohashi, Jun Yokono
  • Publication number: 20120087556
    Abstract: Systems and methods for implementing a multi-step image recognition framework for classifying digital images are provided. The provided multi-step image recognition framework utilizes a gradual approach to model training and image classification tasks requiring multi-dimensional ground truths. A first step of the multi-step image recognition framework differentiates a first image region from a remainder image region. Each subsequent step operates on a remainder image region from the previous step. The provided multi-step image recognition framework permits model training and image classification tasks to be performed more accurately and in a less resource intensive fashion than conventional single-step image recognition frameworks.
    Type: Application
    Filed: October 12, 2010
    Publication date: April 12, 2012
    Inventors: Shengyang Dai, Su Wang, Akira Nakamura, Takeshi Ohashi, Jun Yokono
  • Publication number: 20120033862
    Abstract: Methods and systems disclosed herein provide the capability to automatically process digital pathology images quickly and accurately. According to one embodiment, an digital pathology image segmentation task may be divided into at least two parts. An image segmentation task may be carried out utilizing both bottom-up analysis to capture local definition of features and top-down analysis to use global information to eliminate false positives. In some embodiments, an image segmentation task is carried out using a “pseudo-bootstrapping” iterative technique to produce superior segmentation results. In some embodiments, the superior segmentation results produced by the pseudo-bootstrapping method are used as input in a second segmentation task that uses a combination of bottom-up and top-down analysis.
    Type: Application
    Filed: August 6, 2010
    Publication date: February 9, 2012
    Inventors: Su Wang, Shengyang Dai, Akira Nakamura, Takeshi Ohashi, Jun Yokono
  • Publication number: 20120033861
    Abstract: Systems and methods for implementing a hierarchical image recognition framework for classifying digital images are provided. The provided hierarchical image recognition framework utilizes a multi-layer approach to model training and image classification tasks. A first layer of the hierarchical image recognition framework generates first layer confidence scores, which are utilized by the second layer to produce a final recognition score. The provided hierarchical image recognition framework permits model training and image classification tasks to be performed more accurately and in a less resource intensive fashion than conventional single-layer image recognition frameworks. In some embodiments real-time operator guidance is provided for an image classification task.
    Type: Application
    Filed: August 6, 2010
    Publication date: February 9, 2012
    Inventors: Shengyang Dai, Su Wang, Akira Nakamura, Takeshi Ohashi, Jun Yokono
  • Publication number: 20110237929
    Abstract: Disclosed is a method and apparatus for detection of a bladder wall tumor. Layers of a bladder wall are created by magnetic resonance imaging. A group of voxels having a lowest intensity is identified in a layer and an energy function modification enlarges the layer of the bladder wall. A partial volume image segmentation obtains tissue type mixture percentages in each voxel near inner and outer borders of the bladder wall in the layer of the bladder wall to obtain a bladder wall thickness. A range of uncertainty at the inner and outer borders of the bladder wall is obtained, and integration is performed of the bladder wall thickness along a path starting at a point on the outer border and ending at a corresponding point on the inner border.
    Type: Application
    Filed: September 8, 2009
    Publication date: September 29, 2011
    Inventors: Zhengrong Liang, Su Wang, Chaijie Duan, Hongbin Zhu, Xianfeng Gu
  • Publication number: 20090213763
    Abstract: According to a particular embodiment, a method for automatically assigning dynamic IP addresses without user interaction includes maintaining at least one pool of unused IP addresses. An advertisement message is transmitted from a first network element to at least one additional network element in a transport ring. The advertisement message identifies the first network element as providing IP address assignment services. The IP address request message from a second network element in the transport ring is received at the first network element. In response to the IP address request message, an IP address is dynamically assigned from the at least one pool of unused IP addresses. The dynamically assigned IP address is transmitted from the first network element to the second network element.
    Type: Application
    Filed: February 22, 2008
    Publication date: August 27, 2009
    Inventors: Richard J. Dunsmore, Albert V. Smith, JR., Man Wing Fong, Joseph K. Nguyen, Su Wang
  • Publication number: 20060063225
    Abstract: A novel method is provided, for use within serological or screening assays, wherein microbial colonies are grown on filter membranes in multi-well plates. This process enables the colonies to be stained, imaged, and counted automatically using such automated systems as, e.g., computer and video-based imaging systems.
    Type: Application
    Filed: July 30, 2003
    Publication date: March 23, 2006
    Inventors: Michael Caulfield, Xu Liu, Su Wang
  • Patent number: D452949
    Type: Grant
    Filed: October 27, 2000
    Date of Patent: January 15, 2002
    Assignee: Happy Angel Corporation
    Inventor: Chen-Hsin Su Wang