Patents by Inventor Zhimin Cao

Zhimin Cao 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: 10573049
    Abstract: An intuitive interface may allow users of a computing device (e.g., children, etc.) to create imaginary three dimensional (3D) objects of any shape using body gestures performed by the users as a primary or only input. A user may make motions while in front of an imaging device that senses movement of the user. The interface may allow first-person and/or third person interaction during creation of objects, which may map a body of a user to a body of an object presented by a display. In an example process, the user may start by scanning an arbitrary body gesture into an initial shape of an object. Next, the user may perform various gestures using his body, which may result in various edits to the object. After the object is completed, the object may be animated, possibly based on movements of the user.
    Type: Grant
    Filed: February 5, 2018
    Date of Patent: February 25, 2020
    Assignee: MICROSOFT TECHNOLOGY LICENSING, LLC
    Inventors: Xiang Cao, Yang Liu, Teng Han, Takaaki Shiratori, Nobuyuki Umetani, Yupeng Zhang, Xin Tong, Zhimin Ren
  • Patent number: 10451797
    Abstract: Provided is a few-mode optical fiber. The optical fiber includes: a core and a cladding enclosing the core. The cladding includes: a first inner cladding surrounding the core; a first high-refractive-index mode filter layer surrounding the first inner cladding; a second inner cladding surrounding the first high-refractive-index mode filter layer; a second high-refractive-index mode filter layer surrounding the second inner cladding; and an outer cladding surrounding the second high-refractive-index mode filter layer.
    Type: Grant
    Filed: December 18, 2017
    Date of Patent: October 22, 2019
    Assignees: STATE GRID JIANGXI ELECTRIC POWER COMPANY INFORMATION & TELECOMMUNICATION BRANCH, STATE GRID CORPORATION OF CHINA, JANGSU UNIVERSITY
    Inventors: Hua Wang, Mingyang Chen, Xiaosheng Wu, Renhua Li, Zhimin Cai, Guodong Cao, Shenyi Li, Luming Li, Jihai Yang, Pingping Fu, Meilan Zheng, Hui Xiao, Hongliang Chu, Jun Li, Fang Yin
  • Patent number: 10329858
    Abstract: The present invention relates to the field of petroleum extraction equipment, and discloses a coiled tubing unit, which comprises a vehicle body (T), a control cab (30), a coiled tubing reel (10) configured to wind coiled tubing, and a power skid (20) configured to supply power to the coiled tubing reel (10) and transported separately, wherein, the coiled tubing reel (10) and the control cab (30) are mounted on the vehicle body (T). With the coiled tubing unit provided in the present invention, the total length and total weight of the vehicle body on which the coiled tubing reel is mounted are smaller and can meet the requirements for transportation in regions where smaller vehicle dimensions and weight are specified for transportation when coiled tubing in large diameter and/or great length is transported, and the coiled tubing unit is adaptive to the operating habits, and can be deployed flexibly so that it can be used in a well field where the space is limited.
    Type: Grant
    Filed: September 24, 2018
    Date of Patent: June 25, 2019
    Assignee: JIANGHAN MACHINERY RESEARCH INSTITUTE LIMITED COMP
    Inventors: Huiqun He, Gao Yang, Shoujun Liu, Xuehui Li, Ge Xiong, Shibin Zhang, Jun Hao, Heping Cao, Wenyi Duan, Zhiqiang Hu, Jiafu Yan, Zhimin Yang, Fei Liu, Zhongcheng Zhou
  • Publication number: 20190162899
    Abstract: Provided is a few-mode optical fiber. The optical fiber includes: a core and a cladding enclosing the core. The cladding includes: a first inner cladding surrounding the core; a first high-refractive-index mode filter layer surrounding the first inner cladding; a second inner cladding surrounding the first high-refractive-index mode filter layer; a second high-refractive-index mode filter layer surrounding the second inner cladding; and an outer cladding surrounding the second high-refractive-index mode filter layer.
    Type: Application
    Filed: December 18, 2017
    Publication date: May 30, 2019
    Inventors: Hua WANG, Mingyang CHEN, Xiaosheng WU, Renhua LI, Zhimin CAI, Guodong CAO, Shenyi LI, Luming LI, Jihai YANG, Pingping FU, Meilan ZHENG, Hui XIAO, Hongliang CHU, Jun LI, Fang YIN
  • Patent number: 10268950
    Abstract: A disclosed face detection system (and method) is based on a structure of a convolutional neural network (CNN). One aspect concerns a method for automatically training a CNN for face detection. The training is performed such that balanced number of face images and non-face images are used for training by deriving additional face images from the face images. The training is also performed by adaptively changing a number of trainings of a stage according to automatic stopping criteria. Another aspect concerns a system for performing image detection by integrating data at different scales (i.e., different image extents) for better use of data in each scale. The system may include CNNs automatically trained using the method disclosed herein.
    Type: Grant
    Filed: November 15, 2014
    Date of Patent: April 23, 2019
    Assignee: BEIJING KUANGSHI TECHNOLOGY CO., LTD.
    Inventors: Qi Yin, Zhimin Cao, Kai Jia
  • Publication number: 20180211096
    Abstract: Provided are a living-body detection method and device and a computer program product, belonging to the technical field of face recognition. The living-body detection method comprises: detecting a facial movement from a photograph image; according to said detected facial movement, controlling the display of a virtual object on a display screen; and, if said virtual object satisfies predetermined conditions, determining that the face in said photographed image is a living-body face. By controlling virtual-object display on the basis of face movements and performing living-body detection according to virtual-object display, it is possible to effectively prevent an attack using such means as photograph, video, 3D face model, or face mask.
    Type: Application
    Filed: June 30, 2015
    Publication date: July 26, 2018
    Inventors: Zhimin CAO, Keqing CHEN, Kai JIA
  • Patent number: 9990555
    Abstract: The application relates to a video detection method, a video detection system, and a computer program product, which can implement liveness detection for a human body. The video detection method comprises: obtaining video data acquired by a video data acquisition device; determining a to-be-detected object based on the video data; obtaining a to-be-detected signal corresponding to the to-be-detected object; and determining whether the to-be-detected signal is a liveness physiological signal, wherein the to-be-detected signal is a frequency domain signal corresponding to the video data of the to-be-detected object.
    Type: Grant
    Filed: April 30, 2015
    Date of Patent: June 5, 2018
    Assignees: BEIJING KUANGSHI TECHNOLOGY CO., LTD., PINHOLE (BEIJING) TECHNOLOGY CO., LTD.
    Inventors: Haoqiang Fan, Zhimin Cao
  • Patent number: 9985963
    Abstract: Disclosed are a method and a system for authenticating liveness face, and a computer program product thereof, which belong to a field of face recognition technique. The method for authenticating liveness face comprises: generating a sequence of action instructions randomly; and determining a success of the authentication of the liveness face when face actions are determined to be matched with the sequence of action instructions sequentially. The authentication of the liveness face can be performed based on fine head actions, so that a cost for authenticating the liveness face is decreased, an accuracy of authentication of the liveness face is increased.
    Type: Grant
    Filed: February 15, 2015
    Date of Patent: May 29, 2018
    Assignees: BEIJING KUANGSHI TECHNOLOGY CO., LTD., PINHOLE (BEIJING) TECHNOLOGY CO., LTD.
    Inventors: Tao He, Kai Jia, Zhimin Cao
  • Publication number: 20160379072
    Abstract: The application relates to a video detection method, a video detection system, and a computer program product, which can implement liveness detection for a human body.
    Type: Application
    Filed: April 30, 2015
    Publication date: December 29, 2016
    Inventors: Haoqiang FAN, Zhimin CAO
  • Patent number: 9530071
    Abstract: A disclosed facial recognition system (and method) includes face parsing. In one approach, the face parsing is based on hierarchical interlinked multiscale convolutional neural network (HIM) to identify locations and/or footprints of components of a face image. The HIM generates multiple levels of image patches from different resolution images of the face image, where image patches for different levels have different resolutions. Moreover, the HIM integrates the image patches for different levels to generate interlinked image patches for different levels, where interlinked image patches for different levels have different resolutions. Furthermore, the HIM combines the interlinked image patches to identify refined locations and/or footprints of components.
    Type: Grant
    Filed: October 10, 2014
    Date of Patent: December 27, 2016
    Assignee: Beijing Kuangshi Technology Co., Ltd.
    Inventors: Qi Yin, Zhimin Cao, Yisu Zhou
  • Publication number: 20160373437
    Abstract: Disclosed are a method and a system for authenticating liveness face, and a computer program product thereof, which belong to a field of face recognition technique. The method for authenticating liveness face comprises: generating a sequence of action instructions randomly; and determining a success of the authentication of the liveness face when face actions are determined to be matched with the sequence of action instructions sequentially. The authentication of the liveness face can be performed based on fine head actions, so that a cost for authenticating the liveness face is decreased, an accuracy of authentication of the liveness face is increased.
    Type: Application
    Filed: February 15, 2015
    Publication date: December 22, 2016
    Inventors: Tao HE, Kai JIA, Zhimin CAO
  • Patent number: 9405960
    Abstract: Face hallucination using a bi-channel deep convolutional neural network (BCNN), which can adaptively fuse two channels of information. In one example, the BCNN is implemented to extract high level features from an input image. The extracted high level features are combined with low level details in the input image to produce the higher resolution image. Preferably, a proper coefficient is obtained to adaptively combine the high level features and the low level details.
    Type: Grant
    Filed: June 17, 2014
    Date of Patent: August 2, 2016
    Assignee: Beijing Kuangshi Technology Co., Ltd.
    Inventors: Qi Yin, Zhimin Cao, Erjin Zhou
  • Patent number: 9400918
    Abstract: A deep learning framework jointly optimizes the compactness and discriminative ability of face representations. The compact representation can be as compact as 32 bits and still produce highly discriminative performance. In another aspect, based on the extreme compactness, traditional face analysis tasks (e.g. gender analysis) can be effectively solved by a Look-Up-Table approach given a large-scale face data set.
    Type: Grant
    Filed: May 29, 2014
    Date of Patent: July 26, 2016
    Assignee: Beijing Kuangshi Technology Co., Ltd.
    Inventors: Qi Yin, Zhimin Cao, Yuning Jiang, Haoqiang Fan
  • Patent number: 9400922
    Abstract: The present invention overcomes the limitations of the prior art by performing facial landmark localization in a coarse-to-fine manner with a cascade of neural network levels, and enforcing geometric constraints for each of the neural network levels. In one approach, the neural network levels may be implemented with deep convolutional neural network. One aspect concerns a system for localizing landmarks on face images. The system includes an input for receiving a face image, and an output for presenting landmarks identified by the system. Neural network levels are coupled in a cascade from the input to the output for the system. Each neural network level produces an estimate of landmarks. The estimate of landmarks is more refined than an estimate of landmark of a previous neural network level.
    Type: Grant
    Filed: May 29, 2014
    Date of Patent: July 26, 2016
    Assignee: Beijing Kuangshi Technology Co., Ltd.
    Inventors: Erjin Zhou, Haoqiang Fan, Zhimin Cao, Yuning Jiang, Qi Yin
  • Patent number: 9400919
    Abstract: Face representation is a crucial step of face recognition systems. An optimal face representation should be discriminative, robust, compact, and very easy to implement. While numerous hand-crafted and learning-based representations have been proposed, considerable room for improvement is still present. A very easy-to-implement deep learning framework for face representation is presented. The framework bases on pyramid convolutional neural network (CNN). The pyramid CNN adopts a greedy-filter-and-down-sample operation, which enables the training procedure to be very fast and computation efficient. In addition, the structure of Pyramid CNN can naturally incorporate feature sharing across multi-scale face representations, increasing the discriminative ability of resulting representation.
    Type: Grant
    Filed: May 27, 2014
    Date of Patent: July 26, 2016
    Assignee: Beijing Kuangshi Technology Co., Ltd.
    Inventors: Qi Yin, Zhimin Cao, Yuning Jiang, Haoqiang Fan
  • Publication number: 20160140436
    Abstract: A disclosed face detection system (and method) is based on a structure of a convolutional neural network (CNN). One aspect concerns a method for automatically training a CNN for face detection. The training is performed such that balanced number of face images and non-face images are used for training by deriving additional face images from the face images. The training is also performed by adaptively changing a number of trainings of a stage according to automatic stopping criteria. Another aspect concerns a system for performing image detection by integrating data at different scales (i.e., different image extents) for better use of data in each scale. The system may include CNNs automatically trained using the method disclosed herein.
    Type: Application
    Filed: November 15, 2014
    Publication date: May 19, 2016
    Inventors: Qi Yin, Zhimin Cao, Kai Jia
  • Publication number: 20160104053
    Abstract: A disclosed facial recognition system (and method) includes face parsing. In one approach, the face parsing is based on hierarchical interlinked multiscale convolutional neural network (HIM) to identify locations and/or footprints of components of a face image, The HIM generates multiple levels of image patches from different resolution images of the face image, where image patches for different levels have different resolutions. Moreover, the HIM integrates the image patches for different levels to generate interlinked image patches for different levels, where interlinked image patches for different levels have different resolutions. Furthermore, the HIM combines the interlinked image patches to identify refined locations and/or footprints of components.
    Type: Application
    Filed: October 10, 2014
    Publication date: April 14, 2016
    Inventors: Qi Yin, Zhimin Cao, Yisu Zhou
  • Publication number: 20150363634
    Abstract: Face hallucination using a bi-channel deep convolutional neural network (BCNN), which can adaptively fuse two channels of information. In one example, the BCNN is implemented to extract high level features from an input image. The extracted high level features are combined with low level details in the input image to produce the higher resolution image. Preferably, a proper coefficient is obtained to adaptively combine the high level features and the low level details.
    Type: Application
    Filed: June 17, 2014
    Publication date: December 17, 2015
    Inventors: Qi Yin, Zhimin Cao, Erjin Zhou
  • Publication number: 20150347820
    Abstract: Face representation is a crucial step of face recognition systems. An optimal face representation should be discriminative, robust, compact, and very easy to implement. While numerous hand-crafted and learning-based representations have been proposed, considerable room for improvement is still present. A very easy-to-implement deep learning framework for face representation is presented. The framework bases on pyramid convolutional neural network (CNN). The pyramid CNN adopts a greedy-filter-and-down-sample operation, which enables the training procedure to be very fast and computation efficient. In addition, the structure of Pyramid CNN can naturally incorporate feature sharing across multi-scale face representations, increasing the discriminative ability of resulting representation.
    Type: Application
    Filed: May 27, 2014
    Publication date: December 3, 2015
    Inventors: Qi Yin, Zhimin Cao, Yuning Jiang, Haoqiang Fan
  • Publication number: 20150347819
    Abstract: A deep learning framework jointly optimizes the compactness and discriminative ability of face representations. The compact representation can be as compact as 32 bits and still produce highly discriminative performance. In another aspect, based on the extreme compactness, traditional face analysis tasks (e.g. gender analysis) can be effectively solved by a Look-Up-Table approach given a large-scale face data set.
    Type: Application
    Filed: May 29, 2014
    Publication date: December 3, 2015
    Inventors: Qi Yin, Zhimin Cao, Yuning Jiang, Haoqiang Fan