Patents by Inventor Yudong Liang

Yudong Liang 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: 12277503
    Abstract: A system for image quality assessment of non-aligned images includes a first deep path portion of a convolutional neural network having a set of parameters and a second deep path portion of the convolutional neural network sharing a set of parameters with the first deep path convolutional neural network. Weights are shared between the first and second deep path convolutional neural networks to support extraction of a same set of features in each neural network pathway. Non-aligned reference and distorted images are respectively provided to the first and second deep paths of the convolutional neural network for processing. A concatenation layer is connected to both the first and second deep paths convolutional neural network, and a fully connected layer is connected to the concatenation layer to receive input from both the first and second deep paths of the convolutional neural network, generating an image quality assessment as a linear regressor and outputting an image quality score.
    Type: Grant
    Filed: October 16, 2023
    Date of Patent: April 15, 2025
    Assignee: DeepNorth Inc.
    Inventors: Jinjun Wang, Yudong Liang
  • Patent number: 12269253
    Abstract: A heat press machine includes a base, an extension arm and a heating plate. The base is provided with a first carrier plate and a second carrier plate, the extension arm is rotatably mounted on the base, the extension arm is provided with a lifting assembly, and the lifting assembly is connected to the heating plate and used for driving the heating plate to ascend and descend. A commodity to be pressed is fixed by disposing two carrier plates on the base, the movement of the heating plate above the two carrier plates is achieved by the rotatable extension arm, after the commodity on one of the carrier plates is pressed, the heating plate may be moved to be above the other carrier plate to press the commodity in processes of loading, unloading and laminating the commodity by an operator, thereby improving the printing efficiency.
    Type: Grant
    Filed: October 23, 2024
    Date of Patent: April 8, 2025
    Inventor: Yudong Liang
  • Publication number: 20250042147
    Abstract: A heat transfer machine includes a base, an extension arm and a heating plate. The base is provided with a first carrier plate and a second carrier plate, the extension arm is rotatably mounted on the base, the extension arm is provided with a lifting assembly, and the lifting assembly is connected to the heating plate and used for driving the heating plate to ascend and descend. A commodity to be transferred is fixed by disposing two carrier plates on the base, the movement of the heating plate above the two carrier plates is achieved by the rotatable extension arm, after the commodity on one of the carrier plates is transferred, the heating plate may be moved to be above the other carrier plate to transfer the commodity in processes of loading, unloading and laminating the commodity by an operator, thereby improving the printing efficiency.
    Type: Application
    Filed: October 23, 2024
    Publication date: February 6, 2025
    Inventor: Yudong LIANG
  • Publication number: 20240046105
    Abstract: A system for image quality assessment of non-aligned images includes a first deep path portion of a convolutional neural network having a set of parameters and a second deep path portion of the convolutional neural network sharing a set of parameters with the first deep path convolutional neural network. Weights are shared between the first and second deep path convolutional neural networks to support extraction of a same set of features in each neural network pathway. Non-aligned reference and distorted images are respectively provided to the first and second deep paths of the convolutional neural network for processing. A concatenation layer is connected to both the first and second deep paths convolutional neural network, and a fully connected layer is connected to the concatenation layer to receive input from both the first and second deep paths of the convolutional neural network, generating an image quality assessment as a linear regressor and outputting an image quality score.
    Type: Application
    Filed: October 16, 2023
    Publication date: February 8, 2024
    Inventors: Jinjun Wang, Yudong Liang
  • Patent number: 11816576
    Abstract: A system for image quality assessment of non-aligned images includes a first deep path portion of a convolutional neural network having a set of parameters and a second deep path portion of the convolutional neural network sharing a set of parameters with the first deep path convolutional neural network. Weights are shared between the first and second deep path convolutional neural networks to support extraction of a same set of features in each neural network pathway. Non-aligned reference and distorted images are respectively provided to the first and second deep paths of the convolutional neural network for processing. A concatenation layer is connected to both the first and second deep paths convolutional neural network, and a fully connected layer is connected to the concatenation layer to receive input from both the first and second deep paths of the convolutional neural network, generating an image quality assessment as a linear regressor and outputting an image quality score.
    Type: Grant
    Filed: July 20, 2021
    Date of Patent: November 14, 2023
    Assignee: DEEP NORTH, INC.
    Inventors: Jinjun Wang, Yudong Liang
  • Publication number: 20210350243
    Abstract: A system for image quality assessment of non-aligned images includes a first deep path portion of a convolutional neural network having a set of parameters and a second deep path portion of the convolutional neural network sharing a set of parameters with the first deep path convolutional neural network. Weights are shared between the first and second deep path convolutional neural networks to support extraction of a same set of features in each neural network pathway. Non-aligned reference and distorted images are respectively provided to the first and second deep paths of the convolutional neural network for processing. A concatenation layer is connected to both the first and second deep paths convolutional neural network, and a fully connected layer is connected to the concatenation layer to receive input from both the first and second deep paths of the convolutional neural network, generating an image quality assessment as a linear regressor and outputting an image quality score.
    Type: Application
    Filed: July 20, 2021
    Publication date: November 11, 2021
    Inventors: Jinjun Wang, Yudong Liang
  • Patent number: 11100402
    Abstract: A system for image quality assessment of non-aligned images includes a first deep path portion of a convolutional neural network having a set of parameters and a second deep path portion of the convolutional neural network sharing a set of parameters with the first deep path convolutional neural network. Weights are shared between the first and second deep path convolutional neural networks to support extraction of a same set of features in each neural network pathway. Non-aligned reference and distorted images are respectively provided to the first and second deep paths of the convolutional neural network for processing. A concatenation layer is connected to both the first and second deep paths convolutional neural network, and a fully connected layer is connected to the concatenation layer to receive input from both the first and second deep paths of the convolutional neural network, generating an image quality assessment as a linear regressor and outputting an image quality score.
    Type: Grant
    Filed: January 16, 2020
    Date of Patent: August 24, 2021
    Assignee: DEEP NORTH, INC.
    Inventors: Jinjun Wang, Yudong Liang
  • Publication number: 20200280115
    Abstract: An integrated filter system, including: a dielectric slab assembly; and a filter circuit arranged on the dielectric slab assembly, where the filter circuit includes a low-pass filter and a band-pass filter connected to one another in series. The present invention further discloses an antenna system. By means of the foregoing implementations, the filter system and the antenna system are integrated and miniaturized and have smaller weights, and the filter system and the antenna system have a simple structure and lower costs, and stable and reliable whole performance.
    Type: Application
    Filed: January 20, 2017
    Publication date: September 3, 2020
    Applicants: TONGYU COMMUNICATION INC., TONGYU COMMUNICATION INC.
    Inventors: Hui CAI, Pengbo WANG, Qi ZHOU, Jianzhao YU, Yudong LIANG, Qilue FU, Gang JU
  • Publication number: 20200234141
    Abstract: A system for image quality assessment of non-aligned images includes a first deep path portion of a convolutional neural network having a set of parameters and a second deep path portion of the convolutional neural network sharing a set of parameters with the first deep path convolutional neural network. Weights are shared between the first and second deep path convolutional neural networks to support extraction of a same set of features in each neural network pathway. Non-aligned reference and distorted images are respectively provided to the first and second deep paths of the convolutional neural network for processing. A concatenation layer is connected to both the first and second deep paths convolutional neural network, and a fully connected layer is connected to the concatenation layer to receive input from both the first and second deep paths of the convolutional neural network, generating an image quality assessment as a linear regressor and outputting an image quality score.
    Type: Application
    Filed: January 16, 2020
    Publication date: July 23, 2020
    Inventors: Jinjun Wang, Yudong Liang
  • Patent number: 10540589
    Abstract: A system for image quality assessment of non-aligned images includes a first deep path portion of a convolutional neural network having a set of parameters and a second deep path portion of the convolutional neural network sharing a set of parameters with the first deep path convolutional neural network. Weights are shared between the first and second deep path convolutional neural networks to support extraction of a same set of features in each neural network pathway. Non-aligned reference and distorted images are respectively provided to the first and second deep paths of the convolutional neural network for processing. A concatenation layer is connected to both the first and second deep paths convolutional neural network, and a fully connected layer is connected to the concatenation layer to receive input from both the first and second deep paths of the convolutional neural network, generating an image quality assessment as a linear regressor and outputting an image quality score.
    Type: Grant
    Filed: October 24, 2017
    Date of Patent: January 21, 2020
    Assignee: DEEP NORTH, INC.
    Inventors: Jinjun Wang, Yudong Liang
  • Publication number: 20190122115
    Abstract: A system for image quality assessment of non-aligned images includes a first deep path portion of a convolutional neural network having a set of parameters and a second deep path portion of the convolutional neural network sharing a set of parameters with the first deep path convolutional neural network. Weights are shared between the first and second deep path convolutional neural networks to support extraction of a same set of features in each neural network pathway. Non-aligned reference and distorted images are respectively provided to the first and second deep paths of the convolutional neural network for processing. A concatenation layer is connected to both the first and second deep paths convolutional neural network, and a fully connected layer is connected to the concatenation layer to receive input from both the first and second deep paths of the convolutional neural network, generating an image quality assessment as a linear regressor and outputting an image quality score.
    Type: Application
    Filed: October 24, 2017
    Publication date: April 25, 2019
    Inventors: Jinjun Wang, Yudong Liang
  • Patent number: D734879
    Type: Grant
    Filed: March 7, 2014
    Date of Patent: July 21, 2015
    Assignee: Zhejiang Shengui Lighting Co, Ltd.
    Inventors: Liang Chen, Yudong Liang, Yinxiao Zhu
  • Patent number: D982623
    Type: Grant
    Filed: October 21, 2021
    Date of Patent: April 4, 2023
    Assignee: Guangzhou Jingwushi Information Technology Co., Ltd.
    Inventors: Yudong Liang, De Zhang
  • Patent number: D1051189
    Type: Grant
    Filed: June 21, 2024
    Date of Patent: November 12, 2024
    Inventor: Yudong Liang