Patents by Inventor Ningqing Liang
Ningqing 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: 10438056Abstract: The present invention relates to a face recognition system and a face recognition method, mainly comprising a lighting preprocessing module, a feature generation module, a facial feature library module, and a feature matching and recognition module. In the face recognition method, the inputted face image is first light-difference optimized by means of the lighting preprocessing module, then a feature vector of the face image is generated by means of the feature generation module; then, the feature vector to be recognized is matched with all of the feature vectors in the feature library and computed to arrive at an identity result corresponding to the feature vector to be recognized. In the technical solutions of the present invention, the identity of a face image to be recognized may be determined in real time for a system whose computing resources are limited, using a short period of time and having high accuracy.Type: GrantFiled: June 21, 2016Date of Patent: October 8, 2019Assignee: YUTOU TECHNOLOGY (HANGZHOU) CO., LTD.Inventors: Ningqing Liang, Hongxin Zhang
-
Patent number: 10292232Abstract: Disclosed is a light and display content integration method, applied to a display device. The display device is an integrated screen, comprising a display area and a light area. The light area is illuminated by an LED array located behind the display area and around a periphery of the display area. The method is configured to integrate, according to an input signal, display content of the display area and a display status of the LED array. The LED array comprises a plurality of light assembly units. The display area is partitioned into a plurality of video regions according to the amount of the light assembly units, and each of the video regions corresponds to one of the light assembly units. The present invention controls, according to different input signals, an output of a corresponding light signal and display signal by analyzing a type of the input signals.Type: GrantFiled: June 22, 2016Date of Patent: May 14, 2019Assignee: YUTOU TECHNOLOGY (HANGZHOU) CO. LTD.Inventors: Ningqing Liang, Gangying Du
-
Publication number: 20180203333Abstract: Disclosed is a fusion and display system, which comprises: a structure positioning plate (6); a screen (5) fixed on the structure positioning plate (6); a projection unit (2) arranged on the structure positioning plate (6), for projecting image light to the back of the screen (5); a lighting unit (3) arranged on the structure positioning plate (6), for projecting light rays to the back of the screen (5). The light projected by the projection unit (2) is located inside the light projected by the lighting units (3). A control unit (1) is respectively connected to the projection unit (2) and the lighting units (3), for receiving an input signal and parsing the input signal to control the projected image of the projection unit (2) and the working states of the lighting units (3).Type: ApplicationFiled: June 22, 2016Publication date: July 19, 2018Inventors: Gangying DU, Ningqing LIANG
-
Publication number: 20180199410Abstract: Disclosed is a light and display content integration method, applied to a display device. The display device is an integrated screen, comprising a display area and a light area. The light area is illuminated by an LED array located behind the display area and around a periphery of the display area. The method is configured to integrate, according to an input signal, display content of the display area and a display status of the LED array. The LED array comprises a plurality of light assembly units. The display area is partitioned into a plurality of video regions according to the amount of the light assembly units, and each of the video regions corresponds to one of the light assembly units. The present invention controls, according to different input signals, an output of a corresponding light signal and display signal by analyzing a type of the input signals.Type: ApplicationFiled: June 22, 2016Publication date: July 12, 2018Inventors: Ningqing Liang, Gangying Du
-
Publication number: 20180121714Abstract: The present invention relates to a face recognition system and a face recognition method, mainly comprising a lighting preprocessing module, a feature generation module, a facial feature library module, and a feature matching and recognition module. In the face recognition method, the inputted face image is first light-difference optimized by means of the lighting preprocessing module, then a feature vector of the face image is generated by means of the feature generation module; then, the feature vector to be recognized is matched with all of the feature vectors in the feature library and computed to arrive at an identity result corresponding to the feature vector to be recognized. In the technical solutions of the present invention, the identity of a face image to be recognized may be determined in real time for a system whose computing resources are limited, using a short period of time and having high accuracy.Type: ApplicationFiled: June 21, 2016Publication date: May 3, 2018Inventors: Ningqing LIANG, Hongxin ZHANG
-
Patent number: 9875391Abstract: The invention discloses an image recognition system, comprising: a robot having an image collection module configured to drive an image collection module to collect an image in a view of the robot by the image collection drive module; a light source configured to supplement light when the image collection module collecting an image; a face detection module configured to locate a face image in an image according to the image collected by the image collection module; a face recognition module configured to implement a preprocessing for the located face image, then the preprocessed face image being compared with an image feature information of a known identity in a database, to determine an identity information and a confidence probability of the present face image. The invention can identify a face based on a fixed face pose, and it can identify a face based on a local or web server database.Type: GrantFiled: June 12, 2015Date of Patent: January 23, 2018Assignee: Yutou Technology (Hangzhou) Co., Ltd.Inventors: Ningqing Liang, Mingxiu Chen, Hongxin Zhang
-
Publication number: 20160307027Abstract: The invention discloses an image recognition system, comprising: a robot having an image collection module configured to drive an image collection module to collect an image in a view of the robot by the image collection drive module; a light source configured to fill the light when the image collection module collecting an image; a face detection module configured to locate a face image in an image according to the image collected by the image collection module; a face recognition module configured to implement a preprocessing for the located face image, then the preprocessed face image being compared with an image feature information of a known identity in a database, to determine an identity information and a confidence rate of the present face image. The invention can identify a face based on a fixed face pose, and it can identify a face based on a local or web server database.Type: ApplicationFiled: June 12, 2015Publication date: October 20, 2016Inventors: Ningqing Liang, Mingxiu Chen, Hongxin Zhang
-
Patent number: 9104945Abstract: Detecting a specific image applicable at a website includes detecting an existence of a frame of the specific image. The specific image applicable at the website is obtained. An edge characteristic value of each pixel of the image is calculated. A pixel whose edge characteristic value is a local maximum value is found along a slope direction of each pixel. When the edge characteristic value of the found pixel is larger than a preset characteristic value threshold, a preset color is used to fill the pixel. The specific image is scanned. An amount of pixels whose color is the preset color at each scanning line of the specific image is counted. When the amount of such pixels at a scanning line is larger than a preset number threshold, a line where the scanning line locates is determined as an edge line of the frame.Type: GrantFiled: June 23, 2014Date of Patent: August 11, 2015Assignee: Alibaba Group Holding LimitedInventors: Ningqing Liang, Feijun Jiang, Zengming Zhang, Depin Chen
-
Publication number: 20140376806Abstract: Detecting a specific image applicable at a website includes detecting an existence of a frame of the specific image. The specific image applicable at the website is obtained. An edge characteristic value of each pixel of the image is calculated. A pixel whose edge characteristic value is a local maximum value is found along a slope direction of each pixel. When the edge characteristic value of the found pixel is larger than a preset characteristic value threshold, a preset color is used to fill the pixel. The specific image is scanned. An amount of pixels whose color is the preset color at each scanning line of the specific image is counted. When the amount of such pixels at a scanning line is larger than a preset number threshold, a line where the scanning line locates is determined as an edge line of the frame.Type: ApplicationFiled: June 23, 2014Publication date: December 25, 2014Inventors: Ningqing Liang, Feijun Jiang, Zengming Zhang, Depin Chen