Patents by Inventor Feiyue Huang
Feiyue Huang 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: 20180225552Abstract: Disclosed are a training method and apparatus for a CNN model, which belong to the field of image recognition. The method comprises: performing a convolution operation, maximal pooling operation and horizontal pooling operation on training images, respectively, to obtain second feature images; determining feature vectors according to the second feature images; processing the feature vectors to obtain category probability vectors; according to the category probability vectors and an initial category, calculating a category error; based on the category error, adjusting model parameters; based on the adjusted model parameters, continuing the model parameters adjusting process, and using the model parameters when the number of iteration times reaches a pre-set number of times as the model parameters for the well-trained CNN model. After the convolution operation and maximal pooling operation on the training images on each level of convolution layer, a horizontal pooling operation is performed.Type: ApplicationFiled: March 30, 2018Publication date: August 9, 2018Applicant: TENCENT TECHNOLOGY (SHENZHEN) COMPANY LIMITEDInventors: Xiang Bai, Feiyue Huang, Xiaowei Guo, Cong Yao, Baoguang Shi
-
Publication number: 20180204094Abstract: The present disclosure discloses an image recognition method and apparatus, and belongs to the field of computer technologies. The method includes: extracting a local binary pattern (LBP) feature vector of a target image; calculating a high-dimensional feature vector of the target image according to the LBP feature vector; obtaining a training matrix, the training matrix being a matrix obtained by training images in an image library by using a joint Bayesian algorithm; and recognizing the target image according to the high-dimensional feature vector of the target image and the training matrix. The image recognition method and apparatus according to the present disclosure may combine LBP algorithm with a joint Bayesian algorithm to perform recognition, thereby improving the accuracy of image recognition.Type: ApplicationFiled: March 19, 2018Publication date: July 19, 2018Inventors: Shouhong Ding, Jilin Li, Chengjie Wang, Feiyue Huang, Yongjian Wu, Guofu Tan
-
Patent number: 9977997Abstract: Disclosed are a training method and apparatus for a CNN model, which belong to the field of image recognition. The method comprises: performing a convolution operation, maximal pooling operation and horizontal pooling operation on training images, respectively, to obtain second feature images; determining feature vectors according to the second feature images; processing the feature vectors to obtain category probability vectors; according to the category probability vectors and an initial category, calculating a category error; based on the category error, adjusting model parameters; based on the adjusted model parameters, continuing the model parameters adjusting process, and using the model parameters when the number of iteration times reaches a pre-set number of times as the model parameters for the well-trained CNN model. After the convolution operation and maximal pooling operation on the training images on each level of convolution layer, a horizontal pooling operation is performed.Type: GrantFiled: April 12, 2017Date of Patent: May 22, 2018Assignee: TENCENT TECHNOLOGY (SHENZHEN) COMPANY LIMITEDInventors: Xiang Bai, Feiyue Huang, Xiaowei Guo, Cong Yao, Baoguang Shi
-
Publication number: 20180032828Abstract: A face liveness detection method includes outputting a prompt to complete one or more specified actions in sequence within a specified time period, obtaining a face video, detecting a reference face image frame in the face video using a face detection method, locating a facial keypoint in the reference face image frame, tracking the facial keypoint in one or more subsequent face image frames, determining a state parameter of one of the one or more specified actions using a continuity analysis method according to the facial keypoint, and determining whether the one of the one or more specified actions is completed according to a continuity of the state parameter.Type: ApplicationFiled: October 9, 2017Publication date: February 1, 2018Inventors: Chengjie WANG, Jilin LI, Feiyue HUANG, Yongjian WU
-
Publication number: 20180012107Abstract: An image classification method is provided. The method includes: inputting a to-be-classified image into a plurality of neural network models; obtaining data output by multiple non-input layers specified by each neural network model to generate a plurality of image features corresponding to the plurality of neural network models; respectively inputting the plurality of corresponding image features into linear classifiers, each of the linear classifiers being trained by one of the plurality of neural network models for determining whether an image belongs to a preset class; obtaining, using each neural network model, a corresponding probability that the to-be-classified image comprises an object image of the preset class; and determining, according to each obtained probability, whether the to-be-classified image includes the object image of the preset class.Type: ApplicationFiled: September 13, 2017Publication date: January 11, 2018Inventors: Kun XU, Xiaowei GUO, Feiyue HUANG, Ruixin ZHANG, Juhong WANG, Shimin HU, Bin LIU
-
Publication number: 20180005017Abstract: Face model matrix training method, apparatus, and storage medium are provided. The method includes: obtaining a face image library, the face image library including k groups of face images, and each group of face images including at least one face image of at least one person, k>2, and k being an integer; separately parsing each group of the k groups of face images, and calculating a first matrix and a second matrix according to parsing results, the first matrix being an intra-group covariance matrix of facial features of each group of face images, and the second matrix being an inter-group covariance matrix of facial features of the k groups of face images; and training face model matrices according to the first matrix and the second matrix.Type: ApplicationFiled: September 13, 2017Publication date: January 4, 2018Inventors: Shouhong DING, Jilin LI, Chengjie WANG, Feiyue HUANG, Yongjian WU, Guofu TAN
-
Publication number: 20170337420Abstract: Disclosed are an evaluation method and an evaluation device for a facial key point positioning result. In some embodiments, the evaluation method includes: acquiring a facial image and one or more positioning result coordinates of a key point of the facial image; performing a normalization process on the positioning result coordinate and an average facial model to obtain a normalized facial image; and extracting a facial feature value of the normalized facial image and calculating an evaluation result based on the facial feature value and a weight vector.Type: ApplicationFiled: August 7, 2017Publication date: November 23, 2017Inventors: Chengjie WANG, Jilin LI, Feiyue HUANG, Kekai SHENG, Weiming DONG
-
Patent number: 9811894Abstract: An image processing method is provided. The method includes obtaining a human facial image and providing a total of n number of source images in a preconfigured file, where n is an integer greater than 2, and each source image corresponds to adjusting parameters for the source image in the preconfigured file. The method also includes generating a synthesized human facial image for the each source image by adjusting the human facial image based on the adjusting parameters corresponding to the source image in the preconfigured file, individually synthesizing the each source image and the synthesized human facial image for the each source image to obtain n number frames of synthesized images, and combining the n number frames of synthesized images into a dynamic image in a time order.Type: GrantFiled: May 16, 2016Date of Patent: November 7, 2017Assignee: TENCENT TECHNOLOGY (SHENZHEN) COMPANY LIMITEDInventors: Xiaoguang Yu, Shuguang Huang, Xiaowei Guo, Yang He, Chengzhao Zhang, Feiyue Huang, Zongqiao Yu
-
Publication number: 20170316598Abstract: A 3D human face reconstruction method and apparatus, and a server are provided. In some embodiments, the method includes determining feature points on an acquired 2D human face image; determining posture parameters of a human face according to the feature points, and adjusting a posture of a universal 3D human face model according to the posture parameters; determining points on the universal 3D human face model corresponding to the feature points, and adjusting the corresponding points in a sheltered status to obtain a preliminary 3D human face model; and performing deformation adjusting on the preliminary 3D human face model, and performing texture mapping on the deformed 3D human face model to obtain a final 3D human face.Type: ApplicationFiled: July 17, 2017Publication date: November 2, 2017Inventors: Chengjie Wang, Jilin Li, Feiyue Huang, Lei Zhang
-
Publication number: 20170308739Abstract: The embodiment of the present invention provides a human face recognition method and recognition system. The method includes that: a human face recognition request is acquired, and a statement is randomly generated according to the human face recognition request; audio data and video data returned by a user in response to the statement are acquired; corresponding voice information is acquired according to the audio data; corresponding lip movement information is acquired according to the video data; and when the lip movement information and the voice information satisfy a preset rule, the human face recognition request is permitted. By performing fit goodness matching between the lip movement information and voice information in a video for dynamic human face recognition, an attack by human face recognition with a real photo may be effectively avoided, and higher security is achieved.Type: ApplicationFiled: July 7, 2017Publication date: October 26, 2017Inventors: Chengjie WANG, Jilin LI, Hui NI, Yongjian WU, Feiyue HUANG
-
Publication number: 20170295177Abstract: An identity verification method performed at a terminal includes: displaying and/or playing in an audio form action guide information selected from a preset action guide information library, and collecting a corresponding set of action images within a preset time window; performing matching detection on the collected set of action images and the action guide information, to obtain a living body detection result indicating whether a living body exists in the collected set of action images; according to the living body detection result that indicates that a living body exists in the collected set of action images: collecting user identity information and performing verification according to the collected user identity information, to obtain a user identity information verification result; and determining the identity verification result according to the user identity information verification result.Type: ApplicationFiled: June 23, 2017Publication date: October 12, 2017Inventors: Feiyue HUANG, Jilin LI, Guofu TAN, Xiaoli JIANG, Dan WU, Junwu CHEN, Jianguo XIE, Wei GUO, Yihui LIU, Jiandong Xie
-
Publication number: 20170220904Abstract: Disclosed are a training method and apparatus for a CNN model, which belong to the field of image recognition. The method comprises: performing a convolution operation, maximal pooling operation and horizontal pooling operation on training images, respectively, to obtain second feature images; determining feature vectors according to the second feature images; processing the feature vectors to obtain category probability vectors; according to the category probability vectors and an initial category, calculating a category error; based on the category error, adjusting model parameters; based on the adjusted model parameters, continuing the model parameters adjusting process, and using the model parameters when the number of iteration times reaches a pre-set number of times as the model parameters for the well-trained CNN model. After the convolution operation and maximal pooling operation on the training images on each level of convolution layer, a horizontal pooling operation is performed.Type: ApplicationFiled: April 12, 2017Publication date: August 3, 2017Inventors: Xiang BAI, Feiyue HUANG, Xiaowei GUO, Cong YAO, Baoguang SHI
-
Patent number: 9710929Abstract: The present disclosure discloses method and apparatus for lossless image compression, and relates to the field of computer technologies. The method includes: removing ancillary information and redundant information from a picture having a predefined format in a preset manner; decompressing the picture to restore original picture data of the picture; and setting a compression parameter for the original picture data of the picture and compressing the original picture data of the picture into a picture having the same format before the picture decompression using the compression parameter. According to the present disclosure, ancillary data and redundant data in a picture are removed, and after decompression is performed on the picture, the picture is compressed again according to a preset compression parameter, so that based on lossless compression, a compression rate of the picture is increased, and storage space is saved.Type: GrantFiled: May 19, 2015Date of Patent: July 18, 2017Assignee: TENCENT TECHNOLOGY (SHENZHEN) COMPANY LIMITEDInventors: Feiyue Huang, Yunsheng Wu, Yongjian Wu, Shouhong Ding, Shang Wu
-
Publication number: 20170193287Abstract: The present disclosure discloses a living body identification method, an information generation method, and a terminal, and belongs to the field of biometric feature recognition. The method includes: providing lip language prompt information, the lip language prompt information including at least two target characters, and the at least two target characters being at least one of: characters of a same lip shape, characters of opposite lip shapes, or characters whose lip shape similarity is in a preset range; collecting at least two frame pictures; detecting whether lip changes of a to-be-identified object in the at least two frame pictures meet a preset condition, when the to-be-identified object reads the at least two target characters; and determining that the to-be-identified object is a living body, if the preset condition is met.Type: ApplicationFiled: March 17, 2017Publication date: July 6, 2017Applicant: Tencent Technology (Shenzhen) Company LimitedInventors: Jilin LI, Chengjie WANG, Feiyue HUANG, Yongjian WU, Hui NI, Ruixin ZHANG, Guofu TAN
-
Publication number: 20170161551Abstract: The present disclosure pertains to the field of image processing technologies and discloses a face key point positioning method and a terminal. The method includes: obtaining a face image; recognizing a face frame in the face image; determining positions of n key points of a target face in the face frame according to the face frame and a first positioning algorithm; performing screening to select, from candidate faces, a similar face whose positions of corresponding key points match the positions of the n key points of the target face; and determining positions of m key points of the similar face selected through screening according to a second positioning algorithm, m being a positive integer. In this way, the problem that positions of key points obtained by a terminal have relatively great deviations in the related technologies is resolved, thereby achieving an effect of improving accuracy of positioned positions of the key points.Type: ApplicationFiled: February 21, 2017Publication date: June 8, 2017Applicant: Tencent Technology (Shenzhen) Company LimitedInventors: Chengjie WANG, Jilin LI, Feiyue HUANG, Yongjian WU
-
Publication number: 20160260204Abstract: An image processing method is provided. The method includes obtaining a human facial image and providing a total of n number of source images in a preconfigured file, where n is an integer greater than 2, and each source image corresponds to adjusting parameters for the source image in the preconfigured file. The method also includes generating a synthesized human facial image for the each source image by adjusting the human facial image based on the adjusting parameters corresponding to the source image in the preconfigured file, individually synthesizing the each source image and the synthesized human facial image for the each source image to obtain n number frames of synthesized images, and combining the n number frames of synthesized images into a dynamic image in a time order.Type: ApplicationFiled: May 16, 2016Publication date: September 8, 2016Inventors: XIAOGUANG YU, SHUGUANG HUANG, XIAOWEI GUO, HE YANG, CHENGZHAO ZHANG, FEIYUE HUANG, ZONGQIAO YU
-
Patent number: 9432672Abstract: The present disclosure provides an image compression method and system. The method includes: receiving, by an access server, an image compression request submitted by a terminal; selecting, by the access server according to the image compression request's time information, an image compression server whose load is lower than a preset threshold, and sending the image compression request to the selected image compression server; compressing, by the selected image compression server, the images according to the image compression request, saving the compressed images, and forwarding URL addresses of the compressed images to the access server; and forwarding, by the access server, the URL addresses to the terminal. In the present disclosure, an image compression system processes an image compression request of a terminal, and performs load balancing automatically according to the load of various image compression servers in the system, thereby implementing automatic processing of mass images of the terminal.Type: GrantFiled: April 9, 2015Date of Patent: August 30, 2016Assignee: TENCENT TECHNOLOGY (SHENZHEN) COMPANY LIMITEDInventors: Feiyue Huang, Yongjian Wu, Feng Gao, Shouhong Ding, Qingliang Lin, Lu Zhang
-
Publication number: 20150287217Abstract: The present disclosure discloses method and apparatus for lossless image compression, and relates to the field of computer technologies. The method includes: removing ancillary information and redundant information from a picture having a predefined format in a preset manner; decompressing the picture to restore original picture data of the picture; and setting a compression parameter for the original picture data of the picture and compressing the original picture data of the picture into a picture having the same format before the picture decompression using the compression parameter. According to the present disclosure, ancillary data and redundant data in a picture are removed, and after decompression is performed on the picture, the picture is compressed again according to a preset compression parameter, so that based on lossless compression, a compression rate of the picture is increased, and storage space is saved.Type: ApplicationFiled: May 19, 2015Publication date: October 8, 2015Inventors: Feiyue HUANG, Yunsheng WU, Yongjian WU, Shouhong DING, Shang WU
-
Patent number: 9129395Abstract: A method for implementing a graphic rendering engine may be provided. In the method, rendering function information of a first graphic processing interface and a second graphic processing interface may be extracted. The first graphic processing interface and the second graphic processing interface may be encapsulated as a graphic rendering engine interface. Member functions of the graphic rendering engine interface may be defined according to the rendering function information. A rendering function corresponding to the member functions may be implemented by calling the first graphic processing interface or the second graphic processing interface with the graphic rendering engine interface.Type: GrantFiled: December 30, 2013Date of Patent: September 8, 2015Assignee: TENCENT TECHNOLOGY (SHENZHEN) COMPANY LIMITEDInventors: Yuan Huang, Feiyue Huang, Yongjian Wu, Liqian Dong
-
Publication number: 20150215625Abstract: The present disclosure provides an image compression method and system. The method includes: receiving, by an access server, an image compression request submitted by a terminal; selecting, by the access server according to the image compression request's time information, an image compression server whose load is lower than a preset threshold, and sending the image compression request to the selected image compression server; compressing, by the selected image compression server, the images according to the image compression request, saving the compressed images, and forwarding URL addresses of the compressed images to the access server; and forwarding, by the access server, the URL addresses to the terminal. In the present disclosure, an image compression system processes an image compression request of a terminal, and performs load balancing automatically according to the load of various image compression servers in the system, thereby implementing automatic processing of mass images of the terminal.Type: ApplicationFiled: April 9, 2015Publication date: July 30, 2015Inventors: Feiyue HUANG, Yongjian WU, Feng GAO, Shouhong DING, Qingliang LIN, Lu ZHANG