-
公开(公告)号：US10607120B2
公开(公告)日：2020-03-31
申请号：US15942254
申请日：2018-03-30
Inventor： Xiang Bai , Feiyue Huang , Xiaowei Guo , Cong Yao , Baoguang Shi
Abstract: 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. Since the horizontal pooling operation can extract feature images identifying image horizontal direction features from the feature images, such that the well-trained CNN model can recognize an image of any size, thus expanding the applicable range of the well-trained CNN model in image recognition.
-
Patent Agency Ranking
公开(公告)号：US10599913B2
公开(公告)日：2020-03-24
申请号：US16509091
申请日：2019-07-11
Inventor： Shouhong Ding , Jilin Li , Chengjie Wang , Feiyue Huang , Yongjian Wu , Guofu Tan
Abstract: 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.
-
公开(公告)号：US10331940B2
公开(公告)日：2019-06-25
申请号：US15671041
申请日：2017-08-07
Inventor： Chengjie Wang , Jilin Li , Feiyue Huang , Kekai Sheng , Weiming Dong
IPC: G06K9/00
Abstract: 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.
-
公开(公告)号：US10068128B2
公开(公告)日：2018-09-04
申请号：US15438371
申请日：2017-02-21
Inventor： Chengjie Wang , Jilin Li , Feiyue Huang , Yongjian Wu
Abstract: 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.
-
公开(公告)号：US20180225552A1
公开(公告)日：2018-08-09
申请号：US15942254
申请日：2018-03-30
Inventor： Xiang Bai , Feiyue Huang , Xiaowei Guo , Cong Yao , Baoguang Shi
CPC classification number: G06K9/6267 , G06K9/42 , G06K9/4604 , G06K9/6256 , G06K9/627
Abstract: 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. Since the horizontal pooling operation can extract feature images identifying image horizontal direction features from the feature images, such that the well-trained CNN model can recognize an image of any size, thus expanding the applicable range of the well-trained CNN model in image recognition.
-
46.发明授权公开(公告)号：US09129395B2
公开(公告)日：2015-09-08
申请号：US14144348
申请日：2013-12-30
Inventor： Yuan Huang , Feiyue Huang , Yongjian Wu , Liqian Dong
Abstract: 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.
Abstract translation: 可以提供用于实现图形呈现引擎的方法。 在该方法中，可以提取第一图形处理界面和第二图形处理界面的渲染功能信息。 第一图形处理界面和第二图形处理界面可以被封装为图形呈现引擎界面。 可以根据渲染功能信息来定义图形渲染引擎接口的成员功能。 可以通过利用图形呈现引擎接口调用第一图形处理界面或第二图形处理界面来实现与成员函数相对应的呈现功能。
-
-
-
-
-
Search Results
46
records
(took 0.023 seconds)
