公开(公告)号：US10713532B2

公开(公告)日：2020-07-14

申请号：US15925028

申请日：2018-03-19

Applicant: TENCENT TECHNOLOGY (SHENZHEN) COMPANY LIMITED

Inventor： Shouhong Ding ,  Jilin Li ,  Chengjie Wang ,  Feiyue Huang ,  Yongjian Wu ,  Guofu Tan

IPC: G06K9/62 ,  G06K9/00 ,  G06K9/46

Abstract: 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.

公开(公告)号：US20180204094A1

公开(公告)日：2018-07-19

申请号：US15925028

申请日：2018-03-19

Applicant: TENCENT TECHNOLOGY (SHENZHEN) COMPANY LIMITED

Inventor： Shouhong Ding ,  Jilin Li ,  Chengjie Wang ,  Feiyue Huang ,  Yongjian Wu ,  Guofu Tan

IPC: G06K9/62 ,  G06K9/00

Abstract: 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.

公开(公告)号：US09710929B2

公开(公告)日：2017-07-18

申请号：US14716557

申请日：2015-05-19

Applicant: Tencent Technology (Shenzhen) Company Limited

Inventor： Feiyue Huang ,  Yunsheng Wu ,  Yongjian Wu ,  Shouhong Ding ,  Shang Wu

IPC: G06T9/00 ,  H04N19/40 ,  H04N19/103 ,  H04N19/119 ,  H04N19/186 ,  H04N19/44 ,  H04N19/85

CPC classification number: G06T9/00 ,  H04N19/103 ,  H04N19/119 ,  H04N19/186 ,  H04N19/40 ,  H04N19/44 ,  H04N19/85

Abstract: 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.

公开(公告)号：US09432672B2

公开(公告)日：2016-08-30

申请号：US14682951

申请日：2015-04-09

Applicant: Tencent Technology (Shenzhen) Company Limited

Inventor： Feiyue Huang ,  Yongjian Wu ,  Feng Gao ,  Shouhong Ding ,  Qingliang Lin ,  Lu Zhang

IPC: G06K9/00 ,  H04N19/136 ,  H04L29/08

CPC classification number: H04N19/136 ,  H04L67/02 ,  H04L67/1004 ,  H04L67/1008 ,  H04L67/1034 ,  H04L67/2828

Abstract: 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.

Abstract translation: 本公开提供了一种图像压缩方法和系统。 该方法包括：由接入服务器接收由终端提交的图像压缩请求; 由访问服务器根据图像压缩请求的时间信息选择其负载低于预设阈值的图像压缩服务器，并将图像压缩请求发送到所选择的图像压缩服务器; 通过选择的图像压缩服务器根据图像压缩请求压缩图像，保存压缩图像，并将压缩图像的URL地址转发到接入服务器; 并由接入服务器转发到终端的URL地址。 在本公开中，图像压缩系统处理终端的图像压缩请求，并且根据系统中的各种图像压缩服务器的负载自动执行负载平衡，从而实现终端的质量图像的自动处理。

公开(公告)号：US09325996B2

公开(公告)日：2016-04-26

申请号：US14713506

申请日：2015-05-15

Applicant: Tencent Technology (Shenzhen) Company Limited

Inventor： Shouhong Ding ,  Chuannan Wang ,  Jia Wang ,  Baolong Yang ,  Zhifeng Xie ,  Shang Wu

IPC: H04N19/126 ,  H04N19/172 ,  H04N19/196 ,  H04N19/12 ,  H04N19/154 ,  H04N19/192

CPC classification number: H04N19/126 ,  H04N19/12 ,  H04N19/154 ,  H04N19/172 ,  H04N19/192 ,  H04N19/196 ,  H04N19/197

Abstract: The present disclosure discloses method and apparatus for image compression. The method includes: acquiring a threshold of a similarity score of an image; acquiring a first quality factor of the image, a first similarity score corresponding to the first quality factor, a second quality factor of the image, and a second similarity score corresponding to the second quality factor; obtaining a functional relationship between quality factor and similarity score of the image by means of curve fitting using the first quality factor, the first similarity score, the second quality factor, and the second similarity score; determining an optimum quality factor of the image according to the functional relationship between the quality factor and the similarity score and the threshold of the similarity score; and compressing the image according to the determined optimum quality factor. With the present disclosure, iterations in image compression can be completed in a very short time.

Abstract translation: 本公开公开了用于图像压缩的方法和装置。 该方法包括：获取图像的相似性得分的阈值; 获得图像的第一品质因子，对应于第一品质因子的第一相似度得分，图像的第二品质因子和对​​应于第二品质因子的第二相似度得分; 通过使用第一品质因子，第一相似度得分，第二品质因子和第二相似性得分的曲线拟合来获得图像的质量因子和相似性得分之间的函数关系; 根据质量因子与相似度得分和相似性得分的阈值之间的函数关系确定图像的最优质量因子; 并根据所确定的最佳质量因子压缩图像。 根据本公开，可以在非常短的时间内完成图像压缩中的迭代。