Download link: https://pan.baidu.com/s/1Ah4PXZOctqCu5A5Rnu3PBw Password: pncv
- Publisher: Electronics Industry Press; 1st Edition (February 1, 2018)
- Series Title: Machine Vision and Brain-like Intelligence
- Paperback: 280 pages
- Language: Simplified Chinese
- Format: 16
- ISBN: 7121335735, 9787121335730
- Barcode: 9787121335730
- Product size: 23.2 x 18.4 x 1.6 cm
- Item weight: 540 g
- Brand: Mammoth
- ASIN: B07989QN43
Editor's Choice
Introduction to face recognition, easy and fun, hands-on introduction, advanced and practical
explanation of important algorithms and implementation of face recognition. You
can learn to design your own face recognition system and image user interface
. The content is solid and weighty, based on the Chinese Academy of Sciences, key laboratories, etc. Research accumulation and actual combat with source code, with detailed annotations, become a master of face recognition
source code design in minutes
Celebrity Recommendation
As far as I know, this is the pioneering work of Chinese programming books for beginners in the field of face recognition. It is suitable for readers who are interested in face recognition but don't know where to start.
Tang Yuanyan, Chairman of IEEE-SMC International Pattern Recognition Technical Committee
About the Author
Wang Wenfeng, scholar of the Western Vision of the Chinese Academy of Sciences, academic director of the Brain-inspired Intelligence Research Center of the International Institute of Robotics (Hefei), Harbin Institute of Technology, member of the Cognitive Computing and Systems Special Committee of the Chinese Society of Automation, and a specialist in cognitive systems and information processing of the Chinese Society for Artificial Intelligence Member of the committee, member of several international conferences under IEEE and Springer and chairman of sub-sessions, reviewer of several SCI journals, reviewer of National Natural Science Foundation of China, and co-sponsor of DLG.
Li Daxiang is a master tutor of signal and information processing major in the School of Communication and Information Engineering, Xi'an University of Posts and Telecommunications. His main research fields are machine learning, computer vision and semantic analysis of video images, and he is engaged in criminal investigation in the Key Laboratory of Electronic Information Field Inspection and Application Technology of the Ministry of Public Security. Algorithm research of video image processing and analysis, as well as face detection and recognition algorithm research and system development in surveillance video.
Wang Dong, graduated from Tsinghua University majoring in physical electronics, is currently a master tutor, researcher of the Chinese Academy of Sciences, chairman of the Internet of Things Industry-University-Research International Alliance, director of the Mobile Grain Network Laboratory, visiting scholar and distinguished researcher at Stanford University, focusing on brain computer Research on interaction and brain-like intelligence.
Wang Qingxiang is an associate professor of the School of Medical Information Engineering, Guangzhou University of Traditional Chinese Medicine, and a youth science and technology pacesetter. The main research directions include biomedical signal acquisition and processing, pattern recognition and intelligent systems, medical image processing, artificial intelligence, etc., as the teaching of professional courses such as "Computer Composition Principles", "Digital Signal Processors and Applications", edited 1 textbook, and successfully Developed a series of image processing and expert system software.
Guo Yulan, lecturer at the School of Electronic Science, National University of Defense Technology, founder of the RoPS feature (Rotational Projection Statistical Feature) algorithm, winner of an excellent doctoral dissertation of the Chinese Society for Artificial Intelligence, member of the program committee of many international conferences such as AAAI, and more than 30 TPAMI Reviewer for international journals. His research direction is 3D vision and pattern recognition. He has published more than 50 academic papers in journals and conferences such as TPAMI and IJCV, and co-published 1 monograph.
The DLG-Deep Learning Research Group is formed by scholars in the fields of artificial intelligence and robotics and machine learning enthusiasts. As the third deputy editor of this book, the members are (in alphabetical order of surname): Deng Xiangyang (People's Liberation Army Naval Aviation University) ), Guo Liang (Shenzhen Xinwangda Electronics Co., Ltd.), He Jiaojiao (Kunming University of Science and Technology), Hong Yu (Hefei University of Technology), Liu Qingchang (study in Russia), Liu Shuaiqi (Hebei University), Ma Haifei (Guangdong Institute of Technology) , Ma Yakun (Shanghai Anhan Medical Technology Co., Ltd.), Shao Yongsheng (Xi'an Jiaotong University), Sheng Zhiqiang (Hefei University of Technology), Wang Jingwei (studying in Lianshuchengjin), Wang Ping (Nanjing University of Aeronautics and Astronautics), Wu Dagang (studying in the United States) ), Wu Peng (Yangtze River University), Xie Zhonghua (Tianjin University of Science and Technology), Yu Wei (Hubei University of Science and Technology), Yang Bo (Hangzhou Shengyuan Data Security Technology Co., Ltd.), Zeng Fanyu (University of Electronic Science and Technology), Zhang Feng (Electronic Technology) University), Zou Hui (Huaqiao University).
content
第1章 图像轮廓提取及人脸检测 1
1.1 第1阶段：入门 2
1.1.1 轮廓提取问题 2
1.1.2 轮廓提取函数 3
1.1.3 数学形态学运算 8
1.2 第2阶段：进阶 13
1.2.1 边缘检测算子 13
1.2.2 haar-like特征 23
1.3 第3阶段：实战 27
1.3.1 肤色概率建模 27
1.3.2 人脸检测实战 32
第2章 图像边界显示及人脸对齐 41
2.1 第1阶段：入门 42
2.1.1 边界显示问题 42
2.1.2 边界显示函数 43
2.2 第2阶段：进阶 55
2.2.1 图像边界处理 55
2.2.2 区域属性度量 63
2.3 第3阶段：实战 68
2.3.1 空间几何变换 68
2.3.2 人脸对齐原理 70
2.3.3 人脸对齐实战 77
第3章 图像采样编码及人脸重构 85
3.1 第1阶段：入门 86
3.1.1 采样编码问题 86
3.1.2 采样编码函数 87
3.2 第2阶段：进阶 103
3.2.1 人脸图像采样 103
3.2.2 人脸模板生成 115
3.3 第3阶段：实战 119
3.3.1 数据库初始化 119
3.3.2 遮挡区域验证 125
3.3.3 人脸重构实战 132
第4章 视频图像转换及人脸跟踪 140
4.1 第1阶段：入门 141
4.1.1 视频转换问题 141
4.1.2 视频转换函数 142
4.2 第2阶段：进阶 155
4.2.1 视频压缩感知 155
4.2.2 视频压缩跟踪 165
4.3 第3阶段：实战 167
4.3.1 混编环境配置 167
4.3.2 C++文件编译 169
4.3.3 人脸跟踪实战 176
第5章 类脑视觉认知及人脸识别 197
5.1 第1阶段：入门 198
5.1.1 类脑认知问题 198
5.1.2 类脑认知函数 200
5.2 第2阶段：进阶 214
5.2.1 类脑视觉认知 214
5.2.2 类脑特征计算 217
5.2.3 类脑特征学习 224
5.3 第3阶段：实战 232
5.3.1 深度学习实战 232
5.3.2 宽度学习实战 246
5.3.3 人脸识别实战 255
序言
本书旨在介绍人脸识别应用中的关键技术问题，并与作者主持和参与的中国科学院西部之光项目（XBBS-2014-16）、国家自然科学基金项目（61602499）和国家千人计划项目（Y474161）等的研究积累相结合，深入浅出、循序渐进地解析MATLAB人脸识别中的算法思想、识别原理与高级编程技巧，力图使读者具备大规模编程所需的技术模块设计和集成开发能力，并能基于本书所讲解的MATLAB人脸识别算法设计思想、图形用户界面设计与调试等内容，更深刻地理解真实场景下的人脸识别技术体系。