| 图像理解中的卷积神经网络 |
| |
| 引用本文： | 常亮, 邓小明, 周明全, 武仲科, 袁野, 杨硕, 王宏安. 图像理解中的卷积神经网络. 自动化学报, 2016, 42(9): 1300-1312. doi: 10.16383/j.aas.2016.c150800 |
| |
| 作者姓名： | 常亮 邓小明 周明全 武仲科 袁野 杨硕 王宏安 |
| |
| 作者单位： | 1.北京师范大学信息科学与技术学院 北京 100875;;2.教育部虚拟现实应用工程研究中心 北京 100875;;3.中国科学院软件研究所人机交互北京市重点实验室 北京 100190;;4.中国科学院大学计算机与控制学院 北京 100049 |
| |
| 基金项目： | 国家自然科学基金（61402040，61473276），中国科学院青年创新促进会资助 |
| |
| 摘 要： | 近年来，卷积神经网络（Convolutional neural networks，CNN）已在图像理解领域得到了广泛的应用，引起了研究者的关注. 特别是随着大规模图像数据的产生以及计算机硬件（特别是GPU）的飞速发展，卷积神经网络以及其改进方法在图像理解中取得了突破性的成果，引发了研究的热潮. 本文综述了卷积神经网络在图像理解中的研究进展与典型应用. 首先，阐述卷积神经网络的基础理论;然后，阐述其在图像理解的具体方面，如图像分类与物体检测、人脸识别和场景的语义分割等的研究进展与应用.
|
| 关 键 词： | 卷积神经网络 图像理解 深度学习 图像分类 物体检测 |
| 收稿时间： | 2015-12-11 |
Convolutional Neural Networks in Image Understanding |
| |
| CHANG Liang, DENG Xiao-Ming, ZHOU Ming-Quan, WU Zhong-Ke, YUAN Ye, YANG Shuo, WANG Hong-An. Convolutional Neural Networks in Image Understanding. ACTA AUTOMATICA SINICA, 2016, 42(9): 1300-1312. doi: 10.16383/j.aas.2016.c150800 |
| |
| Authors: | CHANG Liang DENG Xiao-Ming ZHOU Ming-Quan WU Zhong-Ke YUAN Ye YANG Shuo WANG Hong-An |
| |
| Affiliation: | 1. College of Information Science and Technology, Beijing Normal University, Beijing 100875;;2. Engineering Research Center of Virtual Reality and Applications, Ministry of Education, Beijing 100875;;3. Beijing Key Laboratory of Human-Computer Interactions, Institute of Software, Chinese Academy of Sciences, Beijing 100190;;4. School of Computer and Control Engineering, University of Chinese Academy of Sciences, Beijing 100049 |
| |
| Abstract: | Convolutional neural networks (CNN) have been widely applied to image understanding, and they have arose much attention from researchers. Specifically, with the emergence of large image sets and the rapid development of GPUs, convolutional neural networks and their improvements have made breakthroughs in image understanding, bringing about wide applications into this area. This paper summarizes the up-to-date research and typical applications for convolutional neural networks in image understanding. We firstly review the theoretical basis, and then we present the recent advances and achievements in major areas of image understanding, such as image classification, object detection, face recognition, semantic image segmentation etc. |
| |
| Keywords: | Convolutional neural networks (CNN) image understanding deep learning image classification object detection |
|
| 点击此处可从《自动化学报》浏览原始摘要信息 |
|
点击此处可从《自动化学报》下载全文 |
|
