| 深度学习及其在图像物体分类与检测中的应用综述 |
| |
| 引用本文： | 刘栋,李素,曹志冬.深度学习及其在图像物体分类与检测中的应用综述[J].计算机科学,2016,43(12):13-23. |
| |
| 作者姓名： | 刘栋 李素 曹志冬 |
| |
| 作者单位： | 北京工商大学计算机与信息工程学院食品安全大数据技术北京市重点实验室 北京100048;中国科学院自动化研究所复杂系统管理与控制国家重点实验室 北京100190,北京工商大学计算机与信息工程学院食品安全大数据技术北京市重点实验室 北京100048,中国科学院自动化研究所复杂系统管理与控制国家重点实验室 北京100190 |
| |
| 基金项目： | 本文受国家自然科学基金项目(31101088,2,91224008),北京市教育委员会科技计划面上项目(KM201310011010)资助 |
| |
| 摘 要： | 传统的图像物体分类与检测算法及策略难以满足图像视频大数据在处理效率、性能和智能化等方面所提出的要求。深度学习通过模拟类似人脑的层次结构建立从低级信号到高层语义的映射,以实现数据的分级特征表达,具有强大的视觉信息处理能力,成为应对这一挑战的前沿技术和国内外研究热点。首先论述了深度学习的起源、发展历程及理论体系;然后分别围绕图像物体分类和检测,总结了近年来深度学习在视觉领域的发展；最后对深度学习及其在视觉领域目前存在的诸多问题以及后续的研究方向进行了分类探讨。
|
| 关 键 词： | 深度学习 特征表达 图像物体分类 图像物体检测 |
| 收稿时间： | 2016/5/31 0:00:00 |
| 修稿时间： | 9/1/2016 12:00:00 AM |
State-of-the-art on Deep Learning and its Application in Image Object Classification and Detection |
| |
| LIU Dong,LI Su and CAO Zhi-dong.State-of-the-art on Deep Learning and its Application in Image Object Classification and Detection[J].Computer Science,2016,43(12):13-23. |
| |
| Authors: | LIU Dong LI Su and CAO Zhi-dong |
| |
| Affiliation: | Beijing Key Laboratory of Big Data Technology of Food Fafety,School of Computer and Information Engineering, Beijing Technology and Business University,Beijing 100048,China;State Key Laboratory of Complex Systems Management and Control,Institute of Automation, Chinese Academy of Sciences,Bejing 100190,China,Beijing Key Laboratory of Big Data Technology of Food Fafety,School of Computer and Information Engineering, Beijing Technology and Business University,Beijing 100048,China and State Key Laboratory of Complex Systems Management and Control,Institute of Automation, Chinese Academy of Sciences,Bejing 100190,China |
| |
| Abstract: | For traditional algorithms and strategies on image object classification and detection is hard to face the Challenges from efficiency,performance and intelligent of processing of image video big data.Based on the simulation of a hierarchical structure existing in human brain,deep learning can establish the mapping between the low-level signals and the high-level semantics for achieving the hierarchical expression of data characteristic.Deep learning with powerful ablility for visual information processing becomes the cutting-edge technology and research hot spot in coping with the coming challenge.At first,in this paper the basic theory of deep learning was discussed.Then,around image object classification and detection,we respectively summarized the development of deep learning in the visual field recentely.Finally,deep learning and its current problems in the visual field and the subsequent research direction were discussed in a well-informed level. |
| |
| Keywords: | Deep learning Feature representations Image object classification Image object detection |
|
| 点击此处可从《计算机科学》浏览原始摘要信息 |
|
点击此处可从《计算机科学》下载全文 |
|
