Study on the deep neural network of intelligent image detection and the improvement of elastic momentum on image recognition

doi:10.1166/jctn.2016.4994

OPT OpenIR > 光电跟踪与测量技术研究室

	Study on the deep neural network of intelligent image detection and the improvement of elastic momentum on image recognition
	Yue, Qi 1,2; Ma, Caiwen1
作者部门	光电测量技术实验室
	2016-05
发表期刊	Journal of Computational and Theoretical Nanoscience
ISSN	15461955
卷号	13 期号:5 页码:3326-3330
产权排序	1
摘要	Aiming at deep neural network of intelligent image detection, this paper proposes parameter learning method of exponential elastic momentum, applies this method in the pedestrian detection, the detection accuracy is 97.8%. In addition, this algorithm is compared with adaptive momentum methods, standard momentum gradient method and elastic momentum, and the accuracy obtained through this method increases by 2.6% and 6.5% on average respectively. Copyright © 2016 American Scientific Publishers All rights reserved.
关键词	Gradient Methods Image Recognition Object Recognition Target Tracking
DOI	10.1166/jctn.2016.4994
收录类别	EI
语种	英语
引用统计
文献类型	期刊论文
条目标识符	http://ir.opt.ac.cn/handle/181661/28233
专题	光电跟踪与测量技术研究室
通讯作者	Yue, Qi
作者单位	1.Xi'an Institute of Optics and Precision Mechanic, Xi'an; 710119, China 2.University of Chinese Academy of Sciences, Beijing; 100039, China
推荐引用方式 GB/T 7714	Yue, Qi,Ma, Caiwen. Study on the deep neural network of intelligent image detection and the improvement of elastic momentum on image recognition[J]. Journal of Computational and Theoretical Nanoscience,2016,13(5):3326-3330.
APA	Yue, Qi,&Ma, Caiwen.(2016).Study on the deep neural network of intelligent image detection and the improvement of elastic momentum on image recognition.Journal of Computational and Theoretical Nanoscience,13(5),3326-3330.
MLA	Yue, Qi,et al."Study on the deep neural network of intelligent image detection and the improvement of elastic momentum on image recognition".Journal of Computational and Theoretical Nanoscience 13.5(2016):3326-3330.

条目包含的文件
文件名称/大小	文献类型	版本类型	开放类型	使用许可
Study on the deep ne（615KB）	期刊论文	作者接受稿	限制开放	CC BY-NC-SA	请求全文