CASIA OpenIR  > 类脑智能研究中心
HCNN: A Neural Network Model for Combining Local and Global Features Towards Human-Like Classification
Zhang, Tielin1; Zeng, Yi1,2; Xu, Bo1,2; Ceng Y(曾毅)
2016
发表期刊INTERNATIONAL JOURNAL OF PATTERN RECOGNITION AND ARTIFICIAL INTELLIGENCE
卷号30期号:1页码:1-19
文章类型Article
摘要Brain-inspired algorithms such as convolutional neural network (CNN) have helped machine vision systems to achieve state-of-the-art performance for various tasks (e.g. image classification). However, CNNs mainly rely on local features (e.g. hierarchical features of points and angles from images), while important global structured features such as contour features are lost. Global understanding of natural objects is considered to be essential characteristics that the human visual system follows, and for developing human-like visual systems, the lost of consideration from this perspective may lead to inevitable failure on certain tasks. Experimental results have proved that well-trained CNN classifier cannot correctly distinguish fooling images (in which some local features from the natural images are chaotically distributed) from natural images. For example, a picture that is composed of yellow-black bars will be recognized as school bus with very high confidence by CNN. On the contrary, human visual system focuses on both the texture and contour features to form representation of images and would not mistake them. In order to solve the upper problem, we propose a neural network model, named as histogram of oriented gradient (HOG) improved CNN (HCNN), that combines local and global features towards human-like classification based on CNN and HOG. The experimental results on MNIST datasets and part of ImageNet datasets show that HCNN outperforms traditional CNN for object classification with fooling images, which indicates the feasibility, accuracy and potential effectiveness of HCNN for solving image classification problem.
关键词Convolutional Neural Network Object Classification Histogram Of Oriented Gradient Human-like Performance
WOS标题词Science & Technology ; Technology
DOI10.1142/S0218001416550041
关键词[WOS]REPRESENTATION
收录类别SCI
语种英语
项目资助者Strategic Priority Research Program of the Chinese Academy of Sciences ; Beijing Municipality of Science and Technology
WOS研究方向Computer Science
WOS类目Computer Science, Artificial Intelligence
WOS记录号WOS:000367455900008
引用统计
被引频次:1[WOS]   [WOS记录]     [WOS相关记录]
文献类型期刊论文
条目标识符http://ir.ia.ac.cn/handle/173211/10363
专题类脑智能研究中心
通讯作者Ceng Y(曾毅)
作者单位1.Chinese Acad Sci, Inst Automat, Beijing 100190, Peoples R China
2.Chinese Acad Sci, CAS Ctr Excellence Brain Sci & Intelligence Techn, Shanghai 200031, Peoples R China
推荐引用方式
GB/T 7714
Zhang, Tielin,Zeng, Yi,Xu, Bo,et al. HCNN: A Neural Network Model for Combining Local and Global Features Towards Human-Like Classification[J]. INTERNATIONAL JOURNAL OF PATTERN RECOGNITION AND ARTIFICIAL INTELLIGENCE,2016,30(1):1-19.
APA Zhang, Tielin,Zeng, Yi,Xu, Bo,&曾毅.(2016).HCNN: A Neural Network Model for Combining Local and Global Features Towards Human-Like Classification.INTERNATIONAL JOURNAL OF PATTERN RECOGNITION AND ARTIFICIAL INTELLIGENCE,30(1),1-19.
MLA Zhang, Tielin,et al."HCNN: A Neural Network Model for Combining Local and Global Features Towards Human-Like Classification".INTERNATIONAL JOURNAL OF PATTERN RECOGNITION AND ARTIFICIAL INTELLIGENCE 30.1(2016):1-19.
条目包含的文件 下载所有文件
文件名称/大小 文献类型 版本类型 开放类型 使用许可
HCNN A Neural Networ(2104KB)期刊论文作者接受稿开放获取CC BY-NC-SA浏览 下载
个性服务
推荐该条目
保存到收藏夹
查看访问统计
导出为Endnote文件
谷歌学术
谷歌学术中相似的文章
[Zhang, Tielin]的文章
[Zeng, Yi]的文章
[Xu, Bo]的文章
百度学术
百度学术中相似的文章
[Zhang, Tielin]的文章
[Zeng, Yi]的文章
[Xu, Bo]的文章
必应学术
必应学术中相似的文章
[Zhang, Tielin]的文章
[Zeng, Yi]的文章
[Xu, Bo]的文章
相关权益政策
暂无数据
收藏/分享
文件名: HCNN A Neural Network Model for Combining Local and Global.pdf
格式: Adobe PDF
所有评论 (0)
暂无评论
 

除非特别说明,本系统中所有内容都受版权保护,并保留所有权利。