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)
Source PublicationINTERNATIONAL JOURNAL OF PATTERN RECOGNITION AND ARTIFICIAL INTELLIGENCE
2016
Volume30Issue:1Pages:1-19
SubtypeArticle
AbstractBrain-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.
KeywordConvolutional Neural Network Object Classification Histogram Of Oriented Gradient Human-like Performance
WOS HeadingsScience & Technology ; Technology
DOI10.1142/S0218001416550041
WOS KeywordREPRESENTATION
Indexed BySCI
Language英语
Funding OrganizationStrategic Priority Research Program of the Chinese Academy of Sciences ; Beijing Municipality of Science and Technology
WOS Research AreaComputer Science
WOS SubjectComputer Science, Artificial Intelligence
WOS IDWOS:000367455900008
Citation statistics
Cited Times:1[WOS]   [WOS Record]     [Related Records in WOS]
Document Type期刊论文
Identifierhttp://ir.ia.ac.cn/handle/173211/10363
Collection类脑智能研究中心
Corresponding AuthorCeng Y(曾毅)
Affiliation1.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
Recommended Citation
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.
Files in This Item: Download All
File Name/Size DocType Version Access License
HCNN A Neural Networ(2104KB)期刊论文作者接受稿开放获取CC BY-NC-SAView Download
Related Services
Recommend this item
Bookmark
Usage statistics
Export to Endnote
Google Scholar
Similar articles in Google Scholar
[Zhang, Tielin]'s Articles
[Zeng, Yi]'s Articles
[Xu, Bo]'s Articles
Baidu academic
Similar articles in Baidu academic
[Zhang, Tielin]'s Articles
[Zeng, Yi]'s Articles
[Xu, Bo]'s Articles
Bing Scholar
Similar articles in Bing Scholar
[Zhang, Tielin]'s Articles
[Zeng, Yi]'s Articles
[Xu, Bo]'s Articles
Terms of Use
No data!
Social Bookmark/Share
File name: HCNN A Neural Network Model for Combining Local and Global.pdf
Format: Adobe PDF
All comments (0)
No comment.
 

Items in the repository are protected by copyright, with all rights reserved, unless otherwise indicated.