Knowledge Commons of Institute of Automation,CAS
HCNN: A Neural Network Model for Combining Local and Global Features Towards Human-Like Classification | |
Zhang, Tielin1; Zeng, Yi1,2; Xu, Bo1,2 | |
发表期刊 | INTERNATIONAL JOURNAL OF PATTERN RECOGNITION AND ARTIFICIAL INTELLIGENCE |
2016 | |
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 |
DOI | 10.1142/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 |
七大方向——子方向分类 | 类脑模型与计算 |
国重实验室规划方向分类 | 其他 |
引用统计 | |
文献类型 | 期刊论文 |
条目标识符 | http://ir.ia.ac.cn/handle/173211/10363 |
专题 | 脑图谱与类脑智能实验室_类脑认知计算 |
通讯作者 | Zeng, Yi |
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 |
第一作者单位 | 中国科学院自动化研究所 |
通讯作者单位 | 中国科学院自动化研究所 |
推荐引用方式 GB/T 7714 | Zhang, Tielin,Zeng, Yi,Xu, Bo. 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.(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 |
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。
修改评论