Feature Coding in Image Classification: A Comprehensive Study | |
Huang, Yongzhen; Wu, Zifeng; Wang, Liang; Tan, Tieniu | |
发表期刊 | IEEE TRANSACTIONS ON PATTERN ANALYSIS AND MACHINE INTELLIGENCE |
2014-03-01 | |
卷号 | 36期号:3页码:493-506 |
文章类型 | Article |
摘要 | Image classification is a hot topic in computer vision and pattern recognition. Feature coding, as a key component of image classification, has been widely studied over the past several years, and a number of coding algorithms have been proposed. However, there is no comprehensive study concerning the connections between different coding methods, especially how they have evolved. In this paper, we first make a survey on various feature coding methods, including their motivations and mathematical representations, and then exploit their relations, based on which a taxonomy is proposed to reveal their evolution. Further, we summarize the main characteristics of current algorithms, each of which is shared by several coding strategies. Finally, we choose several representatives from different kinds of coding approaches and empirically evaluate them with respect to the size of the codebook and the number of training samples on several widely used databases (15-Scenes, Caltech-256, PASCAL VOC07, and SUN397). Experimental findings firmly justify our theoretical analysis, which is expected to benefit both practical applications and future research. |
关键词 | Image Classification Feature Coding Bag-of-features |
WOS标题词 | Science & Technology ; Technology |
关键词[WOS] | TEXTURE ; REGIONS |
收录类别 | SCI |
语种 | 英语 |
WOS研究方向 | Computer Science ; Engineering |
WOS类目 | Computer Science, Artificial Intelligence ; Engineering, Electrical & Electronic |
WOS记录号 | WOS:000331450100008 |
引用统计 | |
文献类型 | 期刊论文 |
条目标识符 | http://ir.ia.ac.cn/handle/173211/3799 |
专题 | 智能感知与计算研究中心 |
作者单位 | Chinese Acad Sci CASIA, Inst Automat, Natl Lab Pattern Recognit NLPR, CRIPAC, Beijing 100190, Peoples R China |
第一作者单位 | 模式识别国家重点实验室 |
推荐引用方式 GB/T 7714 | Huang, Yongzhen,Wu, Zifeng,Wang, Liang,et al. Feature Coding in Image Classification: A Comprehensive Study[J]. IEEE TRANSACTIONS ON PATTERN ANALYSIS AND MACHINE INTELLIGENCE,2014,36(3):493-506. |
APA | Huang, Yongzhen,Wu, Zifeng,Wang, Liang,&Tan, Tieniu.(2014).Feature Coding in Image Classification: A Comprehensive Study.IEEE TRANSACTIONS ON PATTERN ANALYSIS AND MACHINE INTELLIGENCE,36(3),493-506. |
MLA | Huang, Yongzhen,et al."Feature Coding in Image Classification: A Comprehensive Study".IEEE TRANSACTIONS ON PATTERN ANALYSIS AND MACHINE INTELLIGENCE 36.3(2014):493-506. |
条目包含的文件 | 条目无相关文件。 |
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