Feature Coding in Image Classification:
A Comprehensive Study
 |
| An evolution map of feature coding. |
People
Yongzhen Huang
Zifeng Wu
Liang Wang
Tieniu Tan
Overview
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.
Paper
 |
Feature Coding In Image Classfication: A Comprehensive Study Yongzhen Huang, Zifeng Wu, Liang Wang, Tieniu Tan IEEE Transactions on Pattern Analysis and Machine Intelligence (TPIMI2014) |
Performance Comparison
 |
| Performance comparison on the 15-Scenes and the PASCAL VOC07 databases |
Acknowledgments
This work was jointly supported by the National Natural Science Foundation of China (61135002, 61203252) and the National Basic Research Program of China (2012CB316300), Tsinghua National Laboratory for Information Science and Technology Cross-discipline Foundation, and Hundred Talents Program of CAS. The source code of all coding algorithms and experimental figures in this paper have been released on http://nlpr-web.ia.ac.cn/english/irds/ people/yzhuang.html.