会议论文

Zhu, Zhiyuan

英文

2016 INTERNATIONAL CONFERENCE ON NETWORK AND INFORMATION SYSTEMS FOR COMPUTERS (ICNISC)

2016

306-311

2nd Annual International Conference on Network and Information Systems for Computers (ICNISC)

APR 15-17, 2016

Wuhan, PEOPLES R CHINA

[Zhu, Zhiyuan] Chinese Inst Elect, Consulting & Stand Res Ctr, Beijing, Peoples R China.^[Ren, Dongchun] Beijing 7Invensun Technol Co Ltd, Res Ctr, Beijing, Peoples R China.^[Zhou, Guangyou;Zhou, Yin] Cent China Normal Univ, Sch Comp, Wuhan, Hubei, Peoples R China.

Changsha Univ Sci & Technol, Henan Univ Technol, Kunming Univ Sci & Technol, Xian Univ Sci & Technol, Engn Village

Wang, S Qian, Z

345 E 47TH ST, NEW YORK, NY 10017 USA

IEEE

978-1-4673-8838-2

10.1109/ICNISC.2016.71

本校为其他机构

With the rising popularity of mobile devices, recent years have witnessed a growing interest in document image retrieval (DIR). In conventional Bag-of-Visual-Words (BoVW) based document image retrieval method, only SIFT or SURF feature is used to locate feature points and produce a codebook, which has a low discriminative power. Though several multiple feature based BoVW methods are proposed, these methods are based on multiple codebooks. However, some features can not train a codebook, such as connected-component feature. So this paper propose a new multi-feature fusion method, considering th...