Fusion with CS-LBP and HOG for Vehicle Make and Model Recognition

DOI

10.2991/icmmcce-17.2017.191How to use a DOI?

Keywords

vehicle recognition; local binary pattern; HOG feature; blocking CS-LBP

Abstract

Local binary pattern (LBP) has widely used in face recognition with extracting texture feature, for the high statistical histogram dimensions of LBP and unable to effectively express the edge and direction information of image, so a method which is called fusion with blocking CS-LBP and HOG features is proposed, and applied vehicle recognition. At first, the vehicle image is extracted texture feature with blocking CS-LBP operator, which is calculated the texture histogram for each sub-block, and then the HOG feature of the original image is extracted, as well as the HOG feature which is based on the CS-LBP, finally, the blocking CS-LBP feature is fused with these two different HOG features. The experiments are implemented on the vehicle image databases, the results show that the proposed method can be obtained a higher recognition with K neighbor classification.

Copyright

© 2017, the Authors. Published by Atlantis Press.

Open Access

This is an open access article distributed under the CC BY-NC license (http://creativecommons.org/licenses/by-nc/4.0/).

Download article (PDF)

TY  - CONF
AU  - Shanwei Zhu
AU  - Yuhui Li
AU  - Jin Feng
AU  - Lingfeng Zhang
PY  - 2017/09
DA  - 2017/09
TI  - Fusion with CS-LBP and HOG for Vehicle Make and Model Recognition
BT  - Proceedings of the 2017 5th International Conference on Mechatronics, Materials, Chemistry and Computer Engineering (ICMMCCE 2017)
PB  - Atlantis Press
SP  - 1066
EP  - 1074
SN  - 2352-5401
UR  - https://doi.org/10.2991/icmmcce-17.2017.191
DO  - 10.2991/icmmcce-17.2017.191
ID  - Zhu2017/09
ER  -