ATM Retentate Detection Model of Texture Distinguish Optimization of HOG Operator

DOI

10.2991/iccsae-15.2016.181How to use a DOI?

Keywords

retentate detection; HOG feature operator; Distinguish between grain; Background elimination; the characteristics of the block weighted.

Abstract

For the accuracy of traditional HOG feature detection operator in the application of ATM retentate detection is not high, this paper proposes a distinguish between optimization based on texture HOG feature detection operator ATM retentate detection model. First eliminate background of the original image by LBP operato, in order to highlight the local texture feature of detecting target, and then set a tolerance factor to eliminate the instability of LBP operator when neighborhood pixels change small, then the application of probability theory is adopted to optimize variance the similarity measures, and finally on the basis of the LBP background elimination, using the idea of entropy to HOG feature weighted in order to improve the detection accuracy. Experimental results show that the accuracy of proposed improved HOG feature detection based on texture distinguish optimization operator's is higher, the effect in the application of ATM machine retentate detection is better.

Copyright

© 2016, 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  - Zhen Xu
AU  - JianWei Lin
AU  - Fan Wu
AU  - ZiBin Xu
AU  - Hanjie Gu
PY  - 2016/02
DA  - 2016/02
TI  - ATM Retentate Detection Model of Texture Distinguish Optimization of HOG Operator
BT  - Proceedings of the 2015 5th International Conference on Computer Sciences and Automation Engineering
PB  - Atlantis Press
SP  - 985
EP  - 990
SN  - 2352-538X
UR  - https://doi.org/10.2991/iccsae-15.2016.181
DO  - 10.2991/iccsae-15.2016.181
ID  - Xu2016/02
ER  -