Bill Fibers Extraction Method Based on Global Statistic Decision and Local Adaptive Segmentation

DOI

10.2991/wartia-16.2016.353How to use a DOI?

Keywords

image segmentation, OTSU, adaptive segmentation, fiber extraction

Abstract

In order to solve the problem of high classifying error in the process of bill fibers extraction, an improved method is proposed for bill fibers extraction based on global statistic decision and local adaptive segmentation. First, locates the suspicious fibers regions in the H, S color space of the global bill image according to the statistics of the fibers color. Then, in the V space of the suspicious fibers regions a more adaptive segmentation method called OTSU is adopted to carry out the fine division of local regions to acquire the precise fibers targets. Finally, mathematical morphology is employed to filter the fibers and at the same time reduces classifying error. The experiments show the proposed method extracts fibers from bill images with fewer classifying error and better segmentation result.

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  - Ting Han
AU  - Jianbin Xie
AU  - Tong Liu
PY  - 2016/05
DA  - 2016/05
TI  - Bill Fibers Extraction Method Based on Global Statistic Decision and Local Adaptive Segmentation
BT  - Proceedings of the 2016 2nd Workshop on Advanced Research and Technology in Industry Applications
PB  - Atlantis Press
SP  - 1780
EP  - 1784
SN  - 2352-5401
UR  - https://doi.org/10.2991/wartia-16.2016.353
DO  - 10.2991/wartia-16.2016.353
ID  - Han2016/05
ER  -