A Method of Dual-threshold Dynamic Image Segmentation Based on DTBNN Algorithm

DOI

10.2991/icca-16.2016.86How to use a DOI?

Keywords

Dual-thresholds, Image segmentation, Neural network, Decision tree

Abstract

In order to deal with the segment problem of dynamic image which has indistinctive ups and downs feature in histogram, a method of dual-threshold dynamic image segmentation based on DTBNN (Decision Tree Based on Neutral Network) algorithm is proposed. Firstly, according to the correspondence between decision tree and neural network to build a stable and efficient training neural network; Then, work out the mean of gray value, the maximum deviation and the threshold mapping function as sample data to train the neural network; Finally, using the trained neural network to get threshold mapping function by testing images, and achieve dual-threshold image segment using the result of the upper and lower threshold values which are calculate from previous step. The simulation results shows that this method does not depend on the feature of histogram and it could accurately get upper and lower segmentation threshold. Compared with OTSU dual-threshold method and maximum entropy dual-threshold method, the proposed method could achieve better dynamic image dual-thresholds segmentation.

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  - Lihua Song
AU  - Yongqiang Fu
AU  - Yebai Li
PY  - 2016/01
DA  - 2016/01
TI  - A Method of Dual-threshold Dynamic Image Segmentation Based on DTBNN Algorithm
BT  - Proceedings of the 2016 International Conference on Intelligent Control and Computer Application
PB  - Atlantis Press
SP  - 361
EP  - 366
SN  - 2352-538X
UR  - https://doi.org/10.2991/icca-16.2016.86
DO  - 10.2991/icca-16.2016.86
ID  - Song2016/01
ER  -