Feature Evaluation in Fine-gain of Leaf

DOI

10.2991/icmmct-16.2016.35How to use a DOI?

Keywords

leaf recognition; random forest; feature evaluation

Abstract

In order to compare the value of several features involving leaf retrieval, we design an approach to evaluate 37 features about leaf’s contour, content and texture. Random forest algorithm is employed to rank these features’ contribution to leaf categorization. To forming the optimum features combination, we get the highest retrieval accuracy by gradually adding the most valuable features and depict the relationship between accuracy and feature number. Combined with the time analysis, different features group could be adopted for efficiency requirement. The leaf samples are from Taiwan and ICL database.

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  - Zhanhao Chen
AU  - Shan Xu
AU  - Yixiong Zou
AU  - Hualong Zhang
AU  - Zhu Zhang
AU  - Yue Li
AU  - Wei Wang
PY  - 2016/03
DA  - 2016/03
TI  - Feature Evaluation in Fine-gain of Leaf
BT  - Proceedings of the 2016 4th International Conference on Machinery, Materials and Computing Technology
PB  - Atlantis Press
SP  - 186
EP  - 192
SN  - 2352-5401
UR  - https://doi.org/10.2991/icmmct-16.2016.35
DO  - 10.2991/icmmct-16.2016.35
ID  - Chen2016/03
ER  -