Feature Evaluation in Fine-gain of Leaf
- 10.2991/icmmct-16.2016.35How to use a DOI?
- leaf recognition; random forest; feature evaluation
In order to compare the value of several features involving leaf retrieval, we design an approach to evaluate 37 features about leafâ€™s contour, content and texture. Random forest algorithm is employed to rank these featuresâ€™ 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.
- © 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/).
Cite this article
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 -