Proceedings of the 8th International Conference on Social Network, Communication and Education (SNCE 2018)

Research on Leaf Classification Algorithm Based on the Image

Authors
Zhiliang Kang, Peng Huang
Corresponding Author
Zhiliang Kang
Available Online May 2018.
DOI
10.2991/snce-18.2018.171How to use a DOI?
Keywords
Leaf classification; Image processing; Neural network; Support vector machine (SVM)
Abstract

The MATLAB image processing toolbox is applied to extract 8 classical features of leaf (including perimeter, area, roundness, complexity, elongation, sphericity, average coefficient variation, serration), and 400 leaf samples are classified respectively on BP Neural Network, Probabilistic Neural Network (PNN) and Support Vector Machine (SVM), and the coverage recognition rate for BP Neural Network, PNN and SVM are obtained as 87.22%, 88.95% and 95.15% respectively. The coverage recognition rate of SVM is the highest and stable, which can effectively prevent the low recognition rate.

Copyright
© 2018, 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)

Volume Title
Proceedings of the 8th International Conference on Social Network, Communication and Education (SNCE 2018)
Series
Advances in Computer Science Research
Publication Date
May 2018
ISBN
978-94-6252-505-4
ISSN
2352-538X
DOI
10.2991/snce-18.2018.171How to use a DOI?
Copyright
© 2018, 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  - Zhiliang Kang
AU  - Peng Huang
PY  - 2018/05
DA  - 2018/05
TI  - Research on Leaf Classification Algorithm Based on the Image
BT  - Proceedings of the 8th International Conference on Social Network, Communication and Education (SNCE 2018)
PB  - Atlantis Press
SP  - 835
EP  - 839
SN  - 2352-538X
UR  - https://doi.org/10.2991/snce-18.2018.171
DO  - 10.2991/snce-18.2018.171
ID  - Kang2018/05
ER  -