TELKOMNIKA (Telecommunication Computing Electronics and Control)
Vol 18, No 2: April 2020

Plant species identification based on leaf venation features using SVM

Agus Ambarwari (Politeknik Negeri Lampung)
Qadhli Jafar Adrian (Universitas Teknokrat Indonesia)
Yeni Herdiyeni (IPB University)
Irman Hermadi (IPB University)



Article Info

Publish Date
01 Apr 2020

Abstract

The purpose of this study is to identify plant species using leaf venation features. Leaf venation features were obtained through the extraction of leaf venation features. The leaf image segmentation was performed to obtain the binary image of the leaf venation which is then determined the branching point and ending point. From these points, the extraction of leaf venation feature was performed by calculating the value of straightness, a different angle, length ratio, scale projection, skeleton length, number of segments, total skeleton length, number of branching points and number of ending points. So that from the extraction of leaf venation features 19 features were obtained. Identification of plant species was carried out using Support Vector Machine (SVM) with RBF kernel. The learning model was built using 75% of the training data. The testing results using 25% of the data on the training model, obtained an accuracy of 82.67%, with an average of precision of 84% and recall of 83%. 

Copyrights © 2020






Journal Info

Abbrev

TELKOMNIKA

Publisher

Subject

Computer Science & IT

Description

Submitted papers are evaluated by anonymous referees by single blind peer review for contribution, originality, relevance, and presentation. The Editor shall inform you of the results of the review as soon as possible, hopefully in 10 weeks. Please notice that because of the great number of ...