|
Performance Comparison of Unsupervised Segmentation Algorithms on Rice Groundnut and Apple Plant Leaf Images |
|---|---|
| รหัสดีโอไอ | |
| Creator | Bellapu Rajendra Prasad, Tirumala Ramashri, Rama Naidu Kurukundu |
| Title | Performance Comparison of Unsupervised Segmentation Algorithms on Rice Groundnut and Apple Plant Leaf Images |
| Contributor | - |
| Publisher | TuEngr Group |
| Publication Year | 2564 |
| Journal Title | International Transaction Journal of Engineering, Management, & Applied Sciences & Technologies |
| Journal Vol. | 12 |
| Journal No. | 12 |
| Page no. | 12A12M: 1-18 |
| Keyword | Unsupervised segmentation, Graph Cut, Multi-Level Otsu, Plant Leaf Disease Detection, Semantic Segmentation, KOTSU, CHKMC, GCMO, Automatic plant disease detection, Rice image data, 2D Tsallis Entropy (2DTE), K-means Clustering (KMC), Variation of Information (VoI). |
| URL Website | http://TuEngr.com/Vol12_12.html |
| Website title | ITJEMAST V12(12) 2021 @ TuEngr.com |
| ISSN | 2228-9860 |
| Abstract | This paper focuses on plant leaf image segmentation by considering the aspects of various unsupervised segmentation techniques for automatic plant leaf disease detection. The segmented plant leaves are crucial in automatic disease detection, quantification, and classification of plant leaf diseases. It is challenging to segment out the affected area from the images of complex backgrounds. Hence, robust semantic segmentation for automatic recognition and analysis of plant leaf disease detection is highly demanded in precision agriculture. This breakthrough is expected to demand an accurate and reliable technique for plant leaf segmentation. We propose a hybrid variant that incorporates Graph Cut (GC) and Multi-Level Otsu (MOTSU) in this paper. We compare the segmentation performance implemented on rice, groundnut, and apple plant leaf images for various unsupervised segmentation algorithms. Boundary Displacement error (BDe), Global Consistency error (GCe), Variation of Information (VoI), and Probability Rand index (PRi) are the index metrics used to evaluate the performance of the proposed model. By comparing the outcomes of the simulation, our proposed technique, Graph Cut based Multi-level Otsu (GCMO), provides better segmentation results than other existing unsupervised algorithms. |
