Tommy Saputra
Institut Teknologi dan Sains Nahdlatul Ulama Sriwijaya Sumatera Selatan

Published : 1 Documents Claim Missing Document
Claim Missing Document
Check
Articles

Found 1 Documents
Search

Identification of Medicinal Plants Based on Leaf Texture Using Gray-Level Co-occurrence Matrix (GLCM) and Backpropagation Neural Network Fatihani Nurqolbiah; Eriene Dheanda Absharina; Aspirani Utari; Mukhlis Febriady; Tommy Saputra
Journal of Intelligent Systems and Information Technology Vol. 3 No. 1 (2026): January
Publisher : Apik Cahaya Ilmu

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.61971/jisit.v3i1.250

Abstract

Identifying medicinal plants from their leaves is often subjective and depends on scarce botanical expertise. This study classifies three medicinal plants of the genus Curcuma (white turmeric, mango ginger, and yellow turmeric) from leaf texture using Gray-Level Co-occurrence Matrix (GLCM) features and a Backpropagation Neural Network (BPNN). A primary dataset of 63 leaf images (45 for training and 18 for testing, balanced across the three classes) was resized to 500 × 500 pixels and converted to grayscale. Five GLCM features (ASM, contrast, IDM, entropy, and correlation) were fed into a 5-5-5-3 network, which was evaluated with learning rates of 0.1–1.0 and 100–1,500 epochs. The highest accuracy, 65.03%, was obtained with a learning rate of 0.1 and 100 epochs, and accuracy tended to decrease as either parameter increased. This is lower than the accuracy reported by related studies that use larger datasets or deep learning. Because the dataset is small and was evaluated with a single hold-out split without cross-validation, the findings are preliminary and cannot yet be generalized.