INTECOMS: Journal of Information Technology and Computer Science
Vol 6 No 1 (2023): INTECOMS: Journal of Information Technology and Computer Science

Klasifikasi Penyakit Tanaman Cabai Rawit Dilengkapi Dengan Segmentasi Citra Daun dan Buah Menggunakan Yolo v7

Masrur Anwar (Institut Sains dan Teknologi Terpadu Surabaya)
Yosi Kristian (Institut Sains dan Teknologi Terpadu Surabaya)
Endang Setyati (Institut Sains dan Teknologi Terpadu Surabaya)



Article Info

Publish Date
27 Jun 2023

Abstract

Diseases that attack chili plants can be diagnosed early by observing symptoms or changes that occur in the leaves and fruit of the chili plant. However, diseases or pests that attack chili plants within a single plant can vary. In this study, YOLO v7 was used to perform leaf and chili segmentation on images, and the segmented results were then classified for chili plant disease using Deep Convolutional Neural Network (DCNN) Transfer Learning with the Fine Tuning method. The test results of the constructed model showed that the Yolo v7 segmentation accuracy was 0.970 on mAP50 when performing chili plant leaf and fruit segmentation. For the DCNN model testing with transfer learning method using the EfficientNetV2M based model, an accuracy value of 0.912 was obtained for leaf disease classification and an accuracy of 0.889 was obtained for chili fruit classification. Keyword: Chili Plant Diseases; Classification; Transfer Learning, Yolo v7 segmentation

Copyrights © 2023