Disease Detection Based on Colour and Lesion Range on Leaves


  • Aishwarya Loganathan Universiti Tun Hussein Onn Malaysia
  • Nik Shahidah Afifi Md Taujuddin


Paddy, Bacteria Leaf Blight, Fotor application, Colour extraction, Lesion detection, Python software


The fundamental goal of this study effort is to assist persons, particularly young farmers, in detecting the disease early and producing rice of great quality and quantity. The data images taken at the paddy field are then processed in Python software. Image enhancement was done on the data image to increase image quality. The image background is removed by using the background removal tool in the Fotor application. After the background is removed, the process was continued with the colour extraction technique and lesion detection technique where a masking process is applied to the sample image. The pixel intensity between infected and non-infected areas is calculated using the pixel values obtained from those photos. The Bacteria Leaf Blight (BLB) disease is calculated by subtracting the green pixel of the image from the total image pixel. The severity level table developed by Caudhary CP is then used as a reference to classify the severity level of Brown Spot disease while the accuracy of the Bacterial Leaf Blight (BLB) disease detection is evaluated by comparing the results with the severity level verified by MARDI Pathologist on each sample images. From the study conducted, the detection accuracy is 82.9%.




How to Cite

Loganathan, A., & Md Taujuddin, N. S. A. (2022). Disease Detection Based on Colour and Lesion Range on Leaves. Evolution in Electrical and Electronic Engineering, 3(2), 15–24. Retrieved from https://publisher.uthm.edu.my/periodicals/index.php/eeee/article/view/6856



Computer and Network

Most read articles by the same author(s)