Detection of Plant Leaf Diseases using Image Processing and Machine Learning Techniques

TITLE	Detection of Plant Leaf Diseases using Image Processing and Machine Learning Techniques
ABSTRACT	Plant leaf diseases affect crop yield and quality, and manual detection by farmers is often slow and inaccurate. This study presents a machine learning approach using 11,254 leaf images of healthy and diseased samples. The dataset covers nine disease classifications and three crops: pepper, tomato, and potato. Preprocessing methods included shrinking, noise reduction, and grayscale conversion. Convolutional neural networks (CNN) are used to extract spatial data including color, texture, and shape, whereas artificial neural networks (ANN) are used for classification. TensorFlow/Keras was used to train the model using categorical cross-entropy loss and the Adam optimizer. With an accuracy rate of 84.27%, CNN demonstrated its value in the early and accurate detection of plant diseases.
AUTHOR	Arun N Shet, Dr. Sunitha G P
PUBLICATION DATE	2025-09-01 19:29:59
VOLUME	13
ISSUE	3
DOI	DOI: 10.15662/IJMSERH.2025.1303061
PDF	pdf/2025/7/61_Detection of Plant Leaf Diseases using Image Processing and Machine Learning Techniques.pdf
KEYWORDS

Article