Title

AI DRIVEN CROP DISEASE DETECTION SYSTEM FOR ENHANCED AGRICULTURAL

AUTHOR(S)

Sarim Faridi Shiv shakti Shrivastava

ABSTRACT

Agriculture India's economy depends largely on agriculture; however, illnesses cause 15–25% of crop losses annually, creating financial difficulties. In order to accurately detect agricultural diseases, this study presents sophisticated image processing algorithms. Segmentation is improved by cognitive-based pixel clustering, and picture quality is improved using a unique Cross Central Filter (CCF). Using Support Vector Machines (SVM), a hybrid Genetic Algorithm (GA) and Gravitational Search Algorithm (GSA) optimizes classification, while Principal Component Analysis (PCA) streamlines feature extraction. Metrics such as Mean Squared Error (MSE), Structural Similarity Index (SSIM), sensitivity, and accuracy are used to assess performance, and the results show better performance than those of current approaches. The suggested system provides a scalable and effective way to reduce crop losses and advance sustainable agriculture. Keywords: Crop Disease Detection, Image Processing, Segmentation, Classification, Support Vector Machine, Genetic Algorithm, Principal Component Analysis.

DOI :

Under Process

Download Full Article