International Research Journal of Education and Technology

Mangoes (Mangifera indica) have been grown for more than 4,000 years, with their roots in South Asia. Throughout history, mangoes have established themselves as a key fruit in tropical and subtropical areas around the world, playing a significant role in global agricultural economies. However, in spite of their economic and nutritional value, mango crops are highly vulnerable to various diseases that can greatly affect both yield and quality. As the worldwide demand for mangoes continues to grow, maintaining the health of mango orchards has become a crucial issue for farmers and the agricultural sector. The detection and classification of diseases in mango fruits are critical for ensuring agricultural productivity and food safety. This study proposes a novel approach leveraging a Convolutional Recurrent Neural Network (CRNN) integrated with a metaheuristic optimizer to enhance the accuracy of disease identification in mangoes. The CRNN combines convolutional layers for feature extraction with recurrent layers for sequence prediction, effectively capturing both spatial and temporal patterns in images. The dataset consists of a diverse range of mango images, categorized based on various disease conditions. Experimental results demonstrate that the proposed CRNN framework outperforms traditional machine learning methods, achieving higher accuracy and lower misclassification rates. This research not only contributes to the field of agricultural technology but also offers a scalable solution for real-time monitoring and early intervention in mango cultivation, ultimately aiding farmers in reducing crop losses and enhancing fruit quality.

Key Words: Convolutional Recurrent Neural Network (CRNN), Image Processing, Precision agriculture, Image Classification, Feature extraction.