Food Crop Disease Identification system using ML

Agriculture has played a crucial role in domesticating essential crops and livestock for thousands of years. However, food insecurity caused by plant diseases remains a significant global problem. These diseases result in crop damage and reduced yield, leading to food shortages. According to the Food and Agriculture Organization, plant parasites and diseases are responsible for up to 40 percent of the decline in global agricultural production. This has severe consequences, including widespread hunger and substantial damage to the agriculture industry. Smallholder farmers, who contribute over 80 percent of agricultural output in developing countries, are particularly vulnerable to pathogen-related disruptions in food supply. As a result, the development of new techniques for detecting plant diseases can significantly increase food production and mitigate losses.The limited accuracy and efficiency of previous methods in detecting and classifying crop leaf diseases have hindered agricultural productivity. To address these shortcomings, this research proposes the utilization of the Plant Village Kaggle dataset, which presents challenges due to its varying image capture conditions and diverse image samples. Through the development of a 28-layer deep learning model, we achieved an impressive accuracy rate exceeding 97%. Our model not only overcomes the limitations of previous methods but also demonstrates its effectiveness in accurately detecting and classifying crop leaf diseases. By leveraging this model, we aim to enhance agricultural productivity and mitigate losses caused by plant diseases, thereby contributing to global food security.