Paddy Leaf Disease Classification Using Machine Learning and Deep Learning Techniques

Rice is the main food in nearly every tropical and subtropical country on the planet. This demands the care and ensuring of rice fields spanning several hectares. Farmers face a daunting task ahead of them. Some problems go unnoticed by caregivers, and they are unable to complete this massive task of crop maintenance in such a short time. As an exercise, this study provides a way for swiftly sorting rice into infected or unaffected plants as a result of this time-consuming effort. One of the most common paddy illnesses is leaf disease. Identifying rice leaf diseases is time-consuming and arduous for farmers in distant places due to a shortage of expertise. Regardless of the presence of experts in a few areas, disorder detection is executed via the bare eye, which can also result in erroneous identity. The implementation of a computerized method can aid in the resolution of these issues. This study proposes a semi-automated technique for diagnosing three prevalent rice leaf illnesses (Leaf-Blast, Brown-Spot, and Hispa). The visual content of these disorders is used to classify them (texture, shape, and color). SVM classifier is used to determine the kind of paddy leaf disease.