Plant Disease Detection and Classification Using Transfer Learning Inception Technique

To avoid productivity and quantity losses in agricultural products, it is essential to identify plant diseases. Examining visually discernible patterns on plants is a key component of plant disease research. For agriculture to be sustainable, disease detection and plant health monitoring are essential. Plant disease monitoring by hand is fairly difficult. It demands a sizable quantity of labour, expertise in plant diseases, and protracted processing times. In order to identify plant diseases, image processing is used. In this study, the method for identifying plant diseases using photographs of leaves is discussed. Transfer Learning Inception v3 is used in the suggested method to identify diseases in examples of plant leaf imagery. The model has also been assessed in terms of accuracy and loss. The performance study was carried out using the Plant Village Kaggle database, which is the standard dataset for plant illnesses and problems in terms of intensity variations, color changes, and discrepancies observed in the shapes and sizes of leaves. According to both qualitative and quantitative studies, the proposed method is more proficient and reliable than other existing methods for recognizing and categorizing plant diseases.