PLANT DISEASES CLASSIFICATION USING FEATURE REDUCTION, BPNN AND PSO

Abstract

Agriculture is the culture of land and rearing of the plants to supply food to nourish and enhance life. In India, it is one of the main economic sources and different types of plants are farmed every year which hinders normal growth of the plants. That’s the reason from long ago researchers are searching for new methods of classification of plant diseases. Although there are different neural networks already used for plant disease classification, but only using these methods do not make the best tradeoff between time and accuracy. So to remove this constraint, we proposed method for plant disease classification based on BPNN and PSO. Now we have added some more data to our dataset and applied Principal component analysis to reduce the number of total features and on these features we have applied BPNN with PSO. We have used images of leaves affected by different bacterial and fungal diseases: Alternaria alternata, Anthracnose, Bacterial blight, Bacterial leaf scorch, Cercospora leaf spot, and Downy mildew in our experiment and our proposed method achieves approximately 96.42% accuracy.