Design and Implementation of a CNN architecture to classify images of banana leaves with diseases

Abstract

Piura is an agricultural region, and therefore, crop production is one of the primary sources of income. Competition in this sector has been growing in recent years, and Piura cannot be left behind. Due to factors such as diseases, pest attacks, and sudden changes in climatic conditions, the level of crop production decreases. Automatic recognition of plant diseases is essential to automatically detect disease symptoms as soon as they appear in the growing stage. This paper provides a proposed methodology for the analysis and detection of banana leaf diseases using digital image processing techniques. The results obtained show that the proposed system can successfully detect and classify two major banana leaf diseases: Black Sigatoka (BBS) and Bacterial Wilt (BBW).