Enhancing Sugarcane Disease Classification with Ensemble Deep Learning: A Comparative Study with Transfer Learning Techniques

Deep learning practices in the agriculture sector can address many challenges faced by farmers such as disease detection, yield estimation, soil profile etc. In this paper, classification for sugarcane plant and experimentation involved thereby is thoroughly discussed. Experimental results include performances of well-known existing transfer techniques proposed ensemble deep based architecture that incorporates stack two networks with one having level-wise spatial attention helping to provide better generalization. A Self-created database leaf diseases introduced research community through paper. It involves 5 categories a total 2569 images. Here, it observed best performing method, MobileNet-V2 shows an accuracy around 84% lowest number parameters whereas model reaching 86.53 % less epochs acceptable parameters.