Lightweight modified attention based deep learning model for cassava leaf diseases classification

The primary cause of decline in cassava production are various diseases on cassava leaves. It has direct adverse impact on farmers' income. The detection of diseases in cassava leaves traditionally relies on laboratory tests or expert intervention, that is time-consuming and costly. To address these challenges, an intelligent system that can be capable of accurately and efficiently identifying cassava leaf diseases is needed. In this research, a lightweight deep learning model is proposed that take fewer parameters and gives higher accuracy for the classification of cassava leaf diseases. The proposed model incorporates depthwise separable convolution, channel, spatial attention, and a novel modified channel attention module to reduce parameters and improve classification accuracy. All the training and testing images are from the agricultural field with natural background. The model has used the dedicated testing dataset to get the real effectiveness of the model. The testing images are separate images that not used for training and validation purposes. The proposed model has achieved the 98% validation accuracy and 75% testing accuracy. The primary objective of this proposed model is to promptly identify cassava leaf diseases directly from the agricultural field to address the need of farmers. A mobile application is developed to deploy the proposed lightweight deep learning model to address farmer requirements.