RE-RCNN: A Novel Representation-Enhanced RCNN Model for Early Apple Leaf Disease Detection

Abstract

Apple leaf diseases have significant impacts on apple quality and productivity. So, the implementation of accurate disease detection in the early stages is a powerful guarantee for the rapid and high-quality development of the apple industry. However, early apple leaf disease often represents very small size disease spots, which makes the detection of early apple leaf disease a challenge for existing deep learning-based detection models. In this paper, a novel detection model called Representation-Enhanced RCNN(RE-RCNN) is proposed to perform accurate detection of early apple leaf disease spots. Firstly, an object-enhanced branch is proposed to achieve feature enhancement of small disease spots by introducing small disease spots feature enrichment extractor (SDSFEE). Secondly, a SCMLoss is proposed to balance the inter-class differences of various size disease spots under the same category. Thirdly, an one2one computation strategy is leveraged to sample data reasonably during the training process. From the final experimental results, it can be seen that the proposed model could achieve outstanding performance on the early apple leaf disease detection task.