Using an improved YOLOv5s network for the automatic detection of silicon on wheat straw epidermis of micrographs

Abstract

The silicon on wheat straw epidermis is an obstacle to its resource utilization, and pretreated methods should be applied to remove this structure. Due to the difficulties in detecting the silicon on wheat straw epidermis, judging the efficiency of pretreatment is still a challenging task. In this study, an automatic detection method based on you only look once (YOLO) v5s was proposed to detect the silicon on wheat straw epidermis of micrographs. To improve the efficiency of the network, the Input was modified, the inverted residual module, the pointwise convolution, and the attention mechanism were added, while the focus module was cut off. A total of 4690 micrographs of wheat straw epidermis were collected for training and testing. The training results showed that the proposed model can efficiently detect silicon on wheat straw epidermis of micrographs, and had the highest mean Average Precision of 98.88% among five state-of-the-art comparison models, including RetinaNet, Single Shot MultiBox Detector, YOLOv4tiny, YOLOv4, and YOLOv5s. The weight of the proposed model was 11.7 M, indicating that it can be transplanted to mobile devices. The proposed model showed good robustness under different imaging conditions. All the results indicated that the proposed model could detect the silicon on wheat straw epidermis of micrographs accurately and efficiently.