Real-time detection of particleboard surface defects based on improved YOLOV5 target detection

Abstract

Particleboard surface defect detection technology is of great significance to the automation of particleboard detection, but the current detection technology has disadvantages such as low accuracy and poor real-time performance. Therefore, this paper proposes an improved lightweight detection method of You Only Live Once v5 (YOLOv5), namely PB-YOLOv5 (Particle Board-YOLOv5). Firstly, the gamma-ray transform method and the image difference method are combined to deal with the uneven illumination of the acquired images, so that the uneven illumination is well corrected. Secondly, Ghost Bottleneck lightweight deep convolution module is added to Backbone module and Neck module of YOLOv5 detection algorithm to reduce model volume. Thirdly, the SELayer module of attention mechanism is added into Backbone module. Finally, replace Conv in Neck module with depthwise convolution (DWConv) to compress network parameters. The experimental results show that the PB-YOLOv5 model proposed in this paper can accurately identify five types of defects on the particleboard surface: Bigshavings, SandLeakage, GlueSpot, Soft and OliPollution, and meet the real-time requirements. Specifically, recall, F1 score, mAP@.5, mAP@.5:.95 values of pB-Yolov5s model were 91.22%, 94.5%, 92.1%, 92.8% and 67.8%, respectively. The results of Soft defects were 92.8%, 97.9%, 95.3%, 99.0% and 81.7%, respectively. The detection of single image time of the model is only 0.031 s, and the weight size of the model is only 5.4 MB. Compared with the original YOLOv5s, YOLOv4, YOLOv3 and Faster RCNN, the PB-Yolov5s model has the fastest Detection of single image time. The Detection of single image time was accelerated by 34.0%, 55.1%, 64.4% and 87.9%, and the weight size of the model is compressed by 62.5%, 97.7%, 97.8% and 98.9%, respectively. The mAP value increased by 2.3%, 4.69%, 7.98% and 13.05%, respectively. The results show that the PB-YOLOV5 model proposed in this paper can realize the rapid and accurate detection of particleboard surface defects, and fully meet the requirements of lightweight embedded model.

Detection of Farmland Obstacles Based on an Improved YOLOv5s Algorithm by Using CIoU and Anchor Box Scale Clustering

“…In the literature [20], the TR-YOLOv5s network and down sampling principle were proposed, and an attention mechanism was introduced to meet the highprecision and high-efficiency identification requirements for underwater targets. The literature [21] added the Ghost bottleneck lightweight depth convolution module to the Backbone and Neck modules of YOLOv5 so the model size was reduced, and at the same time, the SELayer module of the attention mechanism was added to the Backbone module, and the deep convolution (DWConv) was used to compress the network parameters to achieve fast and accurate identification of particleboard defects.…”

A pavement distresses identification method optimized for YOLOv5s

“…Therefore, YOLO represents the work of the single-phase algorithm, as well as the update from YOLOv2 to YOLOv5. The YOLOv5 19 is the latest model in the YOLO 20 family. The network model has high detection precision and fast reasoning speed.…”

An Analysis of Defect Detection on Steel Strip Surface Using Modified Yolo V5

“…The compressed network parameters lowers the operational cost. The capacity to extract spatial feature information of varied sizes in place of conventional convolution operation enhances the resilience of the model for spatial layout and object detection [39]. The Convl and C3 in backbone and head layers of YOLOv5 are replaced by GhostConv and C3Ghost.…”

“…mAP is a metric for gauging the precision of object detection. The average detection accuracy improves with increasing value [39]. The precision, recall values calculations are shown in equation ( 8) (9).…”