Surface Defects Recognition of Wheel Hub Based on Improved Faster R-CNN

Abstract

Machine vision is one of the key technologies used to perform intelligent manufacturing. In order to improve the recognition rate of multi-class defects in wheel hubs, an improved Faster R-CNN method was proposed. A data set for wheel hub defects was built. This data set consisted of four types of defects in 2,412 1080 × 1440 pixels images. Faster R-CNN was modified, trained, verified and tested based on this database. The recognition rate for this proposed method was excellent. The proposed method was compared with the popular R-CNN and YOLOv3 methods showing simpler, faster, and more accurate defect detection, which demonstrates the superiority of the improved Faster R-CNN for wheel hub defects.

Defect Inspection in Tire Radiographic Image Using Concise Semantic Segmentation

“…In the later comparative experiment, the networks U-net [27], SegNet [28], Faster R-CNN [29], Mask R-CNN [35] and FCN [17] used for comparison follow the same training strategy as our method. The networks were trained using Adam optimizer with mini-batch of size 5.…”

“…The former sets five types of labels, namely, impurity, sidewall split, sidewall overlap, tread and sidewall background. In Faster R-CNN [29], four kinds of rectangular box labels, namely tread impurity, sidewall impurity, sidewall split and sidewall overlap, are used. We show the training result in Table II. According to the training results shown in Table II, the proposed network has less network parameters and shorter training time than the others.…”

“…The result of comparative experiments between the proposed Concise-SSN and conventional state-of-the-art deep learning methods (U-net [27], FCN [17], SegNet [28], Mask R-CNN [35], Faster R-CNN [29]) is shown in Fig. 9.…”

“…Even though FCN and Mask R-CNN have better segmentation results than U-net and SegNet, further investigation is need for this real-life application. Test image Ground truth U-net [27] FCN [17] SegNet [28] Mask R-CNN [35] Faster R-CNN [29] Our method Fig. 10 shows the comparative experimental results using PA as evaluation index.…”

Object Detection and Classification of Metal Polishing Shaft Surface Defects Based on Convolutional Neural Network Deep Learning

“…Xu, et al [22] proposed using vehicle ground-penetrating radar to obtain irregular railway subgrade images. The improved Fast R-CNN was used to identify hazards and compared with traditional neural network methods; Santur, et al [23] used a 3D laser to acquire the defect image of arail, and then conducted deep learning to achieve the high-precision and rapid detection of lateral defects such as fracture, scour and abrasion on railway surfaces; Sun, et al [24] directly adopted fixed-photographing methods for surface irregularities of automobile hubs and achieved the identification of automobile hub surface defects based on the improved Faster R-CNN, comparing this with the current state-of-the-art YOLOv3.…”