Abstract
Aiming at the problems of low efficiency and poor accuracy in the product surface defect detection. In this paper, an online surface defects detection method based on YOLOV3 is proposed. Firstly, using lightweight network MobileNetV2 to replace the original backbone as the feature extractor to improve network speed. Then, we propose an extended feature pyramid network (EFPN) to extend the detection layer for multi-size object detection and design a novel feature fusing module (FFM) embedded in the extend layer to super-resolve features and capture more regional details. In addition, we add an IoU loss function to solve the mismatch between classification and bounding box regression. The proposed method is used to train and test on the hot rolled steel open dataset NEU-DET, which contains six typical defects of a steel surface, namely rolled-in scale, patches, crazing, pitted surface, inclusion and scratches. The experimental results show that our method achieves a satisfactory balance between performance and consumption and reaches 86.96% mAP with a speed of 80.96 FPS, which is more accurate and faster than many other algorithms and can realize real-time and high-precision inspection of product surface defects.
Highlights
In the process of industrial production, due to the influence of technological processes, production equipment and site environment, there will be various defects on the product surface
The existing research on surface defect detection methods can be roughly divided into two categories: a traditional method based on display feature extraction and a deep learning method based on automatic feature extraction
The label corresponding to the IoU with the maximum score and greater than the threshold 0.5 is counted as the category of the image, according to which the whole image classification results of our method can be calculated, namely precision, recall and F1-score indicators
Summary
In the process of industrial production, due to the influence of technological processes, production equipment and site environment, there will be various defects on the product surface. Many researchers applied the deep learning method to surface defect detection and surpass traditional methods [4,5]. Deng et al [10] used YOLOV2 with graffiti interference to detect cracks and defects on a concrete surface under complex background The accuracy of his method was even higher than that of RCNN (mAP 77% vs 74.5%), and it had higher real-time performance (0.17 s vs 0.23 s). Object detection methods based on deep learning have been partially studied in the industrial field, most of them remain in the laboratory stage and are difficult to be implemented for two reasons. We propose an improved inspection method that is based on YOLOV3 for high-accuracy and high-speed inspection of surface detection. We evaluate the proposed method on NEU-DET, and the results can demonstrate a clear superiority to other methods
Sign-in/Register to view highlights & summary Sign-in/Register to access full text options 
Free) 
Talk to us
Join us for a 30 min session where you can share your feedback and ask us any queries you have
Schedule a call
