Mobile Phone Surface Defect Detection Based on Improved Faster R-CNN

Abstract

Various surface defects will inevitably occur in the production process of mobile phones, which have a huge impact on the enterprise. Therefore, precise defect detection is of great significance in the production of mobile phones. However, traditional manual inspection and machine vision inspection have low efficiency and accuracy respectively which cannot meet the rapid production needs of modern enterprises. In this paper, we proposed a mobile phone surface defect (MPSD) detection model based on deep learning, which greatly reduces the requirement of a large dataset and improves detection performance. First, Boundary Equilibrium Generative Adversarial Networks (BEGAN) is used to generate and augment the defect data. Then, based on the Faster R-CNN model, Feature Pyramid Network (FPN) and ResNet 101 are combined as feature extraction network to get more small target defect features. Further, replacing the ROI pooling layer with an ROI Align layer reduces the quantization deviation during the pooling process. Finally, we train and evaluate our model on our own dataset. The experimental results indicate that compared with some traditional methods based on handcrafted feature extraction and the traditional Faster R-CNN, the improved Faster R-CNN achieves 99.43% mAP, which is more effective in the field of MPSD defect detection.