A new Feature-Fusion method based on training dataset prototype for surface defect recognition. (October 2021)

• Record Type: Journal Article
• Authors: Wang, Yucheng; Li, Xinyu; Gao, Yiping; Wang, Lijian; Gao, Liang
• Is Part Of: Advanced engineering informatics. Volume 50(2021)
• Publication Date: 2021-10
• Subjects: Surface defect recognition -- Feature fusion -- Convolutional neural network -- Prototype vector; Computer-aided engineering -- Periodicals; Engineering -- Data processing -- Periodicals; 620.00285
• DOI: 10.1016/j.aei.2021.101392
• Languages: English
• ISSNs: 1474-0346

Abstract

Abstract: Surface defect recognition is important to improve the surface quality of end products. In this area, there were many convolutional neural network (CNN)-based methods because CNN can extract features automatically. The extracted features determine the performance of recognition, so it is important for CNN-based methods to extract effective and sufficient features. However, feature extraction needs a large-scale dataset, which is hard to obtain. To save the cost of collecting samples and extract effective features, ensemble methods were proposed to make full use of the features extracted by CNN in order to guarantee good performance with limited samples. However, the methods are confined to utilize one sample – they extracted multi-level features from one individual sample – but ignore the vast information in a dataset. Due to the limit information in one sample, this paper turns the attention to the training dataset and attempts to mine the multi-level information in the dataset for predicting. The proposed method is named as Prototype vectors fusion-based CNN (ProtoCNN), which utilizes the prototype information in the training dataset. In training process, it trains a VGG11 as the base model, and meanwhile prototype vectors corresponding to each defect class are generated in multiple feature layers of VGG11. Then, in predicting process, the prototype vectors are fused to predict unknown samples. The experiments on three famous datasets, including NEU-CLS, wood dataset, and textile dataset indicate that the proposed ProtoCNN outperforms conventional ensemble models and other models for surface defect recognition. In these datasets, ProtoCNN has achieved the accuracy of 99.86%, 90.01%, and 81.28% respectively, which increase 1.05%, 4.07%, 19.53% compared to its base model respectively. Finally, this paper analyzes the effectiveness and practicality of prototype vectors, showing that the proposed ProtoCNN is practical for real world application.