A Fast Surface Defect Detection Method Based on Background Reconstruction
- 3 Downloads
In this paper, we propose an unsupervised background reconstruction method to detect defects on surfaces with unevenly distributed textures. An improved deep convolutional autoencoder is utilized to reconstruct the textured background of the original image as a defect-free reference. Specifically, a weighted loss function based on structural similarity (SSIM) is utilized to adapt to the unevenly distributed texture background and improve the reconstruction accuracy. Furthermore, combined with the reconstructed defect-free reference, a novel difference analysis method based on the discrete cosine transform (DCT) is given to accurately segment the defect regions from the original image. A series of experiments for the defect detection on mobile phone cover glass (MPCG) are conducted. The processing time for an image of 512 × 512 pixels is only 20 ms, which satisfies the requirement of online detection. The experimental results verify the effectiveness of the proposed method.
KeywordsDefect detection Unsupervised learning Background reconstruction
This research is supported by National Natural Science Foundation of China under Grant 61503378 and Youth Innovation Promotion Association, CAS (2013097).
- 13.Aiger D., Talbot H. (2010). The phase only transform for unsupervised surface defect detection. In: IEEE Conference on computer vision and pattern recognition (pp. 295–302). San Francisco, CA, USA: IEEE.Google Scholar
- 15.Carrera D., Boracchi G., Foi A., Wohlberg B. (2016). Scale-invariant anomaly detection with multiscale group-sparse models. In IEEE international conference on image processing (pp. 3892–3896). Phoenix, AZ, USA: IEEE.Google Scholar
- 19.Zhao Z., Li B., Dong R., Zhao P. (2018). A surface defect detection method based on positive samples. In Pacific Rim international conference on artificial intelligence (pp. 473–481) Nanjing: Springer.Google Scholar
- 21.Yang H., Chen Y., Song K., Yin Z. (2019). Multiscale feature-clustering-based fully convolutional autoencoder for fast accurate visual inspection of texture surface defects. IEEE Transactions on Automation Science and Engineering.Google Scholar
- 25.Ke M., Lin C., Huang Q. (2017). Anomaly detection of Logo images in the mobile phone using convolutional autoencoder. In International conference on systems and informatics (pp. 1163–1168). Hangzhou: IEEE.Google Scholar