Chaodong Dai, Guoliang Xu, Jiao Mao, Tong Gu, Jiangtao Luo. Cell Phone Screen Defect Segmentation Based on Unsupervised Network[J]. Laser & Optoelectronics Progress, 2021, 58(20): 2015003
- Laser & Optoelectronics Progress
- Vol. 58, Issue 20, 2015003 (2021)
Fig. 1. Cell phone screen texture background. (a) Defect-free image; (b) defect image
Fig. 2. Algorithm overall framework
Fig. 3. Denoising autoencoder structure
Fig. 4. Segmentation process
Fig. 5. Residual image pixel distribution
Fig. 6. Schematic of triangle method
Fig. 7. Pseudo-code graph of triangle threshold segmentation
Fig. 8. Background reconstruction and defect segmentation results
Fig. 9. Comparison of defect segmentation results. (a) Defect images; (b) ground truth; (c) SVD; (d) U-Net; (e) MSCDAE; (f) proposed method
|
Table 1. Composition of the dataset
|
Table 2. Reconstruction performance of different loss functions
|
Table 3. Reconstruction performance of different network layers
|
Table 4. Comparison of experimental index
Set citation alerts for the article
Please enter your email address
© Copyright 2018-2021 | Chinese Laser Press. All Rights Reserved 沪ICP备15018463号-20