Table 1.

The impact of image preprocessing on image quality is analyzed in terms of SSIM, PSNR, and SNR. The table displays the average improvements per class of the NEU-DET dataset.

Class	SSIM (Mean ± Std)	PSNR (Mean ± Std)	SNR (Mean ± Std)
Crazing	0.9316 ± 0.0083	28.36 ± 1.32 dB	12.73 ± 1.46 dB
Inclusion	0.9642 ± 0.0040	33.06 ± 1.56 dB	18.16 ± 2.05 dB
Patches	0.9387 ± 0.0253	27.95 ± 1.08 dB	7.85 ± 1.89 dB
Pitted Surface	0.9531 ± 0.0075	29.57 ± 3.08 dB	16.02 ± 3.50 dB
Rolled-in Scale	0.9234 ± 0.0032	31.42 ± 1.81 dB	16.14 ± 0.87 dB
Scratches	0.9632 ± 0.0056	33.01 ± 1.37 dB	13.25 ± 2.79 dB
AVG	0.9457 ± 0.0195	30.56 ± 2.76 dB	14.03 ± 4.01 dB