Skip to main content
. 2015 Jan 6;15(1):880–898. doi: 10.3390/s150100880

Figure 9.

Figure 9.

Figure 9.

Comparison of different restoration algorithms using a synthetic image; (a) the input image; (b) the degraded image by spatially varying blur; (c) the restored image by the constrained least squares (CLS) filter (peak-to-peak signal-to-noise ratio (PSNR) = 33.13, mean structural similarity (MSSIM) = 0.94); (d) the restored image by the Dong's method [24] (PSNR = 26.68, MSSIM = 0.84); (e) the restored image by the Yang's method [25] (PSNR = 36.44, MSSIM = 0.97); (f) the restored image by the Xu's method [12] (PSNR = 29.62, MSSIM = 0.93); (g) the restored image by the Shen's method [14] (PSNR = 36.88, MSSIM = 0.98); and (h) the restored image by the proposed method (PSNR = 39.19, MSSIM = 0.98).