Figure 4
From: Image inpainting based on sparse representations with a perceptual metric
Obtained results of image 1. (a) Original image (480 × 360 pixels, 24-bit color levels), (b) corrupted image including text regions (11.9% loss), (c) results obtained by the proposed method, (d) results obtained by the method in[31], (e) results obtained by the method in[34], (f) results obtained by the method in[35], (g) results obtained by the method in[24], (h) results obtained by the method in[30], and (i) results obtained by the method in[41].