Blotch Detection in Archive Films Based on Visual Saliency Map

Figure 6

Representation notation of patches in the proposed method: (a) 5 × 5 patch centred at point at the top-left corner of the current frame, (b) corresponding patch in the current frame, and (c) corresponding eighteen patches in the previous and next frames. Here, the patches outside of the frame boundary are considered the same as their nearest neighbour inside of it.

(a)

(b)

(c)