Figure 4.
Image compression using complete and overcomplete dictionaries. Coding with an overcomplete dictionary is more efficient (fewer bits per pixel) and more accurate (lower RMSE). (a) Original image of size 256 × 256 pixels. (b) Compressed with 64×64 complete dictionary to 0.826 bits per pixel at RMSE = 0.329. (c) Compressed with 64 × 128 overcomplete dictionary to 0.777 bits per pixel at RMSE = 0.328.