Skip to main content
. Author manuscript; available in PMC: 2014 Aug 21.
Published in final edited form as: Phys Med Biol. 2013 Aug 2;58(16):R161–R186. doi: 10.1088/0031-9155/58/16/R161

Figure 13.

Figure 13

Dictionary-learning-based reconstruction outperforming TV-minimization-based reconstruction [124]. The more knowledge we have, the less amount of data we need for satisfactory reconstruction. Dictionary learning promises to extract prior knowledge flexibly and effectively from training images, being more specific than a TV-based sparsifying constraint or a generic wavelet transform.