Skip to main content
. Author manuscript; available in PMC: 2013 Jun 26.
Published in final edited form as: Neural Comput. 2013 Jan 22;25(4):922–939. doi: 10.1162/NECO_a_00418

Figure 5.

Figure 5

ICA filters trained on 21 × 21 position-centered patches from van Hateren’s database of natural images. Our criterion for a position-centered patch here was || < 0.05 in units of a pixel. There were more than 2.8 × 106 patches in our training set. The filters are separated into three groups: the upper box contains filters that are better fit with a Gabor filter, the bottom box contains double-Gabor filters, and the ones in the middle did not satisfy the criterion of adjusted coefficient of determination R2 greater than 0.98 (see Figure 10).