Skip to main content
. Author manuscript; available in PMC: 2014 Jul 1.
Published in final edited form as: Int J Comput Vis. 2013 Feb 19;103(3):348–371. doi: 10.1007/s11263-013-0609-0

Fig. 20. SVM results on texture synthesized images (30×30).

Fig. 20

We trained SVM classifiers on the original images (Figure 5a), and we tested them on texture synthesized images (Figure 5e) with patch size set to 30×30 pixels. The best performance on the texture synthesized images (42.6%) is comparable to human performance (46.9%).