Skip to main content
. 2017 May 8;17(5):1065. doi: 10.3390/s17051065

Figure 5.

Figure 5

Figure 5

Examples of 96 filters obtained from 1st convolution layer through training: (a) CVC-14 database; (b) DNHD-DB1; (c) KAIST database; and (d) combined database. In (ad), the left four images show the 96 filters obtained by training with the original images, whereas the right four images represent those obtained by training with the HE images. In the left and right four images, the left-upper, right-upper, left-lower, and right lower images show the 96 filters obtained by training using 1-, 2-, 3-, and 4-fold cross validation, respectively.