Remote-Sensing Image Tile-Level Annotation Based on Discriminative Features and Expressive Visual Word Descriptors

Figure 6

Experimental results by using different method for tile-level annotation. (a) Image to be annotated. (b) Ground truth. (c) Result of using color features only. (d) Result of using texture features only. (e) Result of using spatial features only. (f) Result of using NOF + K-means. (g) Result of using WOF + K-means. (h) Result of using our proposed method.

(a)

(b)

(c)

(d)

(e)

(f)

(g)

(h)