Research Article
Remote-Sensing Image Tile-Level Annotation Based on Discriminative Features and Expressive Visual Word Descriptors
Figure 7
Experimental results of tile-level annotation using four different methods. (a) Image to be annotated. (b) Ground truth. (c) Result of using -based method. (d) Result of using the object-based LDA method. (e) Result of using LEGION + SVM. (f) Result of using our proposed method.
(a) |
(b) |
(c) |
(d) |
(e) |
(f) |