Semantic annotation of satellite images using discrete infinite logistic normal distribution based mixed-membership model

In this paper, we propose a novel method for the annotation of the multispectral satellite images by incorporating a new graphical model. In order to obtain the annotated image, first, we use a set of images with defined semantic concepts to represent the training set. Second, the images are represented by several visual words based on the image features. At last, the model of discrete infinite logistic normal distribution is exploited to estimate probabilities of semantic classes for the regions in the test images, and categorize them into the semantic concepts. Experimental evaluation on the multispectral images demonstrates the good performance of the proposed method on the multispectral images annotation.