An Adaptive Relevance Feedback Image Retrieval Method with Based on Possibilistic Clustering Algorithm

Image classification is uncertain, an image may belong to different classes simultaneously, the image possibilistic membership can express the multiple interpretations of an image. In light of the image possibilistic membership, a new image retrieval method with relevance feedback based on possibilistic clustering algorithm (PCA) is proposed in this paper. The method uses the PCA to classify images of image database, moreover, only inquiring images in the existent classification. The paper also proposes a new relevance feedback image retrieval algorithm, feature in which the user is especially interested will be chosen as the attributes in image retrieval according to user´s preference feedback. Additionally, the experiments have manifested that the method outperforms the traditional ones in speed of image retrieval