Detection of sensitive images based on affinity propagation clustering
Maofu Liu, Wenhao Liang, Li Chen · Proceedings of SPIE, the International Society for Optical Engineering/Proceedings of SPIE · 2009
In order to detect sensitive images, a content-based detection method using image retrieval technology is proposed in this paper. The method utilizes color correlogram and Gabor wavelet transformation to extract color and texture features, and then employs integrated similarity approach to calculate similarity and affinity propagation clustering algorithm to group the images in image database. In the end, the image is detected by the content-based image retrieval. Experiment results show that the proposed method is better in detection accuracy ratio and retrieval efficiency than the traditional method and using K-means clustering for image database.