Unsupervised watershed-driven region-based image retrieval

I. Pratikakis, I. Vanhamel, H. Sahli, B. Gatos, S.J. Perantonis
2006 IEE Proceedings - Vision Image and Signal Processing  
A novel unsupervised strategy for content-based image retrieval is presented. It is based on a meaningful segmentation procedure that can provide proper distributions for matching via the earth mover's distance as a similarity metric. The segmentation procedure is based on a hierarchical watershed-driven algorithm that extracts meaningful regions automatically. In this framework, the proposed robust feature extraction and the many-to-many region matching along with the novel region weighting
more » ... enhancing feature discrimination play a major role. Experimental results demonstrate the performance of the proposed strategy.
doi:10.1049/ip-vis:20050061 fatcat:5jhtczt3szfo7dkdmmxkhenb4y