Advancing content-based image retrieval by exploiting image color and region features

In this paper, we propose a novel system that strives to achieve advanced c ontent-based image retrieval using seamless combination of two complementar y approaches: on the one hand, we propose a new color-clustering method to better capture color properties of the original images, on the other hand, expecting that image regions acquired from the original images inevitably c ontain many errors, we make use of the available erroneous, ill-segmented i mage regions to accomplish the object-region-based image retrieval. We also propose an effective image-indexing scheme to facilitate fast and efficien t image matching and retrieval. The carefully designed experimental evaluat ion shows that our proposed image retrieval system surpasses other methods under comparison in terms of not only quantitative measures, but also image retrieval capabilities.