CBIR Based on Color and Low-Level Texture Features

R.S.Choraś (Poland)


CBIR, color histogram, Gabor filters, similarity metrics, texture features.


Content-based image retrieval systems allow the user to in teractively search image databases looking for those im ages which are similar to a specified query image. Simi larity between images is then assessed by computing sim ilarity between feature vectors. These features are repre sented in the vector form, and often are combined together. This paper explores image retrieval mechanisms based on a combination of texture and color features. Texture fea tures are extracted using the Gabor filters analysis. Color moments are used as color features.

Important Links:

Go Back