Abstract:

Extracting texture features of images with probability statistics models is a significant method of contentbased image retrieval. In order to overcome the shortcomings of lack of color information and improve probability statistics retrieval performance, an approach that combines the global dominant color and probability statistics is proposed. The combinative features including texture and color are utilized for second retrieval after linear weighting. Experiments based on the 2600 images database shows superior performance of our proposed method compared with the single feature image retrieval and the probability statistics retrieval, recall rates and average normalized modified retrieval rank have been raised by 30% and 22% respectively.

Key words: probability statistics, dominant color, texture, image retrieval