Average mean based feature extraction for image retrieval

This paper aims to improve the effectiveness of retrieving images on the basis of color content by Color averaging technique. In this paper, a new technique of feature extraction based on relative mean is proposed. Here, the relative mean based technique initially normalizes the mean value into a binary form to reduce the computational complexity and to increase the speed of retrieval. Later, the binary values are represented as hexadecimal strings and stored in feature database. The proposed relative mean technique is tested on generic image database and indexed image database. Results obtained are compared with the existing technique based on memory utilization and query execution time. The experimental results show that proposed relative mean gives the better performance in terms of higher precision and recall values with less computational complexity than the conventional techniques.