Usage of Color and Texture Features for Natural Image Indexing and Retrieval

Main Article Content

N. Magesh
Dr.P. Thangaraj

Abstract

The novel approach combines color and texture features for content based image retrieval (CBIR). This paper is used to retrieve the images from the huge collection of image databases. The image retrieval performed with basic concepts are not reaching to the user specifications and not attracted to the user, So a lot of research interest in recent years with new specifications such as feature indexing techniques are used in retrieval. The proposed system has focused on the computing the average and standard deviation value for color and entropy and tamura features for texture. By using above features, retrieval accuracy can be improved. The proposed method outperforms the other previously developed methods by providing the classification accuracy of more than 70% for the various types of images taken from coral database. Hence, this paper concentrates on color and texture features for image retrieval in different directions. The proposed method significantly improves efficiency with less computational complexity.

 


Keywords: Color, Texture, Tamura, Threshold, Retrieval, Image Database, Mean, Standard deviation, Median features.

Downloads

Download data is not yet available.

Article Details

Section
Articles