International Journal of Computer Applications
Foundation of Computer Science (FCS), NY, USA
|
Volume 59 - Issue 17 |
Published: December 2012 |
Authors: S. Mangijao Singh, K. Hemachandran |
![]() |
S. Mangijao Singh, K. Hemachandran . Content based Image Retrieval based on the integration of Color Histogram, Color Moment and Gabor Texture. International Journal of Computer Applications. 59, 17 (December 2012), 13-22. DOI=10.5120/9639-4325
@article{ 10.5120/9639-4325, author = { S. Mangijao Singh,K. Hemachandran }, title = { Content based Image Retrieval based on the integration of Color Histogram, Color Moment and Gabor Texture }, journal = { International Journal of Computer Applications }, year = { 2012 }, volume = { 59 }, number = { 17 }, pages = { 13-22 }, doi = { 10.5120/9639-4325 }, publisher = { Foundation of Computer Science (FCS), NY, USA } }
%0 Journal Article %D 2012 %A S. Mangijao Singh %A K. Hemachandran %T Content based Image Retrieval based on the integration of Color Histogram, Color Moment and Gabor Texture%T %J International Journal of Computer Applications %V 59 %N 17 %P 13-22 %R 10.5120/9639-4325 %I Foundation of Computer Science (FCS), NY, USA
Content-Based Image Retrieval (CBIR) systems help users to retrieve relevant images based on their contents such as color and texture. In this paper, a new approach is proposed in which color histogram, color moment and Gabor texture descriptors are integrated. The color histogram has the advantages of rotation and translation invariance. The HSV (16, 4, 4) quantization scheme has been adopted for color histogram and an image is represented by a vector of 256-dimension. The color histogram has the disadvantages of lack of spatial information and to improve the discriminating power of color indexing techniques, a minimal amount of spatial information is encoded in the color index by dividing the image horizontally into three equal non-overlapping regions and extracts the three moments (mean, variance and skewness) from each region, for all the color channels. Thus, for a HSV color space, 27 floating point numbers per image are used for indexing. As its texture feature, Gabor texture descriptors are adopted. Weights are assigned to each feature respectively and calculate the similarity with combined features of color histogram, color moment and Gabor texture using Histogram intersection distance and Canberra distance as similarity measures. Experimental results show that the proposed method has higher retrieval accuracy in terms of precision than other conventional methods combining color histogram, color moment and Gabor texture based on global features approach.