How to fuse color and texture features for image retrieval

Dear Team,

     Kindly request you to clarify my doubt on Content based image retrieval. I've extracted color features from an image using color histogram and used Euclidean distance for calculating the distance between query image and database images. This went on fine and the images were retrieved.

Similarly, I've used GLCM for extracting texture features and i used euclidean distance for calculating similarity measure.This again went on fine. My doubt here is how do i combine this color and texture features of an image? Is there any algorithm to be followed for fusion of two different features of an image? If so,how do i go ahead in fusing this color and texture features? Please explain? Any reference papers would be of much helpful.

Size of extracted color feature of an image = 128 x 128 double Size of extracted texture feature of an image = 1 x 4 double

Thank you.

Malini

Answer 1

[Image Analyst]

See section 19.4 here: http://iris.usc.edu/Vision-Notes/bibliography/contentsapplicat.html#Implementations%20and%20Applications,%20Databases,%20QBIC,%20Video%20Analysis,%20Hardware%20and%20Software,%20Inspection