Enhancement Of color Image Retrieval Capabilites; Fusion Of Color with Texure (Optmized)

Abstract

Challenge in content based color image retrieval system lies in assigning syn!hetic descriptor to the image features which are economic in terms of memory required and time taken to compare query image features with features of images from database. Texture is a very important feature of an image and lots of mathematical model have been presented earlier, which describes the textural feature of the images, but mo !,f them are textural features of gray scale images. If the same met!lod is tried to extend for color images the time arid space parameter surpass the practical boundaries. The solutions to this is to convert the color images to gray scale and then extract the textural features, but the importance of color features in similarity measurement by a human observer can not be over looked. So, either a new mathematical model is Cj reqUifed to represent the color texture features or during com" rison, combine the texture property and color property ex ,ted separately. The work presented here extracts the color featufe by quantizing it- in color and pixel space, then finding the color dominance locally and globally. The texture ieatures are extracted using !:Q-occurrence matrix method. First, with a liberal value of threshold the image names with similar textures are retrieved from the texture database and then as a second level of filtering, color feature is combined with the texture feature and similar images are displayed. A[;"'ors have used MATLAB for the .logic implementation and pc ~e SQL 8.1 for windows, as the database to store image features.