A method for object-based color image retrieval
Chaobing Huang, Yarong Han, Yu Zhang · 2012
Based on HSV color model, a method of object-based spatial-color feature (OSCF) for color image retrieval is proposed. Firstly, objects are extracted from color image based on our previous algorithm. Then image features are represented by objects in it. Color and spatial-color feature are adopted for description of objects. The new method only pays attention to main central objects. For images whose main objects are located in the central region of image, the description of main central objects is much more accurate in describing the image content than integrated properties of all the regions in the image. Experimental results show the effectiveness and efficiency of the method.