Multi Variant Regional Features for Color Image Classification Using Fuzzy Rule Sets

Color image classification has been discussed deeply in the literature and uses various features like color, intensity, shape features to classify the input image. We propose a naval approach for color image classification which uses various features of different regions of the image. The image classification process suffers with the precision of classification due to the varying size of image and different colors of the objects of same with different color. The proposed method uses various sizes of box filters to generate many number of sub sampling images and extracts the features of the image. The sub sampled images are used to generate feature descriptors of those regions of interest. Generated descriptors represent the features of the image and used to generate a feature vector of the selected region. The generated features are used to generate a single value to represent the ROI and based on the ROI using rule set available the image class is identified. The proposed classification approach has produced efficient results.