Image classification using spatial relationship matrix based on color spatio-histogram

Efficient and reliable content-based image retrieval and classification techniques are required for the large image databases. Humans perceive images by breaking the scenes into regions and objects. We, therefore, present a novel approach for extracting color and spatial relationships among image regions. For this, we propose a color spatio-histogram and a bin image which express not only the color distribution but also the spatial information of an image. The system constructs a spatial relationship matrix (SRM) with representative bin pixels of a bin image in order to classify natural images, which define prototypical color and spatial relationships of image regions recurred throughout the image collection. Experiment results show that our scheme performs well for image classification.