Identifying natural images and computer graphic images based on texture feature homogeneity

Classification of natural images and computer graphic images is widely used in the applications which include video indexing, animal classification, flower classification, web and many other fields. Since, computer graphic images possess high realism it is very difficult to distinguish from natural images by a naked eye. This paper presents a novel identification scheme to classify natural images and computer graphic images based on texture feature homogeneity. Experimental results show that, the proposed scheme can achieve an average identification accuracy of 93.30% by using KNN classifier.