Detecting differences between photographs and computer generated images

With the development of computer graphic rendering software and the appearance of more and more photorealistic pictures, the need for automatically distinguishing Computer Generated Images from real photographs has become of particular interest to criminal and forensic science investigators. Previous studies have been based on wavelet statistics, while in our study we examined several visual features derived from colour, edge, saturation and texture features extracted with the Gabor filter. Based on the feature extraction, we examined three commonly-used classifiers: non-linear SVM, Weighted k-nearest neighbors and Fuzzy k-nearest neighbors with 1,044 Computer Generated Images and 1,114 photographs downloaded from open sources. Finally we report on the comparative analysis of the results of these automatic classifications: Gabor filter based texture feature shows very promising results (99% for photo and 91.5% for CGI) while visual features show some abilities to perform differentiation.