An Improved Image Entropy Algorithm Suitable for Digital Painting Style

Abstract

Traditional painting style classification method based on image entropy cannot be directly applied to the classification of digital painting style. After analyzing the similarities and differences between the two types of works in the existing literature, this paper sets additional saturation weighting to improve the previous color entropy calculation method and eliminates the contour entropy calculation to describe the digital painting image style better. The experimental results show that this method can classify the styles of digital paintings more accurately.