In order to solve the problem that the traditional color feature extraction method is difficult to support the accurate classification of art painting images when analyzing the features of art painting images, a color feature extraction method of art painting images based on edge complexity is designed. Color moment is used to represent the color feature component, and Sobel operator is used to quantify the edge extension direction into horizontal and vertical directions. Then the region of the art painting image is detected, and the edge intensity is calculated to determine the edge direction. Finally, the color feature extraction process of the art painting image is given, and the experimental comparison and analysis are carried out. The results show that compared with the traditional method, the color features of the image obtained by this method are used to classify the image, and the classification results of the art painting content and painting style are more accurate.