Image Aesthetic Quality Assessment Based on Photographic Composition Rules

Image composition is a vital factor in image aesthetics. In this paper, based on photographic composition of the image itself, we combine the aesthetic deep features with composition features by utilizing multi-task learning. We summarize a series of calculation formulas of the most classic photographic composition rules, such as the rule of thirds, and calculate the composition features and scores of the images. In multi-task learning module, we design double-column networks with static sharing structures. Features from different networks are fused by the method of soft parameter sharing. The composition score and the original aesthetic score of the image are used to supervise the training of the networks. Experiments on AVA-mini dataset show that the multi-task learning can make better use of the composition information of the image. Our method can outperform on the regression task of the image aesthetic quality assessment.