Image Aesthetic Quality Evaluation Using Convolution Neural Network Embedded Fine-Tune

Abstract

A way of convolution neural network (CNN) embedded fine-tune based on the image contents is proposed to evaluate the image aesthetic quality in this paper. Our approach can not only solve the problem of small-scale data but also quantify the image aesthetic quality. First, we chose Alexnet and VGG_S to compare which is more suitable for image aesthetic quality evaluation task. Second, to further boost the image aesthetic quality classification performance, we employ the image content to train aesthetic quality classification models. But the training samples become smaller and only using once fine-tune can not make full use of the small-scale dataset. Third, to solve the problem in second step, a way of using twice fine-tune continually based on the aesthetic quality label and content label respective, is proposed. At last, the categorization probability of the trained CNN models is used to evaluate the image aesthetic quality. We experiment on the small-scale dataset Photo Quality. The experiment results show that the classification accuracy rates of our approach are higher than the existing image aesthetic quality evaluation approaches.