An Aesthetic Preference Prediction System for Assessing Natural Images Based on Photo Complexity and Composition Evaluation

Photo aesthetics is a field in computer vision, which aims at analyzing the beautifulness of a photo. With the advancement of imaging technology, people capture and produce photos easily but they find it difficult to sort out good ones. Therefore, in this paper, we propose a method for efficient photo aesthetics analysis for quality classification. We developed some features based on human psychology and criterions on photography, including complexity, texture, color, composition. Particularly, the Sobel edge detector and Harris corner points are extracted to assess the image complexity, and some color and composition features proposed in previous literature are improved for better analysis accuracy.The supervised machine learning methods are applied for photo aesthetics analysis, and the SVM is used to measure the effectiveness of the proposed features. In our experiments, both image databases CUHKPQ and CUHK are used for evaluation. In the experiment, the CUHKPQ dataset is divided into seven thematic categories, whereas the CUHK dataset contains all categories. The experimental results show that the proposed method is able to classify the photo aesthetic quality efficiently with lower dimension compared to other related work. In the CHUK dataset, the accuracy above 88.72% and in the CUHKPQ dataset, the accuracy is up to 96.4%.