Objective Aesthetic Quality Assessment for Photos

Nowadays, the acquisition of digital photos is becoming easier and easier, and the demand for objective assessment of the aesthetic quality of photos is growing, with the development of computer vision and pattern recognition technology, this demand is gradually being explored. After studying the effect of gray interval distribution on the aesthetic quality of photos, an objective assessment method for the aesthetic quality of photographs which considers both global and local features is proposed. For the whole features, the gray interval and line angles features are extracted. The subject areas are extracted from the photos through clarity detection method, then calculate the clarity, lighting and the calculation of rule of thirds in the subject area, as to extract the local features. A total of 18 features including the whole and the local features, using LIBSVM to calculate and train, and to test this method on CUHKPQ image dataset, then we get a good performance. It can be concluded that the combination of 18 features in the objective assessment of photos aesthetic quality can meet the demand of practical application.