Learning self-adaptive color harmony model for aesthetic quality classification

Color harmony is one of the key aspects in aesthetic quality classification for photos. The existing color harmony models either are in lack of quantization schemes or can assess simple color patterns only. Therefore, these models cannot be applied to assess color harmony of photos directly. To address this problem, we proposed a simple data-based self-adaptive color harmony model. In this model, the hue distribution of a photo is fitted by mean shift based method, then features are extracted according to this distribution and finally the Gaussian mixture model is applied for learning features extracted from all the photos. The experimental results on eight categories datasets show that the proposed method outperforms the classic rule-based methods and the state-of-the-art data-based model.