Facial beauty prediction model based on self-taught learning and convolutional restricted Boltzmann machine

The research of facial beauty mostly focuses on geometric features, which may easily lose much feature information characterizing facial beauty and rely heavily on the accurate manual localization of landmark facial features. Therefore, a novel method to extract apparent features of face images by convolutional restricted Boltzmann machine (CRBM) without relying on artificial features selection is proposed. Massive beautiful and ugly training samples are required by traditional machine learning methods, and it is hard to be satisfied because most face images are actually neutral beauty. A better method of relaxing strict restrictions of training samples is self-taught learning, which automatically improves CRBM to understand the characteristics of data distribution even if the requirements of the class and number of training samples are not satisfied, thus the facial beauty prediction model could be established reasonably. Experimental results show that the proposed facial beauty prediction model can achieve recognition rate of 87.3% on three classes of beautiful, ordinary and unbeautiful face images, and 95% on two classes of beautiful and unbeautiful face images. Meanwhile, the extracted apparent features can effectively characterize feature information of beautiful faces.