Texture and Wavelet based PCANet (TW-PCANet) for Infants' Facial Expression Recognition

Abstract

The babyhood is a very important stage in the human growth process. Thus learning the facial expression characteristics of infants is of great significance to nursing care for infants. Infants' faces are significantly different from adults' faces, like eyebrows, eyes, nose, cheeks, skin texture, etc. Therefore, the facial expression recognition models trained on adults' facial expression database cannot be directly applied to infants' facial expression recognition. There are dozens of facial expression databases for adults' facial expression analysis, but there is no database composed by various infants' facial expressions. Hence we first collect candid images of infants' facial expression, which includes six obvious expressions of infants, namely crying, curious, happy, sleeping, wronged, neutral. Then the texture and wavelet based PCANet (TW-PCANet) is proposed to fully extract the features of infants' facial expressions. The proposed method first handles original input color images by local binary patterns (LBP) and Gabor wavelet, then the processed images are put into the PCANet to get the final class. The experimental results show that the proposed method can achieve higher recognition rate obtained by PCANet, LBP and Gabor wavelet.