Mixing, abduction and illegal adoption of newborns is a global problem and the research done to solve this problem is minimal. Traditional methods of biometric and non-biometric techniques have their own limitations and fail to provide enough level of security for newborns. The work on adult face recognition has been an active research area in recent years and automatic face recognition for newborns is least reported in the literature. Therefore it is imperative to initiate research, so that future face recognition algorithms will be able to solve this important problem for identification of newborns. The contributions of this research are (i) proposed method, which mitigates the effect of the covariates of newborn face; (ii) providing an analytical and experimental underpinning effect of different facial expressions exhibited by newborns; (iii) preparing newborn face database of 280 individuals with slight variations in pose, illumination and expression. The accuracy of the proposed matching algorithms on the newborn face database with neutral expression is 87.04% and this negates the notion that all newborns look alike.