In this paper, a novel example-based automatic face alignment strategy has been proposed for facial features alignment, i.e. facial shape extracting. The method is motivated by an intuitive and experimental observation that there exists an approximate linearity relationship between the image intensity difference and the shape difference, that is, similar face image intensity distribution implies similar face shape. Therefore, given a learning set of face images with their corresponding face landmarks labeled, the shape of any other face image can be learned by estimating its similarities to the training images in the learning set and applying these similarities to the shape reconstruction of the unknown face image. Concretely, if the unknown face image is expressed by an optimal linear combination of the training images, the same linear combination coefficients can be directly applied to the linear combination of the corresponding training shapes to construct the optimal shape for the novel face image. Experiments have shown that, compared with traditional methods, the proposed method can achieve a comparable alignment accuracy in less time. Furthermore, the same strategy has been extended to extract the shape of face images with varying poses.