The popularity of face recognition systems has increased due to their use in widespread applications, such as biometric access-control, security, and law enforcement. Driven by the enormous number of potential application domains, several algorithms have been proposed for face recognition. Face pose and image resolutions are among the two important factors that influence the performance of face recognition algorithms. In this paper, we present a comparative study of three baseline face recognition algorithms to analyse the effects of two aforementioned factors. The algorithms studied include (a) the AdaBoost with Linear Discriminant Analysis (LDA) as weak learner, (b) the PCA based approach, and (c) the Local Binary Pattern (LBP) based approach. We perform an empirical study using the images with systematic pose variation and resolution from Multi-PIE database to explore the recognition accuracy. This evaluation is useful for practical applications because most engineers start development of a face recognition application using these baseline algorithms. Simulation results revealed that the PCA is more accurate in classifying the variation in pose, while the AdaBoost is more robust in identifying low resolution images. The LBP does not classify face images of size 20x20 pixels and below and has lower recognition accuracy than PCA and AdaBoost.

Abstract—Part-based methods have seen popular applica-tions for face verification in the wild, since they are more robust to local variations in terms of pose, illumination and so on. However, most of the part-based approaches are built on hand-crafted features, which may be not suitable for the specific face verification purpose. In this work, we propose to learn a part-based feature representation under the supervision of face identities through a deep model, which ensures the generated representations are more robust and suitable for face verification. The proposed framework consists of following two deliberate components: a Deep Mixture Model (DMM) to find accurate patch correspondence and a Convolutional Fusion Network (CFN) to extract the part based facial features. Specifically, DMM robustly depicts the spatial-appearance distribution of patch features over the faces via several Gaussian mixtures, which provide more accurate patch correspondence even in the presence of local distortions. Then, DMM only feeds the patches which preserve the identity information to the following CFN. The proposed CFN is a two-layer cascade of Convolutional Neural Networks (CNN): 1) a local layer built on face patches to deal with local variations and 2) a fusion layer integrating the responses from the local layer. CFN jointly learns and fuses multiple local responses to optimize the verification performance. The composite rep-resentation obtained possesses certain robustness to pose and illumination variations and shows comparable performance with the state-of-the-arts on two benchmark data sets.