Learn to Recognise: Exploring Priors of Sparse Face Recognition on Smartphones

Abstract

Face recognition is one of the important components of many smart devices apps, e.g., face unlocking, people tagging and games on smart phones, tablets, or smart glasses. Sparse Representation Classification (SRC) is a state-of-the-art face recognition algorithm, which has been shown to outperform many classical face recognition algorithms in OpenCV, e.g., Eigenface algorithm. The success of SRC is due to its use of ' 1 optimization, which makes SRC robust to noise and occlusions. Since ' 1 optimization is computationally intensive, SRC uses random projection matrices to reduce the dimension of the ' 1 problem. However, random projection matrices do not give consistent classification accuracy as they ignored the prior knowledge of the training set. In this paper, we propose to exploit the prior knowlege of the training set to improve the recognition accuracy. It first learns the optimized projection matrix from the training set to produce consistent recognition performance then applies ' 1-based classification based on the group sparsity structure of SRC to further improve the recognition accuracy. Our evaluations, based on publicly available databases and real experiment, show that face recognition using optimized projection matrix is 8-17 percent more accurate than its random counterpart and Eigenface algorithm, and the recognition accuracy can be further improved by up to 5 percent by exploiting group sparsity structure. Furthermore, the optimized projection matrix does not have to be recalculated even if new faces are added to the training set. We implement the SRC with optimized projection matrix on Android smartphones and find that the computation of residuals in SRC is a severe bottleneck, taking up 85-90 percent of the computation time. To address this problem, we propose a method to compute the residuals approximately, which is 50 times faster with little sacrificing recognition accuracy. Lastly, we demonstrate the feasibility of our new algorithm by the implementation and evaluation of a new face unlocking app and show its robustness to variation of poses, facial expressions, lighting changes, and occlusions.

From Real to Complex

“…Wei et al [44] developed an acoustic classification method on wireless sensor networks by applying SRC to increase the recognition performance and decrease the computation time to meet the requirement of real-time classification. Shen et al [30,31] optimised the SRC to boost the face recognition performance in smartphones.…”

A New Native Video Filtering based on OpenGL ES for Mobile Platform

“…In our research, the developed native video filtering technique uses OpenGL ES that is positioned on the component of Native C/C++ Libraries. Our approach aims to achieve faster-filtering performance as OpenGL ES gets direct support from the Graphics Processing Unit of the Android device [11]- [13]. Fig.…”

A Computing Offloading Game for Mobile Devices and Edge Cloud Servers

“…Especially for mobile devices (MDs), network services provide convenience and functional possibilities. However, functional and computationally intensive applications consume a large amount of energy and computing time on MDs, such as augmented reality [1] and face recognition [2]. Moreover, the MD is characterized by its mobility and portability with the poor CPU performance and limited battery power.…”