Mathematically inspired approaches to face recognition in uncontrolled conditions: super resolution and compressive sensing

Al-Hassan, Nadia (2014) Mathematically inspired approaches to face recognition in uncontrolled conditions: super resolution and compressive sensing. Doctoral thesis, University of Buckingham.

Preview

Text AL-Hassan_2014_Mathematically.pdf Available under License Creative Commons Attribution Non-commercial No Derivatives. Download (3MB) | Preview

Abstract

Face recognition systems under uncontrolled conditions using surveillance cameras is becom-ing essential for establishing the identity of a person at a distance from the camera and providing safety and security against terrorist, attack, robbery and crime. Therefore, the performance of face recognition in low-resolution degraded images with low quality against im-ages with high quality/and of good resolution/size is considered the most challenging tasks and constitutes focus of this thesis. The work in this thesis is designed to further investigate these issues and the following being our main aim: “To investigate face identification from a distance and under uncontrolled conditions by pri-marily addressing the problem of low-resolution images using existing/modified mathemati-cally inspired super resolution schemes that are based on the emerging new paradigm of compressive sensing and non-adaptive dictionaries based super resolution.” We shall firstly investigate and develop the compressive sensing (CS) based sparse represen-tation of a sample image to reconstruct a high-resolution image for face recognition, by tak-ing different approaches to constructing CS-compliant dictionaries such as Gaussian Random Matrix and Toeplitz Circular Random Matrix. In particular, our focus is on constructing CS non-adaptive dictionaries (independent of face image information), which contrasts with ex-isting image-learnt dictionaries, but satisfies some form of the Restricted Isometry Property (RIP) which is sufficient to comply with the CS theorem regarding the recovery of sparsely represented images. We shall demonstrate that the CS dictionary techniques for resolution enhancement tasks are able to develop scalable face recognition schemes under uncontrolled conditions and at a distance. Secondly, we shall clarify the comparisons of the strength of sufficient CS property for the various types of dictionaries and demonstrate that the image-learnt dictionary far from satisfies the RIP for compressive sensing. Thirdly, we propose dic-tionaries based on the high frequency coefficients of the training set and investigate the im-pact of using dictionaries on the space of feature vectors of the low-resolution image for face recognition when applied to the wavelet domain. Finally, we test the performance of the de-veloped schemes on CCTV images with unknown model of degradation, and show that these schemes significantly outperform existing techniques developed for such a challenging task. However, the performance is still not comparable to what could be achieved in controlled en-vironment, and hence we shall identify remaining challenges to be investigated in the future.

Actions (login required)

View Item