Face recognition in low resolution video sequences using super resolution.

摘要

Human activity is a major concern in a wide variety of applications, such as video surveillance, human computer interface and face image database management. Detecting and recognizing faces is a crucial step in these applications. Furthermore, major advancements and initiatives in security applications in the past years have propelled face recognition technology into the spotlight.;The performance of existing face recognition systems declines significantly if the resolution of the face image falls below a certain level. This is especially critical in surveillance imagery where often, due to many reasons, only low-resolution video of faces is available. If these low-resolution images are passed to a face recognition system, the performance is usually unacceptable. Hence, resolution plays a key role in face recognition systems. In this thesis, we address this issue by using super-resolution techniques as a middle step, where multiple low resolution face image frames are used to obtain a high-resolution face image for improved recognition rates. Two different techniques based on frequency and spatial domains were utilized in super resolution image enhancement. In this thesis, we apply super resolution to both images and video utilizing these techniques and we employ principal component analysis for face matching, which is both computationally efficient and accurate. The result is a system hat can accurately recognize faces using multiple low resolution images/frames.