Real-time face recognition has recently become available for the government and industry due to developments in face recognition algorithms, human head detection algorithms, and faster/low cost computers. Despite these advances, however, there are still some critical issues that affect the performance of real-time face recognition software. This paper addresses the problem of off-centered and out-of-pose faces in pictures, particularly in regard to the eigenface method for face recognition. We first demonstrate how the representation of faces by the eigenface method, and ultimately the performance of the software depend on the location of the eyes in the pictures. The eigenface method for face recognition is described: specifically, the creation of a face basis using the singular value decomposition, the reduction of dimension, and the unique representation of faces in the basis. Two different approaches for aligning the eyes in images are presented. The first considers the rotation of images using the orthogonal Procrustes Problem. The second approach looks at locating features in images using energy-minimizing active contours. We then conclude with a simple and fast algorithm for locating faces in images. Future research is also discussed. / Master of Science

The interface with the real-world has proved to be extremely challenging throughout the past 70 years in which computer technology has been developing. The problem initially is assumed to be somewhat trivial, as humans are exceptionally skilled at interpreting real-world data, for example pictures and sounds. Traditional analytical methods have so far not provided the complete answer to what will be termed pattern recognition. Biological inspiration has motivated pattern recognition researchers since the early days of the subject, and the idea of a neural network which has self-evolving properties has always been seen to be a potential solution to this endeavour. Unlike the development of computer technology in which successive generations of improved devices have been developed, the neural network approach has been less successful, with major setbacks occurring in its development. However, the fact that natural processing in animals and humans is a voltage-based process, devoid of software, and self-evolving, provides an on-going motivation for pattern recognition in artificial neural networks. This thesis addresses the application of weightless neural networks using a ranking pre-processor to implement general pattern recognition with specific reference to face processing. The evaluation of the system will be carried out on open source databases in order to obtain a direct comparison of the efficacy of the method, in particular considerable use will be made of the MIT-CBCL face database. The methodology is cost effective in both software and hardware forms, offers real-time video processing, and can be implemented on all computer platforms. The results of this research show significant improvements over published results, and provide a viable commercial methodology for general pattern recognition.

Face recognition finds various applications in surveillance, Law enforcement etc. These applications require fast image processing in real time. Modern GPUs have evolved fully programmable parallel stream processors. The problem of face recognition in real time system is benefited by parallelism. With the aim of fulfilling both speed and accuracy criteria we present a GPU accelerated Face Recognition system. OpenCL is a heterogeneous computing language that allows extracting parallelism on different platforms like DSP processors, FPGAs, GPUs. The proposed kernel on GPU exploits coarse grain parallelism for Local Binary Pattern (LBP) histogram computation and ELTP (Enhanced Local Ternary Pattern) feature extraction. The proposed optimization techniques on local memory, work group size and work group dimension enhances the computation of face recognition on GPU further. As a result, we have achieved a speed up of 30 times to 300 times for 124*124 to 2048*2048 image sizes for LBP and ELTP feature extraction compared to CPU. We also present a robust real time face recognition and tracking on GPU using fusion of RGB and Depth images taken from Kinect sensor. The proposed segmentation after detection algorithm enhances the performances of recognition using LBP.

Face recognition is a field of biometrics that deals with identification of subjects based on features present in the images of their faces. The factors that make face recognition popular and favorite as compared to other biometric methods are easier operation and ability to identify subjects without their knowledge. With these features, face recognition has become an integral part of the present day security systems, targeting a smart and secure world. There are various factors that de ne the performance of a face recognition system. The most important among them are recognition accuracy of algorithm used and time taken for recognition. Recognition accuracy of the face recognition algorithm gets affected by changes in pose, facial expression and illumination along with occlusions in the images. There have been a number of algorithms proposed to enable recognition under these ambient changes. However, it has been hard to and a single algorithm that can efficiently recognize faces in all the above mentioned conditions. Moreover, achieving real time performance for most of the complex face recognition algorithms on embedded platforms has been a challenge. Real-time performance is highly preferred in critical applications such as identification of crime suspects in public. As available software solutions for FR have significantly large latency in recognizing individuals, they are not suitable for such critical real-time applications. This thesis focuses on real-time aspect of FR, where acceleration of the algorithms is achieved by means of parallel hardware architectures. The major contributions of this work are as follows. We target to design a face recognition system that can identify at most 30 faces in each frame of video at 15 frames per second, which amounts to 450 recognitions per second. In addition, we target to achieve good recognition accuracy along with scalability in terms of database size and input image resolutions. To design a system with these specifications, as a first step, we explore algorithms in literature and come up with a hybrid face recognition algorithm. This hybrid algorithm shows good recognition accuracy on face images with changes in illumination, pose and expressions, and also with occlusions. In addition the computations in the algorithm are modular in nature which are suitable for real-time realizations through parallel processing. The face recognition system consists of a face detection module to detect faces in the input image, which is followed by a face recognition module to identify the detected faces. There are well established algorithms and architectures for face detection in literature which can perform detection at 15 frames per second on video frames. Detected faces of different sizes need to be scaled to the size specified by the face recognition module. To meet the real-time constraints, we propose a hardware architecture for real-time bi-cubic convolution interpolation with dynamic scaling factors. To recognize the resized faces in real-time, a scalable parallel pipelined architecture is designed for the hybrid algorithm which can perform 450 recognitions per second on a database containing grayscale images of at most 450 classes on Virtex 6 FPGA. To provide flexibility and programmability, we extend this design to REDEFINE, a multi-core massively parallel reconfigurable architecture. In this design, we come up with FR specific programmable cores termed Scalable Unit for Region Evaluation (SURE) capable of performing modular computations in the hybrid face recognition algorithm. We replicate SUREs in each tile of REDEFINE to construct a face recognition module termed REDEFINE for Face Recognition using SURE Homogeneous Cores (REFRESH). There is a need to learn new unseen faces on-line in practical face recognition systems. Considering this, for real-time on-line learning of unseen face images, we design tiny processors termed VOP, Processor for Vector Operations. VOPs function as coprocessors to process elements under each tile of REDEFINE to accelerate micro vector operations appearing in the synaptic weight computations. We also explore deep neural networks which operate similar to the processing in human brain and capable of working on very large face databases. We explore the field of Random matrix theory to come up with a solution for synaptic weight initialization in deep neural networks for better classification . In addition, we perform design space exploration of hardware architecture for deep convolution networks and conclude with directions for future work.