Comparative Study on Hidden Markov Model Versus Support Vector Machine: A Component-Based Method for Better Face Recognition

In this paper, we report a comprehensive study of two well evolved and developed learning algorithms for effective Face Recognition (FR); viz. the Hidden Markov Model (HMM) and Support Vector Machines (SVM). It is evident that, the accuracy of recognition and efficiency in terms of time and speed of a FR system are directly proportional to the competency of the underlying learning algorithms. Here, we propose to compare the two acclaimed method stated above. A component-based approach is adapted to train face images for recognition. Each face image is divided into sub-states for both HMM and SVM algorithm. In attempt to achieve better rates of recognition, all face images are pre-processed and resizing which helps in reducing the overall complexity of the FR system. We run this proposed system against benchmarks accredited by previous researches.

I. Introduction

We humans have always had the innate skill to recognize and distinguish between faces of other beings since inception. As a matter of fact, human vision and recognition is very complex by nature, yet machines, only recently have shown the same ability to identify viz. Computer Vision. Face Recognition has been a prominent area of research in the image processing and pattern recognition domains. Over the past two decades, numerous FR researches and studies have been carried out in the field of Computer Vision (CV) [1]. FR has many real-time applications like biometrics, surveillance, security access control, Human Computer Interaction (HCI), robotic vision, video indexing and artificially intelligent smart environments. These applications demand robust, accurate, efficient, fast and easily trainable Face Recognition (FR) systems. Research and studies in attempt to achieve these goals has led to rapid development of cheap and yet so very competent FR system. This iterative process has ultimately led to commercialize the system.