Kiran Davakhar et al. Int. Journal of Engineering Research and Application www.ijera.com Vol. 3, Issue 5, Sep-Oct 2013, pp.178-182 www.ijera.com 178 | Page Person Authentication Using Color Face Recognition Kiran Davakhar 1 , S. B. Mule 2 , Achala Deshmukh 3 1 (Department of E&TC, Sinhgad COE, Vadgaon, Pune, Pune University, India) 2 (Department of E&TC, Sinhgad COE, Vadgaon, Pune, Pune University, India) 3 (Department of E&TC, Sinhgad COE, Vadgaon, Pune, Pune University, India) Abstract Face is a complex multidimensional structure and needs good computing techniques for recognition. Our approach consists of two feature extraction algorithms that are Gabor wavelet and local binary pattern for the purpose of color face recognition. These methods provide excellent recognition rates for face images taken under severe variation in pose, illumination as well as for small resolution face images. Face recognition is done by Principal Component Analysis. This work shows the performance of color face recognition with YCbCr color space using GW and LBP. The experiments are performed on FEI color database. Result includes recognition rate (in percent) for different method such as YCbCr and Gray using GW and LBP for different pixels resolution such as 54x36, 81x54, and 108x72. Keywords — Gabor wavelet, local binary pattern, Principal Component Analysis, FEI color database, YCbCr color space. I. INTRODUCTION The face is our primary focus of attention in social life playing an important role in conveying identity and emotions. We can recognize a number of faces learned throughout our lifespan and identify faces at a glance even after years of separation [1]. Face detection and recognition is attracting a lot of interest in areas such as network security, content indexing and retrieval, and video compression, because people are the object of attention in a lot of video or images. To perform such real-time detection and recognition, novel algorithms are needed which better current efficiencies and speeds. After four decades of research and with today’s wide range of applications and new possibilities, researchers are still trying to find the algorithm that best works in different illuminations, environments, over time and with minimum error [2]. This work pretends to explore the potential of a Gabor wavelet [4] and Local Binary Patterns (LBP) [5] and the main motivations to study it in this work are: It can be applied for both detection and recognition and robustness to pose, low resolution and illumination changes [3]. Features extracted from a face are processed and compared with similarly processed faces present in the database. If a face is recognized it is known or the system may show a similar face existing in database else it is unknown. In surveillance system if an unknown face appears more than one time then it is stored in database for further recognition. These steps are very useful in criminal identification. The rest of this paper is organized as follows: section II, we describe generic face recognition system. In section III, we describe framework of color face recognition. In section IV, we describe feature extraction approach. In section V, we present face recognition using PCA. Experimentation and results generated in Section VI. Conclusions and future scope constitute Section VII. II. FACE RECOGNITION SYSTEM Figure 1 A generic face recognition system [3] From figure 1, the input of a face recognition system is always an image or video stream. The output is an identification or verification of the subject or subjects that appear in the image or video. Face detection is defined as the process of extracting faces from scenes. So, the system positively identifies a certain image region as a face. The next step feature extraction involves obtaining relevant facial features from the data. These features could be certain face regions, variations, angles or measures, which can be human relevant or not. Finally, system does recognize the face. In an identification task, the system would report an identity from a database. This phase involves a comparison method, a classification algorithm and an accuracy measure [10]. III. FRAMEWORK OF COLOR FR As shown in Figure 2, the color FR framework using GW and LBP consists of three major steps: color space conversion and partition, feature extraction, and combination and classification. A face image represented in the RGB color space is first translated, rotated, and rescaled to a fixed template, yielding the corresponding aligned face image. Face Detection Feature Extraction Face Recognition RESEARCH ARTICLE OPEN ACCESS