IACSIT International Journal of Engineering and Technology Vol. 2, No.1, February, 2010 ISSN: 1793-8236 117 Abstract—This paper brings out a new approach of information extraction based on fuzzy logic, which can be used for robust face recognition system. We have applied a fuzzification operation to extract the pixel wise association of face images to different classes. The fuzzification operation uses  membership function to obtain the degree of belonging of a particular pixel to all classes. Further nearest neighbor classification using correlation coefficient and principal component analysis are used to obtain the classification error over AT&T face database. The results clearly confirmed the superiority of proposed approach. Index Terms—Face recognition, fuzzy logic, information extraction,  membership. I. I NTRODUCTION Within the last several years, face recognition has been very active research area of computer vision. This is because of its wide range of applications, from identity authentication, access control, law enforcement and surveillance to human-computer interaction [1], [2]. Consequently, many algorithms have been proposed [4]-[7], [10]-[15]. Even though current machine recognition systems have reached a certain level of maturity, their success is limited by the real applications constraints, like pose, illumination and expression. A face as a three-dimensional object subject to varying constraints and it is to be identified based on its two-dimensional image, inherently limits the recognition rate [3]. Broadly, face recognition methods can be categorized into two groups: feature-based and appearance-based. In feature-based approach, a set of local features is extracted from the image such as eyes, nose, mouth etc. and they are used to classify the face. The major benefit of this approach is its relative robustness to variations in illumination, contrast, and small amounts of out-of-plane rotation. But there is generally no Manuscript received Sep. 3, 2009. Virendra P. Vishwakarma is with the department of Computer Science and Engineering, Amity School of Engineering Technology (Guru Gobind Singh Indraprastha University), 580, Delhi Palam Vihar Road, Bijwasan, New Delhi-110061, India. (email: vpvishwakarma@aset.amity.edu, mobile: 91-9891307464, tel.: 91-11-28062106, fax: 91-11-28062105). Sujata Pandey is with the department of Electronics and Communication Engineering, Amity University (e-mail: spandey@amity.edu). M. N. Gupta is with the department of Computer Science and Engineering, Amity School of Engineering Technology (Guru Gobind Singh Indraprastha University), (e-mail: mngupta@gmail.com). reliable and optimal method to extract an optimal set of features. Another problem of this approach is that it may cause some loss of useful information in the feature extraction step. The appearance-based approaches use the entire image as the pattern to be classified, thus using all information available in the image. However, they tend to be more sensitive to image variations. Thus major issue of designing an appearance-based approach is the extraction of useful information which can be used for efficient face recognition system that is robust under different constraints (pose, illumination, expressions etc.) [4], [6]. In this paper we are utilizing appearance-based approach of face recognition in our implementation. When using appearance-based approach, an image of size mxn pixels is represented as a vector in mn-dimensional space. But for an efficient and fast recognition system, the mn-dimensional space is quite large. This generates the need for dimension reduction algorithms. While reducing the dimension, these algorithms must also possess enhanced discrimination power. Some of the most used algorithms are principal component analysis (PCA), linear discriminant analysis (LDA), and independent component analysis (ICA) [5]-[7]. These linear algorithms project data linearly from high dimensional image space to a low dimensional subspace. Since the entire image space along with constraints is highly non-linear, they are unable to preserve the non-linear variations necessary to differentiate among different classes. Due to this, the linear methods fail to achieve high face recognition accuracy [3]. Soft computing techniques (artificial neural networks, fuzzy logic and genetic algorithms) have emerged as an important methodology for analysis in computer vision research. Artificial neural network is a powerful tool to resolve the nonlinearity imposed by different constraints [12], [13]. Similarly, fuzzy logic [16], [17] is used for modeling human thinking and perception [18]. In place of using crisp set (theory of binary propositions), fuzzy systems reason with fuzzy set of multi-values. It is well established that the effectiveness of human brain is not only from precise cognition, but also from analysis based on fuzzy set and fuzzy logic. Uncertainty is always involved in real application constraints and this is a common problem in pattern recognition. Analysis based on fuzzy logic has proved to generate substantial improvement in pattern recognition results [8], [9], [14], [15], [18]. Fuzzy based Pixel wise Information Extraction for Face Recognition Virendra P. Vishwakarma, Member, IACSIT, Sujata Pandey, Member, IEEE and M. N. Gupta