A New Distance Measure for Face Recognition System

Detecting the similarity of face image aims to determine the image of a face for verification purpose of documents such as passport, driving license, ID cards, etc. Similarity measures are essential to solve many pattern recognition problems such as classification, clustering, and retrieval problems. There are efforts in finding the appropriate measures among such a plethora of choices because it is of fundamental importance to solve our problems. A new approach for face recognition based on similarity measure method is introduced.

The face expression recognition problem is challenging because different individuals display the same expression differently [1].Here PCA algorithm is used for the feature extraction. Distance metric or matching criteria is the main tool for retrieving similar images from large image databases for the above category of search. Two distance metrics, such as the L1 metric (Manhattan Distance), the L2 metric (Euclidean Distance) have been proposed in the literature for measuring similarity between feature vectors. In content-based image retrieval systems, Manhattan distance and Euclidean distance are typically used to determine similarities between a pair of image [2]. Here facial images of three subjects with different expression and angles are used for classification. Experimental results are compared and the results show that the Manhattan distance performs better than the Euclidean Distance.

International Journal of Engineering & Technology, 2018

Face recognition plays a vital role and has a huge scope in the field of biometrics, image processing, artificial intelligence, pattern recognition and computer vision. This paper presents an approach to perform face recognition using Principal Components Analysis (PCA) as feature extraction technique and different distance measures as matching techniques. The proposed method is developed after the deep study of a number of face recognition methods and their outcomes. In the proposed method, Principal Components Analysis is used for facial features extraction and data representation. It generates eigenvalues of the facial images, hence, reduces the dimensionality. The recognition is produced using three different matching techniques (Euclidean, Manhattan and Mahalanobis) and the results are` presented. Yale and Aberdeen Face Databases are used to test and analyze the results of the proposed method.

Face recognition has become one of the robust means of authentication and hence lots of research has been carried on in this regard. For any face recognition system, the availability of a standard database consisting of appropriate face image samples is very important, since it serves as a benchmark for testing and comparing the results directly for the face recognition algorithms. From the last few decades, the creation of face database by proper acquisition of face images, has been an interesting research topic among research community. While there are many face databases available, the appropriate choice should be based on the task given (age, lighting, poses, expression, etc.). This paper makes a scrutinizing study of the existing face databases. The aim here is to give a clear picture to the researchers regarding the selection of the face databases to build effective face recognition systems.

DergiPark (Istanbul University), 2022

Facial recognition is used efficiently in human-computer interactions, passports, driver's licence, border controls, video surveillance and criminal identification, and is an important biometric's security option in many device-related security requirements. In this paper, we use Eigenface recognition based on the Principal Component Analysis (PCA) to develop the project. PCA aims to reduce the size of large image matrices and is used for feature extraction. Then, we use the euclidean distance method for classification. The dataset used in this project was obtained by AT&T Laboratories at Cambridge University [1]. The training dataset contains grayscale facial images of 40 people; each person has 10 different facial images taken from different angles and emotions. This study aims to give researchers a hunch before they start to develop image recognition using deep learning methods. It also shows that face recognition can be done without deep learning.

Countless number of applications varying from music, document classification, image and video retrieval, require measuring similarity between the query and the corresponding class. To achieve this, features, that belong to these objects are extracted and modified to produce an N-dimensional feature vector. A database containing these feature vectors is constructed, allowing query vectors to be applied and the distance between these vectors and those stored in the database to be calculated. As such, the careful choice of suitable proximity measures is a crucial success factor in pattern classification. The evaluation presented in this paper aims at showing the best distance measure that can be used in visual retrieval and more specifically in the field of face recognition. There exist a number of commonly used distance or similarity measures, where we have tested and implemented eight of these metrics. These eight metrics are famous in the field of pattern recognition and are recomme...

Journal of Software Engineering and Applications, 2015

Face recognition systems have been in the active research in the area of image processing for quite a long time. Evaluating the face recognition system was carried out with various types of algorithms used for extracting the features, their classification and matching. Similarity measure or distance measure is also an important factor in assessing the quality of a face recognition system. There are various distance measures in literature which are widely used in this area. In this work, a new class of similarity measure based on the Lp metric between fuzzy sets is proposed which gives better results when compared to the existing distance measures in the area with Linear Discriminant Analysis (LDA). The result points to a positive direction that with the existing feature extraction methods itself the results can be improved if the similarity measure in the matching part is efficient.

IAEME PUBLICATION, 2014

With the growth of information technology there is a greater need of high security, so biometric authentication systems are gaining importance. Face recognition is more used because it’s easy and non intrusive method during acquisition procedure. Here PCA algorithm is used for the feature extraction. Distance metric or matching criteria is the main tool for retrieving similar images from large image databases for the above category of search. Two distance measures, such as the Manhattan Distance, Mahalanobis Distance have been proposed in the literature for measuring similarity between feature vectors. In content-based image retrieval systems, Manhattan distance and Euclidean distance are typically used to determine similarities between a pair of image. Here facial images of three subjects with different expression and angles are used for classification. Experimental results are compared and the results show that the Mahalanobis distance performs better than the Manhattan Distance.

2011

INTRODUCTION Abstract – Face recognition has received substantial attention in recent years due to applications in research fields such as biometrics community and computer vision. A lot of face recognition algorithms have been developed during the past decades. These algorithms can be classified into appearance-based and model-based schemes. Principal Component Analysis (PCA) and Linear Discriminant Analysis (LDA) or Fisher Discriminant Analysis (FDA) are two typical linear appearance-algorithms, and Elastic Bunch Graph Matching (EBGM) is a twodimensional model-based approach. This paper reviews the three classical methods and a typical face image database for standard testing. After the review is presented, the algorithms are implemented on Matlab environment. Scenarios and performance benchmarking are compared for each of the algorithms. The effectiveness and bottlenecks of each computation are discussed and possible improvements in different applications are given.