A Study on Similarity Computations in Template Matching Technique for Identity Verification
Journal Title: International Journal on Computer Science and Engineering - Year 2010, Vol 2, Issue 8
Abstract
This paper describes a study on the development of a human face verification system by merely using template matching (TM) as the main verification engine. In contrast to common face recognition techniques, our approach for the identity erification (face recognition) consists of matching the facial features extracted from the detected face. These facial features namely left eye, right eye and mouth regions; are detected using a system known as EMoTracker. As TM is sensitive to lighting, this study considered different type of lighting directions and similarity computation in TM. Three types of TM functions are evaluated in this paper: Sum of Squared ifference, Cross Correlation and Correlation Coefficient. In the experiments, YaleB Database is used. Based on the bservation results, using Correlation Coefficient is shown to be the most reliable similarity computation to handle different lighting conditions using TM.
Authors and Affiliations
Lam, , S. K. , , Yeong , C. Y. , , Yew , C. T. , Chai , W. S. , , Suandi , S. A.
Keywords
Related Articles
- EP ID EP139745
- DOI -
- Views 125
- Downloads 0
SEMU - An Adaptive Policy - Control Based Routing Approach to Provide Effective QoS over Wireless Sensor Networks
Error control mechanism carries vital importance in research aspects of Wireless Sensor Networks (WSNs) due to its limited energy constraints and minimal support for power communication. The survey and analysis provides...
DIGITAL IMAGE PROCESSING TECHNIQUES FOR DETECTION AND REMOVAL OF NOISE IN IMAGES IMPLEMENTING BLIND SOURCE SEPARATION
In different fields, the problem of Blind Source Separation (BSS) is known as a collection of linear combinations of unknown sources and worse the coefficients of the linear combinations that are unknown. The main proble...
Efficient Lossless Colour Image Compression Using Run Length Encoding and Special Character Replacement
Image compression, in the present context of heavy network traffic, is going through major research and development. The lossless compression techniques, presently in practise, follow three basic paradigms – character re...
AN EXTENDED METHOD FOR ORDER REDUCTION OF LARGE SCALE MULTI VARIABLE SYSTEMS
In this paper, an effective procedure to determine the reduced order model of higher order linear time invariant dynamic multivariable systems is discussed. Numerator and denominator polynomials of reduced order model ar...
A Highly Effective and Efficient Route Discovery & Maintenance in DSR
Mobile Ad Hoc Network (MANET) is collection of multi-hop wireless mobile nodes that communicate with each other without centralized control or established infrastructure. The wireless links in this network are highly err...