Open Access Open Access  Restricted Access Subscription or Fee Access

An Effective Application of Illumination Invariant Transform on Face Recognition

P. Kannan, X.M. Binisha, J. Jebila

Abstract



This paper presents an image quality based face recognition system. Face recognition which plays a vital role in surveillance and security applications. The significance of this system is that it recognizes faces at different illumination conditions, facial expressions, pose and occlusion, among which the recognition at varying illumination conditions have greater accuracy. A practically easible and a challenging technique are employed in this project work. Image quality based approach has been used for recognizing face and identifying a person to increase recognition accuracy and to avoid misidentification. Histogram equalization is used as preprocessing method. The importance of histogram equalization is to normalize the illumination variations. The DWT is used for dimensionality reduction by reducing the number of samples thereby increasing the speed. This system provided 98.6% accuracy in recognizing faces from a set of 2680 images; we evaluate our approach on PIE, AT and T, MIT, Georgia tech face, PICS , AR, Bao and GTAVE face database.

Keywords


Facial expressions, Image quality, Histogram equalization, Illumination variations.

Full Text:

PDF

Refbacks

  • There are currently no refbacks.


Disclaimer/Regarding indexing issue:

We have provided the online access of all issues and papers to the indexing agencies (as given on journal web site). It’s depend on indexing agencies when, how and what manner they can index or not. Hence, we like to inform that on the basis of earlier indexing, we can’t predict the today or future indexing policy of third party (i.e. indexing agencies) as they have right to discontinue any journal at any time without prior information to the journal. So, please neither sends any question nor expects any answer from us on the behalf of third party i.e. indexing agencies.Hence, we will not issue any certificate or letter for indexing issue. Our role is just to provide the online access to them. So we do properly this and one can visit indexing agencies website to get the authentic information. Also: DOI is paid service which provided by a third party. We never mentioned that we go for this for our any journal. However, journal have no objection if author go directly for this paid DOI service.