Neuro-fuzzy fusion in a multimodal face recognition using PCA, ICA and SIFT
by Vandana S. Bhat; Jagadeesh D. Pujari
International Journal of Computational Vision and Robotics (IJCVR), Vol. 6, No. 4, 2016

Abstract: Face recognition has been widely used in much real-time application for biometric authentication. This paper is discussed with the implementation of multimodal face recognition with neuro-fuzzy fusion. We used principal component analysis, independent component analysis and scale invariant feature transform for feature extraction and result are fused with neuro fuzzy inference system to obtain the recognition ID. PCA is the statistical method for face recognition under the enormous subject of 'factor analysis'. This unsupervised method for a set of reference images represents faces as linear combination. The generalised expression (independent component analysis) can treat pixels as observations and images at random variables or vice versa. Another method considered is scale invariant feature transform that scales histogram orientation for dominant feature determination invariant to illumination, rotation and is robust against considerable amount of noise. This research studies the performance evaluation of recognition method constructed in union with neuro fuzzy inference system employing PCA, ICA and SIFT.

Online publication date: Wed, 28-Sep-2016

The full text of this article is only available to individual subscribers or to users at subscribing institutions.

 
Existing subscribers:
Go to Inderscience Online Journals to access the Full Text of this article.

Pay per view:
If you are not a subscriber and you just want to read the full contents of this article, buy online access here.

Complimentary Subscribers, Editors or Members of the Editorial Board of the International Journal of Computational Vision and Robotics (IJCVR):
Login with your Inderscience username and password:

Username:        Password:          Forgotten your password?

Want to subscribe?
A subscription gives you complete access to all articles in the current issue, as well as to all articles in the previous three years (where applicable). See our Orders page to subscribe.

If you still need assistance, please email subs@inderscience.com