HIGH-SPEED FACE RECOGNITION ppt

[seminar surveyer]

---

[attachment=8405]

A.MURALI KRISHNA

CONTENTS

Abstract
Introduction
Feature extraction
Classification using RBF neural networks
Conclusion

INTRODUCTION

Human face recognition has become a very active research area in recent years mainly due to increasing security demands and its potential commercial and law enforcement applications.

FEATURE EXTRACTION

DCT (discrete cosine transform)
CLUSTERING
FLD (fisher’s linear discriminant)

FLD
In order to obtain the most salient and invarient feature of human faces ,the FLD is applied in the truncated DCT domain .

CLASSIFICATION USING RBF NN
Width estimation
Weight adjustment

CONCLUSION

To maintain the main facial features.
Data independency fast computational speed.
Effect of non-uniform illumination can be alleviated.

---