A new approach towards facial recognition system using DCT & LVQ

Author

Sharma, Shipra ; Raina, Manish ; Shruti, Devisha ; Sehgal, Gorija

Author_Institution

Dept. of Comput. Sci. & Eng., Jaypee Univ. of Inf. Technol., Solan

fYear

2009

fDate

8-11 Feb. 2009

Firstpage

1

Lastpage

4

Abstract

This paper introduces a novel means of neuron coding allowing us to recognize the face of an unknown individual. The algorithm involves the application of segmentation and Discrete Cosine Transform (DCT) and is used to perform the facial recognition after training and classification from a neural network. The algorithm determines features´ position and pixel value using image segmentation and DCT which is then applied to the neural network. The neural network used in the present discussion is Linear Vector Quantization (LVQ). The main aim here has been to incorporate varied constraints of pose and expressions of inputs facilitating insensitivity to system fluctuations.

Keywords

discrete cosine transforms; face recognition; image classification; image segmentation; learning (artificial intelligence); vector quantisation; DCT; LVQ; classification; discrete cosine transform; facial recognition system; image segmentation; linear vector quantization; neural network; neuron coding; Discrete cosine transforms; Face recognition; Facial features; Image recognition; Image segmentation; Neural networks; Pixel; Signal processing algorithms; Testing; Vector quantization;

fLanguage

English

Publisher

ieee

Conference_Titel

Intelligent Signal Processing and Communications Systems, 2008. ISPACS 2008. International Symposium on

Conference_Location

Bangkok

Print_ISBN

978-1-4244-2564-8

Electronic_ISBN

978-1-4244-2565-5

Type

conf

DOI

10.1109/ISPACS.2009.4806752

Filename

4806752