The impact of image block size on face feature extraction using Discrete Cosine Transform

Author

Kulkani, Sameer S. ; Moriarty, John ; Hung, Chih-Cheng

Author_Institution

Sch. of Comput. & Software Eng., Southern Polytech. State Univ., Marietta, GA, USA

fYear

2010

fDate

18-21 March 2010

Firstpage

98

Lastpage

101

Abstract

In this paper we conduct an experiment to study the effects of multiple block sizes in face images using the Discrete Cosine Transform (DCT) algorithm. Facial features are extracted from each block using the DCT algorithm. These features are then combined to form a feature vector for facial recognition. The goal of the paper is to discover if there is an underlying principle for determining the best block size for increasing the recognition accuracy with the DCT, when it is being used for facial recognition. The support vector machine (SVM) algorithm is used for facial recognition experiments.

Keywords

discrete cosine transforms; face recognition; feature extraction; support vector machines; DCT algorithm; SVM algorithm; discrete cosine transform; face feature extraction; face image; facial recognition; feature vector; image block size; support vector machine; Discrete cosine transforms; Face recognition; Feature extraction; Image classification; Image coding; Image storage; Software algorithms; Software engineering; Support vector machine classification; Support vector machines; Discrete Cosine Transform (DCT); Facial Recognition; Feature Extraction; Support Vector Machines (SVM);

fLanguage

English

Publisher

ieee

Conference_Titel

IEEE SoutheastCon 2010 (SoutheastCon), Proceedings of the

Conference_Location

Concord, NC

Print_ISBN

978-1-4244-5854-7

Type

conf

DOI

10.1109/SECON.2010.5453913

Filename

5453913