Image classification using L-GEM based RBFNN with local feature keypoints and MPEG-7 descriptors

Author

Wang, Qian-cheng ; Yeung, Daniel S. ; Ng, Wing W Y ; Lin, Cheng-hu ; Sun, Bin-bin ; Li, Jin-cheng

Author_Institution

Machine Learning & Cybern. Res. Center, South China Univ. of Technol., Guangzhou, China

Volume

6

fYear

2009

fDate

12-15 July 2009

Firstpage

3215

Lastpage

3220

Abstract

Image with MPEG-7 descriptors as features may loss local details. In this work, we combine MPEG-7 descriptors with local feature key points to cover both global and local image characteristics. Images are classified by a Radial Basis Function Neural Network (RBFNN) trained via a minimization of Localized Generalization Error Model (L-GEM). In this paper, we extract local feature key points by the Scale Invariant Feature Transform (SIFT). Four color and three texture MPEG-7 descriptors are extracted. Experimental results show that the introduction of local feature key points effectively improves the testing accuracy of image classification.

Keywords

image classification; minimisation; radial basis function networks; transforms; L-GEM; RBFNN; image characteristics; image classification; local feature; localized generalization error model; minimization; radial basis function neural network; scale invariant feature transform; texture MPEG-7 descriptor; Computer science; Cybernetics; Data mining; Feature extraction; Histograms; Image classification; MPEG 7 Standard; Machine learning; Support vector machine classification; Support vector machines; Image Classification; Local Feature Key points; Localized Generalization Error Model; MPEG-7 Descriptors;

fLanguage

English

Publisher

ieee

Conference_Titel

Machine Learning and Cybernetics, 2009 International Conference on

Conference_Location

Baoding

Print_ISBN

978-1-4244-3702-3

Electronic_ISBN

978-1-4244-3703-0

Type

conf

DOI

10.1109/ICMLC.2009.5212711

Filename

5212711