Trademark classification by shape using ensemble of RBFNNs

Author

Lai, Wei-wei ; Ng, Wing W Y ; Chan, Patrick P K ; Yeung, Daniel S.

Author_Institution

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

Volume

1

fYear

2010

fDate

11-14 July 2010

Firstpage

391

Lastpage

396

Abstract

Identification of similar trademarks is important in trademark registration. Shape feature could intuitively and effectively describes an object in a given image. Therefore, shape feature plays an important role in content-based image retrieval (CBIR) systems. The shape feature is particularly suitable for trademark image retrieval (TIR) systems. In this paper, we propose an effective solution for TIR by using Hu´s invariant moments and an ensemble of Radial Basis Function Neural Networks (RBFNN) trained via a minimization of the Localized Generalization Error Model (L-GEM). The proposed method outperforms TIR with similarity measure based on Euclidean distance.

Keywords

content-based retrieval; feature extraction; image classification; radial basis function networks; shape recognition; CBIR; Euclidean distance; RBFNN; TIR; content based image retrieval; radial basis function neural networks; shape feature; trademark classification; trademark image retrieval; trademark registration; Euclidean distance; Feature extraction; Image color analysis; Image retrieval; Shape; Trademarks; Training; CBIR; L-GEM; Shape Feature; Trademark Image Retrieval;

fLanguage

English

Publisher

ieee

Conference_Titel

Machine Learning and Cybernetics (ICMLC), 2010 International Conference on

Conference_Location

Qingdao

Print_ISBN

978-1-4244-6526-2

Type

conf

DOI

10.1109/ICMLC.2010.5581030

Filename

5581030