Fourier fuzzy neural network for clustering of visual objects based on their gross shape and its application to handwritten character recognition

Author

Patil, P.M. ; Deshmukh, Manish ; Bonde, P.V. ; Dhabe, P.S. ; Sontakke, T.R.

Author_Institution

Dept. of Electron. & Comput. Sci. & Eng., SGGS Coll. of Eng. & Technol., Vishnupuri, India

Volume

3

fYear

2004

fDate

25-29 July 2004

Firstpage

2391

Abstract

In this paper, an unsupervised feedforward Fourier fuzzy neural network (FFNN) is proposed which is suitable for clustering of object images based on their gross shapes. This 3-layer feedforward neural network is described along with its training. Its performance is tested for synthetic image database containing objects of various shapes and with realistic image database of handwritten Devanagari digits. FFNN is found as superior to the fuzzy min-max neural network (FMN) clustering, and it takes less recall time per pattern than FMN.

Keywords

Fourier analysis; feedforward neural nets; fuzzy neural nets; handwritten character recognition; minimax techniques; neural net architecture; pattern clustering; visual databases; Fourier fuzzy neural network; fuzzy min-max neural network; handwritten character recognition; synthetic image database; three layer feedforward neural network; unsupervised feedforward neural network; visual object clustering; Application software; Character recognition; Feature extraction; Feeds; Fuzzy neural networks; Image databases; Image recognition; Network topology; Neural networks; Shape;

fLanguage

English

Publisher

ieee

Conference_Titel

Neural Networks, 2004. Proceedings. 2004 IEEE International Joint Conference on

ISSN

1098-7576

Print_ISBN

0-7803-8359-1

Type

conf

DOI

10.1109/IJCNN.2004.1381002

Filename

1381002