A handwritten numeral recognition algorithm based on independent components analysis

Lai Jiang; Zhen Ji; Li Zhang; Jihong Zhang

doi:10.1117/12.538845

Translator Disclaimer

25 September 2003 A handwritten numeral recognition algorithm based on independent components analysis

Lai Jiang; Zhen Ji; Li Zhang; Jihong Zhang

Author Affiliations +

Proceedings Volume 5286, Third International Symposium on Multispectral Image Processing and Pattern Recognition; (2003) https://doi.org/10.1117/12.538845
Event: Third International Symposium on Multispectral Image Processing and Pattern Recognition, 2003, Beijing, China

Abstract

Independent Components Analysis (ICA) is an effective approach of blind source separation and has been received much more attention because of its potential application in signal processing such as telecommunication and image processing. Feature extraction of images has been also focused as one of prominent applications of ICA. Nine Stroke Density (NSD) feature extraction method will provide sufficient information to the recognition engine. Several other feature extraction methods are discussed and compared to stroke density method in detail. ICA extracts the underlying statistically independent components from a mixture of the NSD feature vectors. These independent components are feed into the neural netowrk for the recognition purpose. The experiment results show that ICA performs well for feature extraction and this proposed method is more effective in recognizing handwriting character than merely using neural networks directly.

Citation Download Citation

Lai Jiang, Zhen Ji, Li Zhang, and Jihong Zhang "A handwritten numeral recognition algorithm based on independent components analysis", Proc. SPIE 5286, Third International Symposium on Multispectral Image Processing and Pattern Recognition, (25 September 2003); https://doi.org/10.1117/12.538845

PROCEEDINGS
4 PAGES

DOWNLOAD PDF SAVE TO MY LIBRARY

SHARE

GET CITATION

< Previous Article

|

Next Article >

KEYWORDS

Independent component analysis

Feature extraction

Neural networks

Detection and tracking algorithms

Image processing

Optical character recognition

Neurons

Show All Keywords

RELATED CONTENT

Exploring multiple feature combination strategies with a recurrent neural network...
Proceedings of SPIE (February 08 2015)

Handwritten character recognition using the hybrid learning rule
Proceedings of SPIE (December 16 1992)

Identification and correction of rejection and substitution errors in optical...
Proceedings of SPIE (April 14 1993)

Frequency-based pattern recognition using neural networks
Proceedings of SPIE (October 01 1991)

Assembly line inspection using neural networks
Proceedings of SPIE (September 01 1990)

Pattern recognition by cooperating neural networks
Proceedings of SPIE (December 16 1992)

Appearance-based three-dimensional object recognition using independent component analysis
Proceedings of SPIE (July 17 2000)

Subscribe to Digital Library

Receive Erratum Email Alert

Show All Keywords

Keywords/Phrases

Search In:

Publication Years