Feature Extraction of Off-line Handwritten Characters Based on Optical Neural Field


The Transactions of the Korea Information Processing Society (1994 ~ 2000), Vol. 6, No. 12, pp. 3530-3538, Dec. 1999
10.3745/KIPSTE.1999.6.12.3530,   PDF Download:

Abstract

In this paper, we propose a novel method for feature extraction of off-line handwritten characters recognition based on human optical neural field model. The proposed feature extraction system divide into three parts; 1) smoothing process, 2) removing boundaries(boundary lines), 3) extracting feature information. The proposed system first removes rough pixels which are easy to occur in handwritten characters. The system then extracts and removes the boundary information which have no influence on characters recognition. Finally, the feature information for off-line handwritten characters recognition extracted. With PE2 Hangul database, we perform feature extraction experiments for off-line handwritten characters recognition. In the experiment result, the proposed system based on optical neural field shows that can extract the feature information of off-line handwritten characters including curve line, circles, quadrangles and so on.


Statistics
Show / Hide Statistics

Statistics (Cumulative Counts from September 1st, 2017)
Multiple requests among the same browser session are counted as one view.
If you mouse over a chart, the values of data points will be shown.


Cite this article
[IEEE Style]
K. H. Hong, E. H. Jeong, B. C. Ahn, "Feature Extraction of Off-line Handwritten Characters Based on Optical Neural Field," The Transactions of the Korea Information Processing Society (1994 ~ 2000), vol. 6, no. 12, pp. 3530-3538, 1999. DOI: 10.3745/KIPSTE.1999.6.12.3530.

[ACM Style]
Keong Ho Hong, Eun Hwa Jeong, and Byung Chul Ahn. 1999. Feature Extraction of Off-line Handwritten Characters Based on Optical Neural Field. The Transactions of the Korea Information Processing Society (1994 ~ 2000), 6, 12, (1999), 3530-3538. DOI: 10.3745/KIPSTE.1999.6.12.3530.