A handwritten character recognition system using directional element feature and asymmetric Mahalanobis distance
- 1 March 1999
- journal article
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Pattern Analysis and Machine Intelligence
- Vol. 21 (3), 258-262
- https://doi.org/10.1109/34.754617
Abstract
This paper presents a precise system for handwritten Chinese and Japanese character recognition. Before extracting directional element feature (DEF) from each character image, transformation based on partial inclination detection (TPID) is used to reduce undesired effects of degraded images. In the recognition process, city block distance with deviation (CBDD) and asymmetric Mahalanobis distance (AMD) are proposed for rough classification and fine classification. With this recognition system, the experimental result of the database ETL9B reaches to 99.42%.This publication has 7 references indexed in Scilit:
- Learning Pattern Generation for Handwritten Chinese Character using Pattern Transform Method with Cosine FunctionPublished by Institute of Electrical and Electronics Engineers (IEEE) ,2006
- Effect of the perturbed correlation method for optical character recognitionPublished by Institute of Electrical and Electronics Engineers (IEEE) ,2002
- Multi-stroke relaxation matching method for handwritten chinese character recognitionPattern Recognition, 1998
- Handwritten Chinese character recognition by metasynthetic approachPattern Recognition, 1997
- Optical recognition of handwritten Chinese characters: Advances since 1980Pattern Recognition, 1993
- Small sample size effects in statistical pattern recognition: recommendations for practitionersIEEE Transactions on Pattern Analysis and Machine Intelligence, 1991
- Recognition of Printed Chinese CharactersIEEE Transactions on Electronic Computers, 1966