Multi-level post-processing for Korean character recognition using morphological analysis and linguistic evaluation
SCIE
SCOPUS
- Title
- Multi-level post-processing for Korean character recognition using morphological analysis and linguistic evaluation
- Authors
- Lee, G; Lee, JH; Yoo, J
- Date Issued
- 1997-08
- Publisher
- PERGAMON-ELSEVIER SCIENCE LTD
- Abstract
- Most of the post-processing methods for character recognition rely on contextual information of character and word-fragment levels. However, due to linguistic characteristics of Korean, such low-level information alone is not sufficient for high-quality character-recognition applications, and we need much higher-level contextual information to improve the recognition results. This paper presents a domain independent postprocessing technique that utilizes multi-level morphological, syntactic, and semantic information as well as character-level information. The proposed post-processing system performs three-level processing: candidate character-set selection, candidate eojeol (Korean word) generation through morphological analysis, and final single eojeol-sequence selection by linguistic evaluation. All the required linguistic information and probabilities are automatically acquired from a statistical corpus analysis. Experimental results demonstrate the effectiveness of our method, yielding an error correction rate of 80.46%, and improved recognition rate of 95.53% from the before-post-processing rate of 71.2% for single best-solution selection. (C) 1997 Pattern Recognition Society. Published by Elsevier Science Ltd.
- Keywords
- Korean character recognition; post-processing; morphological analysis; part-of-speech tagging; co-occurrence patterns; linguistic evaluation
- URI
- https://oasis.postech.ac.kr/handle/2014.oak/21276
- DOI
- 10.1016/S0031-3203(96)00156-2
- ISSN
- 0031-3203
- Article Type
- Article
- Citation
- PATTERN RECOGNITION, vol. 30, no. 8, page. 1347 - 1360, 1997-08
- Files in This Item:
- There are no files associated with this item.
Items in DSpace are protected by copyright, with all rights reserved, unless otherwise indicated.