MULTILEVEL POST-PROCESSING FOR KOREAN CHARACTER-RECOGNITION USING MORPHOLOGICAL ANALYSIS AND LINGUISTIC EVALUATION

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 informati on alone is not sufficient for high-quality character-recognition appl ications, and we need much higher-level contextual information to impr ove the recognition results. This paper presents a domain independent postprocessing technique that utilizes multi-level morphological, synt actic, 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) gen eration through morphological analysis, and final single eojeol-sequen ce selection by linguistic evaluation. All the required linguistic inf ormation and probabilities are automatically acquired from a statistic al corpus analysis. Experimental results demonstrate the effectiveness of our method, yielding an error correction rate of 80.46%, and impro ved recognition rate of 95.53% from the before-post-processing rate of 71.2% for single best-solution selection. (C) 1997 Pattern Recognitio n Society. Published by Elsevier Science Ltd.