2 Hits in 4.9 sec

Correction for Misrecognition of Korean Texts in Signboard Images using Improved Levenshtein Metric

Myung-Hun Lee
2012 KSII Transactions on Internet and Information Systems  
This study proposes a correction method for misrecognition of Korean Texts in signboard images using improved Levenshtein metric.  ...  As a result, the proposed method based on improved Levenshtein metric represents an improvement in recognition rates 31.5% on average compared to that of conventional methods.  ...  Correction of Misrecognized Characters using iLM In this study, an improved Levenshtein Metric (iLM) that improves Levenshtein Metric (LM) algorithm, which has been most largely used among character correction  ... 
doi:10.3837/tiis.2012.02.016 fatcat:lrzq52swdrbwbimlao2rnfvtfi

Weighted Disassemble-based Correction Method to Improve Recognition Rates of Korean Text in Signboard Images
간판영상에서 한글 인식 성능향상을 위한 가중치 기반 음소 단위 분할 교정

Myung-Hun Lee, Hyung-Jeong Yang, Soo-Hyung Kim, Guee-Sang Lee, Sun-Hee Kim
2012 The Journal of the Korea Contents Association  
In this paper, we propose a correction method using phoneme unit segmentation to solve misrecognition of Korean Texts in signboard images using weighted Disassemble Levenshtein Distance.  ...  For verifying the efficiency of the proposed method, a database dictionary is built using 1.3 million words of nationwide signboard through removing duplicated words.  ...  Tanaka, and T.Kasai, "A Method for the Correction of Garbled Words Based on the Levenshtein Metric," Computers, IEEE Transactions, Vol.C-25, No.2, pp.172-178, 1976. ▪2003년 ~ 2005년 : 카네기멜런 대학교 연구원 ▪2005년  ... 
doi:10.5392/jkca.2012.12.02.105 fatcat:igo2hm2c35fuxdah6n3zqumnfa