A lexicon-driven approach for optimal segment combination in off-line recognition of unconstrained handwritten Korean words

Pattern Recognition

Volumn 34, Issue 7, 2001, Pages 1437-1447

  Kim, Soo H ^a   Jeong, S ^a   Suen, Ching Y ^b  

^a Chonnam National University   (South Korea)

^b Gina Cody School of Engineering and Computer Science   (Canada)

Author keywords

Handwritten Korean words; Lexicon driven word scoring; Nearest neighbor classifier; Over segmentation; Segment combination

Indexed keywords

IMAGE SEGMENTATION;

HANDWRITTEN WORDS RECOGNITION; LEXICON-DRIVEN APPROACH;

CHARACTER RECOGNITION;

PATTERN RECOGNITION;

EID: 0035400794     PISSN: 00313203     EISSN: None     Source Type: Journal    
DOI: 10.1016/S0031-3203(00)00098-4     Document Type: Article

References (20)

1. Integration of hand-written address interpretation technology into the United States postal service remote computer reader system
2. Sorting and recognizing cheques and financial documents
3. The advantage of using HMM-based approach for faxed word recognition
4. Cursive script recognition: A survey
5. A survey on the off-line recognition of handwritten Korean characters
6. Off-line handwritten word recognition using a hidden Markov model type stochastic network
7. Modeling and recognition of cursive words with hidden Markov models
8. Strategies for cursive script recognition using hidden Markov models
9. Alternatives to variable duration HMM in handwriting recognition
10. Lexicon directed segmentation-recognition procedure for unconstrained handwritten words
11. Character model word recognition
12. A lexicon driven approach to handwritten word recognition for real-time applications
13. An error detection/correction method for handwritten Hangul address recognition
14. Efficient postprocessing algorithm for error correction in handwritten Hangul address and human name recognition
15. Korean address recognition system
16. Handwritten Korean address recognition by combining minimum distance classification and dictionary look-up
17. Classification of hand-printed Kanji characters by the structured segment matching method
18. Handwritten Korean character image database PE92