A review of segmentation and contextual analysis techniques for text recognition

Pattern Recognition

Volumn 23, Issue 3-4, 1990, Pages 337-346

  Elliman, D G ^a   Lancaster, I T ^b  

^a UNIVERSITY OF NOTTINGHAM   (United Kingdom)

^b PAFEC Ltd ^*  (United Kingdom)

Author keywords

Contextual processing; Dictionary structure; Levenshtein Distance N gram techniques; Markov methods; Text processing; Text recognition; Text segmentation; Viterbi Algorithm

Indexed keywords

CHARACTER RECOGNITION; CHARACTER RECOGNITION, OPTICAL; COMPUTER VISION;

CHARACTER SEGMENTATION; CONTEXTUAL RECOGNITION; DICTIONARY LOOK-UP METHODS; MARKOV-BASED METHODS; SCANNING; TEXT RECOGNITION;

IMAGE PROCESSING;

CONTEXTUAL PROCESSING; DICTIONARY STRUCTURE; TEXT PROCESSING; TEXT RECOGNITION;

EID: 0025198769     PISSN: 00313203     EISSN: None     Source Type: Journal    
DOI: 10.1016/0031-3203(90)90021-C     Document Type: Article

References (58)

1. Document analysis system
2. Automatic recognition of handprinted characters - the state of the art
3. Character recognition by computer and applications
4. An overview of character recognition methodologies
5. Combined symbol matching facsimile data compression system
6. Address location on envelopes
7. Printed text discrimination
8. Study of extracting Japanese newspaper article
9. Automatic separation of text, graphic and picture segments in printed material
10. Procedures for an automatic segmentation of text, graphic and halftone regions in documents
11. Block segmentation and text extraction in mixed text/image documents
12. Representation and segmentation of document images
13. A step towards intelligent document input to computers
14. Recursive segmentation and classification of composite character patterns
15. Character image segmentation
16. Recognition of isolated and simply connected handwritten numerals
17. Context-directed segmentation algorithm for handwritten numeral strings
18. A robust algorithm for text string separation from mixed text/graphics images
19. The use of context in pattern recognition
20. Error bounds for convolutional codes and an asymptomatically optimum decoding algorithm
21. The Viterbi Algorithm
22. The Viterbi Algorithm as an acid in text recognition
23. Experiments in text recognition with the modified Viterbi Algorithm
24. Decision making in Markov chains applied to the problem of pattern recognition
25. A. simplified heuristic version of a recursive Bayes algorithm for using context in text recognition
26. Contextual word recognition using probabilistic relaxation labelling
27. Contextual word recognition using binary diagrams
28. A contextual postprocessing system for error correction using binary n-grams
29. Context in word recognition
30. A binary N-gram technique for automatic correction of substitution deletion insertion and reversal errors in words
31. A technique for computer detection and correction of spelling errors
32. Binary codes capable of correcting deletions, insertions, and reversals
33. A method for the correction of garbled words based on the Levenshtein Metric
34. Synchronisation and substitution error correcting codes for the Levenshtein Metric
35. The string to string correction problem
36. An extension of the string to string correction problem
37. A faster algorithm computing string edit distance
38. Approximate string matching
39. Spelling correction using probabilistic methods
40. Trie memory
41. Digital searching
42. The smallest automaton recognising the subwords of a text
43. The world's fastest scrabble program
44. Median split trees: a fast lookup technique for frequently occurring keys
45. A very fast associative method for the recognition and correction of misspelt words, based on redundant hash addressing
46. A bottom-up and top-down approach to using context in text recognition
47. A hybrid algorithm for contextual text recognition
48. Integrating diverse knowledge sources in text recognition
49. An inegrated algorithm for text recognition: comparison with a cascaded algorithm
50. Visual text recognition through contextual processing
51. Using knowledge in the computer interpretation of handwritten FORTRAN coding sheets
52. The Hearsay-II speech understanding system integrating knowledge to resolve uncertainty
53. n-Gram statistics for natural language understanding and text processing
54. Some characteristic curves for dictionary organisation with digital search
55. Checking for spelling and typographical errors in computer-based text
56. A note on undetected typing errors
57. Development of a spelling list