DocumentCode
3173724
Title
A connected character recogniser using level building of HMMs
Author
Elms, A.J.
Author_Institution
Dept. of Electron. & Electr. Eng., Surrey Univ., Guildford, UK
Volume
2
fYear
1994
fDate
9-13 Oct 1994
Firstpage
439
Abstract
The recognition of a printed word is traditionally limited by its segmentation into individual characters due to the noise introduced by facsimile transmission, photocopying, handling or ageing. In this paper, a character recogniser is described which does not require a prior segmentation of the word, and is thus suited to the recognition of noisy text images. A novel method is described whereby hidden Markov models are used to recognise a horizontal “profile” of a word generated from an analysis of each vertical line of pixels in its image
Keywords
optical character recognition; HMM; ageing; connected character recogniser; facsimile transmission; handling; hidden Markov models; level building; noisy text images; photocopying; printed word; segmentation; Aging; Character generation; Character recognition; Facsimile; Hidden Markov models; Image recognition; Image segmentation; Noise robustness; Pixel; Text recognition;
fLanguage
English
Publisher
ieee
Conference_Titel
Pattern Recognition, 1994. Vol. 2 - Conference B: Computer Vision & Image Processing., Proceedings of the 12th IAPR International. Conference on
Conference_Location
Jerusalem
Print_ISBN
0-8186-6270-0
Type
conf
DOI
10.1109/ICPR.1994.576976
Filename
576976
Link To Document