Combining multiple OCRs for optimizing word recognition

Sinha, P.; Mao, Jianchang

doi:10.1109/icpr.1998.711174

Cited by 8 publications

(2 citation statements)

References 4 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Recently, Sinha and Mao have proposed a method similar to ours [5]. However, their method makes use of statistical analysis while ours uses a simpler, more practical approach.…”

Section: Introductionmentioning

confidence: 99%

Cursive handwritten word recognition by integrating multiple classifiers

et al. 2000

View full text Add to dashboard Cite

This paper proposes a method for cursive handwritten word recognition. In the traditional research, cursive handwritten word recognition used a single method for character recognition. Our research proposes a method that integrates multiple classifiers in order to improve the word recognition rate by combining their results. Our experiment demonstrates that two classifiers outperform the word recognition rate of any single character classifier. © 2000 Scripta Technica, Syst Comp Jpn, 31(12): 2332, 2000

show abstract

“…Recently, Sinha and Mao have proposed a method similar to ours [5]. However, their method makes use of statistical analysis while ours uses a simpler, more practical approach.…”

Section: Introductionmentioning

confidence: 99%

Cursive handwritten word recognition by integrating multiple classifiers

et al. 2000

View full text Add to dashboard Cite

show abstract

“…The letter 'o' is merged into the same class as zero '0'). The inputs to the neural network are 108 features extracted from a segment [2].…”

Section: Dynamic Zip Locationmentioning

confidence: 99%

A system for cursive handwritten address recognition

Mao

Sinha²,

Mohiuddin³

Proceedings. Fourteenth International Conference on Pattern Recognition (Cat. No.98EX170)

Self Cite

View full text Add to dashboard Cite

This paper presents a cursive handwritten address recognition system, which consists of four main modules: (i) over-segmentor, (ii) dynamic zip locator, (iii) zip candidates generator, and (iv) city-state-zip verifier. The dynamic zip locator and city-state-zip verifier are based on a flexible matcher for matching a sequence of graphemes with a list of generalized strings. The dynamic zip locator is able to locate zip without knowing exactly where the zip starts. The zip candidates generator uses a hidden Markov model (HMM) with position-dependent state transition probabilities. A scheme for utilizing prefixes is designed to reduce computation and memory requirement. Finally, the system employs a mechanism for rejection based on rank features extracted from the matching. The overall system achieves an acceptance rate of 83.5% with 3.6% error for 5-digit encoding on 805 USPS cursive address images.

show abstract