Handwriting Recognition : Soft Computing and Probabilistic Approaches /

Handwriting Recognition : Soft Computing and Probabilistic Approaches /

Saved in:
Bibliographic Details
Author / Creator:Liu, Zhi-Qiang.
Imprint:Berlin, Heidelberg : Springer Berlin Heidelberg, 2003.
Description:1 online resource (xv, 230 pages).
Language:English
Series:Studies in Fuzziness and Soft Computing, 1434-9922 ; 133
Studies in fuzziness and soft computing ; 133.
Subject:
Computer science.
Artificial intelligence.
Text processing (Computer science)
Optical pattern recognition.
Mathematics.
Physics.
Engineering.
Artificial intelligence.
Computer science.
Engineering.
Mathematics.
Optical pattern recognition.
Physics.
Text processing (Computer science)
Format: E-Resource Book
URL for this record:http://pi.lib.uchicago.edu/1001/cat/bib/11079619
Hidden Bibliographic Details
Other authors / contributors:Cai, Jinhai.
Buse, Richard.
ISBN:9783540448501
3540448500
9783642072802
3642072801
3540448500
Summary:This book takes a fresh look at the problem of unconstrained handwriting recognition and introduces the reader to new techniques for the recognition of written words and characters using statistical and soft computing approaches. The types of uncertainties and variations present in handwriting data are discussed in detail. The book presents several algorithms that use modified hidden Markov models and Markov random field models to simulate the handwriting data statistically and structurally in a single framework. The book explores methods that use fuzzy logic and fuzzy sets for handwriting recognition. The effectiveness of these techniques is demonstrated through extensive experimental results and real handwritten characters and words.
Other form:Print version: 9783642072802
Table of Contents:
  • 1 Introduction
  • 1.1 Feature Extraction Methods
  • 1.2 Pattern Recognition Methods
  • 2 Pre-processing and Feature Extraction
  • 2.1 Pre-processing of Handwritten Images
  • 2.2 Feature Extraction from Binarized Images
  • 2.3 Feature Extraction Using Gabor Filters
  • 2.4 Concluding Remarks
  • 3 Hidden Markov Model-Based Method for Recognizing Handwritten Digits
  • 3.1 Theory of Hidden Markov Models
  • 3.2 Recognizing Handwritten Numerals Using Statistical and Structural Information
  • 3.3 Experimental Results
  • 3.4 Conclusion
  • 4 Markov Models with Spectral Features for Handwritten Numeral Recognition
  • 4.1 Related Work Using Contour Information
  • 4.2 Fourier Descriptors
  • 4.3 Hidden Markov Model in Spectral Space
  • 4.4 Experimental Results
  • 4.5 Discussion
  • 5 Markov Random Field Model for Recognizing Handwritten Digits
  • 5.1 Fundamentals of Markov Random Fields
  • 5.2 Markov Random Field for Pattern Recognition
  • 5.3 Recognition of Handwritten Numerals Using MRF Models
  • 5.4 Conclusion
  • 6 Markov Random Field Models for Recognizing Handwritten Words
  • 6.1 Markov Random Field for Handwritten Word Recognition
  • 6.2 Neighborhood Systems and Cliques
  • 6.3 Clique Functions
  • 6.4 Maximizing the Compatibility with Relaxation Labeling
  • 6.5 Design of Weights
  • 6.6 Experimental Results
  • 6.7 Conclusion
  • 7 A Structural and Relational Approach to Handwritten Word Recognition
  • 7.1 Introduction
  • 7.2 Gabor Parameter Estimation
  • 7.3 Feature Extraction
  • 7.4 Conditional Rule Generation System
  • 7.5 Experimental Results
  • 7.6 Conclusion
  • 8 Handwritten Word Recognition Using Fuzzy Logic
  • 8.1 Introduction
  • 8.2 Extraction of Oriented Parts
  • 8.3 System Training
  • 8.4 Word Recognition
  • 8.5 Experimental Results
  • 8.6 Conclusion
  • 9 Conclusion
  • 9.1 Summary and Discussions
  • 9.2 Future Directions
  • 9.3 References.

Similar Items