An HMM-Based Approach for Off-Line Unconstrained Handwritten Word Modeling and Recognition

Authors:
A. El-Yacoubi;R. Sabourin;C. Y. Suen;M. Gilloux
Affiliations:
Concordia Univ., Montré/al, Canada/ and Pontificia Univ. Catolica do Parana, Curitaba-PR-Brazil;Concordia Univ., Montré/al, Canada/ and LIVIA, Montré/al, Canada;Concordia Univ., Montré/al, Canada;Dé/portement Reconnaissance, Modé/lisation et Optimasation, Nantes CedexService de Recherche Technique de La Poste, Nantes Cedex 02, France
Venue:
IEEE Transactions on Pattern Analysis and Machine Intelligence
Year:
1999

Citing 6
Cited 36

Off-Line Cursive Script Word Recognition

IEEE Transactions on Pattern Analysis and Machine Intelligence
Handwritten Word Recognition Using Segmentation-Free Hidden Markov Modeling and Segmentation-Based Dynamic Programming Techniques

IEEE Transactions on Pattern Analysis and Machine Intelligence
Off-Line Handwritten Word Recognition Using a Hidden Markov Model Type Stochastic Network

IEEE Transactions on Pattern Analysis and Machine Intelligence
Das ISADORA-System - ein akustisch-phonetisches Netzwerk zur automatischen Spracherkennung

Mustererkennung 1991, 13. DAGM-Symposium
Modeling and recognition of cursive words with hidden Markov models

Pattern Recognition
Variable duration hidden Markov model and morphological segmentation for handwritten word recognition

IEEE Transactions on Image Processing

A Statistical Approach for Phrase Location and Recognition within a Text Line: An Application to Street Name Recognition

IEEE Transactions on Pattern Analysis and Machine Intelligence
A 2-D HMM method for offline handwritten character recognition

Hidden Markov models
On the Dependence of Handwritten Word Recognizers on Lexicons

IEEE Transactions on Pattern Analysis and Machine Intelligence
A Time-Length Constrained Level Building Algorithm for Large Vocabulary Handwritten Word Recognition

ICAPR '01 Proceedings of the Second International Conference on Advances in Pattern Recognition
A Stochastic Model Combining Discrete Symbols and Continuous Attributes and Its Application to Handwriting Recognition

DAS '02 Proceedings of the 5th International Workshop on Document Analysis Systems V
Robust Line Detection in Historical Church Registers

Proceedings of the 23rd DAGM-Symposium on Pattern Recognition
Pairwise Markov Chains

IEEE Transactions on Pattern Analysis and Machine Intelligence
Recognition of Cursive Roman Handwriting - Past, Present and Future

ICDAR '03 Proceedings of the Seventh International Conference on Document Analysis and Recognition - Volume 1
Integration of Contextual Information in Handwriting Recognition Systems

ICDAR '03 Proceedings of the Seventh International Conference on Document Analysis and Recognition - Volume 2
On the structure of hidden Markov models

Pattern Recognition Letters
Recognition and Verification of Unconstrained Handwritten Words

IEEE Transactions on Pattern Analysis and Machine Intelligence
Automatic extraction of numerical sequences in handwritten incoming mail documents

Pattern Recognition Letters
A New Feature Ranking Method in a HMM-Based Handwriting Recognition System

ICDAR '05 Proceedings of the Eighth International Conference on Document Analysis and Recognition
Hidden Markov Models Combining Discrete Symbols and Continuous Attributes in Handwriting Recognition

IEEE Transactions on Pattern Analysis and Machine Intelligence
An implicit segmentation-based method for recognition of handwritten strings of characters

Proceedings of the 2006 ACM symposium on Applied computing
Lexicon and hidden Markov model-based optimisation of the recognised Sinhala script

Pattern Recognition Letters
Using codebooks of fragmented connected-component contours in forensic and historic writer identification

Pattern Recognition Letters
Offline recognition of omnifont Arabic text using the HMM ToolKit (HTK)

Pattern Recognition Letters
Semi-continuous HMMs with explicit state duration for unconstrained Arabic word modeling and recognition

Pattern Recognition Letters
Off-line recognition of realistic Chinese handwriting using segmentation-free strategy

Pattern Recognition
A prediction algorithm for time series based on adaptive model selection

Expert Systems with Applications: An International Journal
Handwritten word-spotting using hidden Markov models and universal vocabularies

Pattern Recognition
Combination of generative models and SVM based classifier for speech emotion recognition

IJCNN'09 Proceedings of the 2009 international joint conference on Neural Networks
HMM-based system for recognizing words in historical Arabic manuscript

International Journal of Robotics and Automation
Unsupervised writer adaptation of whole-word HMMs with application to word-spotting

Pattern Recognition Letters
Gabor-based recognizer for Chinese handwriting from segmentation-free strategy

CAIP'07 Proceedings of the 12th international conference on Computer analysis of images and patterns
Determining the similarity of signatures on the basis of characteristic points analysis

International Journal of Biometrics
Off-line signature verification using structural features

Proceedings of the 7th International Conference on Frontiers of Information Technology
Offline handwritten Amharic word recognition

Pattern Recognition Letters
A survey of techniques for incremental learning of HMM parameters

Information Sciences: an International Journal
Off-line cursive script recognition: current advances, comparisons and remaining problems

Artificial Intelligence Review
A synthesised word approach to word retrieval in handwritten documents

Pattern Recognition
A symbol spotting approach in graphical documents by hashing serialized graphs

Pattern Recognition
Evaluation Approach of Arabic Character Recognition

International Journal of Computer Vision and Image Processing
Offline text-independent writer identification using codebook and efficient code extraction methods

Image and Vision Computing
Multilingual OCR research and applications: an overview

Proceedings of the 4th International Workshop on Multilingual OCR

Quantified Score

Hi-index	0.15

Visualization

Abstract

This paper describes a hidden Markov model-based approach designed to recognize off-line unconstrained handwritten words for large vocabularies. After preprocessing, a word image is segmented into letters or pseudoletters and represented by two feature sequences of equal length, each consisting of an alternating sequence of shape-symbols and segmentation-symbols, which are both explicitly modeled. The word model is made up of the concatenation of appropriate letter models consisting of elementary HMMs and an HMM-based interpolation technique is used to optimally combine the two feature sets. Two rejection mechanisms are considered depending on whether or not the word image is guaranteed to belong to the lexicon. Experiments carried out on real-life data show that the proposed approach can be successfully used for handwritten word recognition.