File Download

There are no files associated with this item.

  Links for fulltext
     (May Require Subscription)
Supplementary

Article: A bayesian framework for deformable pattern recognition with application to handwritten character recognition

TitleA bayesian framework for deformable pattern recognition with application to handwritten character recognition
Authors
KeywordsBayesian inference
Deformable models
Expectation-maximization
Handwriting recognition
Nist database
Issue Date1998
PublisherI E E E. The Journal's web site is located at http://www.computer.org/tpami
Citation
Ieee Transactions On Pattern Analysis And Machine Intelligence, 1998, v. 20 n. 12, p. 1382-1388 How to Cite?
AbstractDeformable models have recently been proposed for many pattern recognition applications due to their ability to handle large shape variations. These proposed approaches represent patterns or shapes as deformable models, which deform themselves to match with the input image, and subsequently feed the extracted information into a classifier. The three components-modeling, matching, and classification-are often treated as independent tasks. In this paper, we study how to integrate deformable models into a Bayesian framework as a unified approach for modeling, matching, and classifying shapes. Handwritten character recognition serves as a testbed for evaluating the approach. With the use of our system, recognition is invariant to affine transformation as well as other handwriting variations. In addition, no preprocessing or manual setting of hyperparameters (e.g., regularization parameter and character width) is required. Besides, issues on the incorporation of constraints on model flexibility, detection of subparts, and speed-up are investigated. Using a model set with only 23 prototypes without any discriminative training, we can achieve an accuracy of 94.7 percent with no rejection on a subset (11,791 images by 100 writers) of handwritten digits from the NIST SD-1 dataset. ©1998 IEEE.
Persistent Identifierhttp://hdl.handle.net/10722/65516
ISSN
2023 Impact Factor: 20.8
2023 SCImago Journal Rankings: 6.158
ISI Accession Number ID
References

 

DC FieldValueLanguage
dc.contributor.authorCheung, KWen_HK
dc.contributor.authorYeung, DVen_HK
dc.contributor.authorChin, RTen_HK
dc.date.accessioned2010-08-31T07:15:01Z-
dc.date.available2010-08-31T07:15:01Z-
dc.date.issued1998en_HK
dc.identifier.citationIeee Transactions On Pattern Analysis And Machine Intelligence, 1998, v. 20 n. 12, p. 1382-1388en_HK
dc.identifier.issn0162-8828en_HK
dc.identifier.urihttp://hdl.handle.net/10722/65516-
dc.description.abstractDeformable models have recently been proposed for many pattern recognition applications due to their ability to handle large shape variations. These proposed approaches represent patterns or shapes as deformable models, which deform themselves to match with the input image, and subsequently feed the extracted information into a classifier. The three components-modeling, matching, and classification-are often treated as independent tasks. In this paper, we study how to integrate deformable models into a Bayesian framework as a unified approach for modeling, matching, and classifying shapes. Handwritten character recognition serves as a testbed for evaluating the approach. With the use of our system, recognition is invariant to affine transformation as well as other handwriting variations. In addition, no preprocessing or manual setting of hyperparameters (e.g., regularization parameter and character width) is required. Besides, issues on the incorporation of constraints on model flexibility, detection of subparts, and speed-up are investigated. Using a model set with only 23 prototypes without any discriminative training, we can achieve an accuracy of 94.7 percent with no rejection on a subset (11,791 images by 100 writers) of handwritten digits from the NIST SD-1 dataset. ©1998 IEEE.en_HK
dc.languageengen_HK
dc.publisherI E E E. The Journal's web site is located at http://www.computer.org/tpamien_HK
dc.relation.ispartofIEEE Transactions on Pattern Analysis and Machine Intelligenceen_HK
dc.subjectBayesian inferenceen_HK
dc.subjectDeformable modelsen_HK
dc.subjectExpectation-maximizationen_HK
dc.subjectHandwriting recognitionen_HK
dc.subjectNist databaseen_HK
dc.titleA bayesian framework for deformable pattern recognition with application to handwritten character recognitionen_HK
dc.typeArticleen_HK
dc.identifier.emailChin, RT: rchin@hku.hken_HK
dc.identifier.authorityChin, RT=rp01300en_HK
dc.description.naturelink_to_subscribed_fulltexten_HK
dc.identifier.doi10.1109/34.735813en_HK
dc.identifier.scopuseid_2-s2.0-0032297353en_HK
dc.relation.referenceshttp://www.scopus.com/mlt/select.url?eid=2-s2.0-0032297353&selection=ref&src=s&origin=recordpageen_HK
dc.identifier.volume20en_HK
dc.identifier.issue12en_HK
dc.identifier.spage1382en_HK
dc.identifier.epage1388en_HK
dc.identifier.isiWOS:000077578300012-
dc.publisher.placeUnited Statesen_HK
dc.identifier.scopusauthoridCheung, KW=55413672000en_HK
dc.identifier.scopusauthoridYeung, DV=55436462600en_HK
dc.identifier.scopusauthoridChin, RT=7102445426en_HK
dc.identifier.issnl0162-8828-

Export via OAI-PMH Interface in XML Formats


OR


Export to Other Non-XML Formats