Show simple item record

dc.contributor.authorAdak, Chandranath
dc.contributor.authorChaudhuri, Bidyut B.
dc.contributor.authorBlumenstein, Michael
dc.contributor.editorJuan E. Guerrero
dc.date.accessioned2017-06-08T01:42:03Z
dc.date.available2017-06-08T01:42:03Z
dc.date.issued2016
dc.identifier.doi10.1109/ICFHR.2016.0086
dc.identifier.urihttp://hdl.handle.net/10072/339286
dc.description.abstractThis paper deals with offline handwritten word recognition of a major Indic script: Bengali. Due to the structure of this script, the characters (mostly ortho-syllables) are frequently overlapping and hard to segment, especially when the writing is cursive. Individual character recognition and the combination of outputs can increase the likelihood of errors. Instead, a better approach can be sending the whole word to a suitable recognizer. Here we use the Convolutional Neural Network (CNN) integrated with a recurrent model for this purpose. Long short-term memory blocks are used as hidden units. Also, the CNN-derived features are employed in a recurrent model with a CTC (Connectionist Temporal Classification) layer to get the output. We have tested our method on three datasets: (a) a publicly available dataset, (b) a new dataset generated by our research group and (c) an unconstrained dataset. The dataset (a) contains 17,091 words, while our dataset (b) contains 107,550 number of words in total. In addition to these, the dataset (c) is comprised of 5,223 words. We have compared our results with those of some earlier work in the area and have found improved performance, which is due to the novel integration of CNNs with the recurrent model.
dc.description.peerreviewedYes
dc.languageEnglish
dc.publisherInstitute of Electrical and Electronics Engineers (IEEE)
dc.publisher.placeUnited States
dc.relation.ispartofconferencenameICFHR 2016
dc.relation.ispartofconferencetitleProceedings 2016 15th International Conference on Frontiers in Handwriting Recognition
dc.relation.ispartofdatefrom2016-10-23
dc.relation.ispartofdateto2016-10-26
dc.relation.ispartoflocationShenzhen, China
dc.subject.fieldofresearchTechnology not elsewhere classified
dc.subject.fieldofresearchcode109999
dc.titleOffline Cursive Bengali Word Recognition using CNNs with a Recurrent Model
dc.typeConference output
dc.type.descriptionE1 - Conferences
dc.type.codeE - Conference Publications
gro.facultyGriffith Sciences, School of Information and Communication Technology
gro.hasfulltextNo Full Text
gro.griffith.authorBlumenstein, Michael M.
gro.griffith.authorAdak, Chandranath


Files in this item

FilesSizeFormatView

There are no files associated with this item.

This item appears in the following Collection(s)

  • Conference outputs
    Contains papers delivered by Griffith authors at national and international conferences.

Show simple item record