Recognition of online handwritten Bangla characters using hierarchical system with Denoising Autoencoders

This work describes the recognition of online handwritten Bengali characters using Deep Denoising Autoencoder with Multilayer Perceptron (MLP) trained through backpropagation algorithm [1]. Initial pre-training has been done to the Denoising Autoencoder with MLP trained through backpropagation algor...

Full description

Saved in:
Bibliographic Details
Published in:2015 International Conference on Computation of Power, Energy, Information and Communication (ICCPEIC) pp. 0047 - 0051
Main Authors: Pal, Arghya, Pawar, J. D.
Format: Conference Proceeding
Language:English
Published: IEEE 01.04.2015
Subjects:
Backpropagation algorithms
Bengali Character
Character recognition
Classification
Computational modeling
Deep Network
Denoising Autoencoder
Handwriting recognition
Hidden Markov models
MLP
Numerical models
Online Access:Get full text
Tags: Add Tag
No Tags, Be the first to tag this record!
Abstract This work describes the recognition of online handwritten Bengali characters using Deep Denoising Autoencoder with Multilayer Perceptron (MLP) trained through backpropagation algorithm [1]. Initial pre-training has been done to the Denoising Autoencoder with MLP trained through backpropagation algorithm, to bring the weights of the Deep network to some good solution and then pre-trained Denoising Autoencoders are stacked to form a Deep Denoising Autoencoder (DDA). A final classification layer makes DDA to a Deep Classifier (DC) followed by a final fine-tune that gives the best classifier for the job of classification of Bengali characters. The overall system is hierarchical in nature and the system has been trained in two phase where the first phase has trained a broad classifier and in the second phase class specific recognizer has been trained. At the testing phase in this hierarchical approach, first a broad classifier has been used to recognize broad classes like Vowel, Consonant, Special Symbol and Numeral for a novel test sample. Once the broad class gets recognized then a class specific recognizer has been used to recognize the exact character the test sample belongs. Recognition performance of the hierarchical system is 93.12%.
AbstractList This work describes the recognition of online handwritten Bengali characters using Deep Denoising Autoencoder with Multilayer Perceptron (MLP) trained through backpropagation algorithm [1]. Initial pre-training has been done to the Denoising Autoencoder with MLP trained through backpropagation algorithm, to bring the weights of the Deep network to some good solution and then pre-trained Denoising Autoencoders are stacked to form a Deep Denoising Autoencoder (DDA). A final classification layer makes DDA to a Deep Classifier (DC) followed by a final fine-tune that gives the best classifier for the job of classification of Bengali characters. The overall system is hierarchical in nature and the system has been trained in two phase where the first phase has trained a broad classifier and in the second phase class specific recognizer has been trained. At the testing phase in this hierarchical approach, first a broad classifier has been used to recognize broad classes like Vowel, Consonant, Special Symbol and Numeral for a novel test sample. Once the broad class gets recognized then a class specific recognizer has been used to recognize the exact character the test sample belongs. Recognition performance of the hierarchical system is 93.12%.
Author Pal, Arghya
Pawar, J. D.
Author_xml – sequence: 1
  givenname: Arghya
  surname: Pal
  fullname: Pal, Arghya
  email: arghyapaI5@gmail.com
  organization: Dept. of C.S.T., Goa Univ., Taleigao Plateau, India
– sequence: 2
  givenname: J. D.
  surname: Pawar
  fullname: Pawar, J. D.
  organization: Dept. of C.S.T., Goa Univ., Taleigao Plateau, India
BookMark eNotkLFOwzAURY0EA5R-AQz-gZQ4ie14LKGUSpVACObqxXlOnpTayHFV9e-poNNZzrnDvWPXPnhk7FHkCyFy87Rpmo_VplkUuZALXUhTVfkVmxtdi0rpUsmiUreMPtGG3lOi4HlwPPiRPPIBfHeMlBJ6_gy-H4HbASLYhHHih4l8zwfCCNEOZGHk02lKuOdHSgN_QR_oT1keUkBvQ3eu7tmNg3HC-YUz9v26-mresu37etMstxmJokyZUQhCmE5KUUPrjFHSOC1MC6Bb53JbSyVMrUwtCy3BOGhBn7UuFzUqjeWMPfzvEiLufiLtIZ52lwPKX1WIV8g
ContentType Conference Proceeding
DBID 6IE
6IL
CBEJK
RIE
RIL
DOI 10.1109/ICCPEIC.2015.7259440
DatabaseName IEEE Electronic Library (IEL) Conference Proceedings
IEEE Proceedings Order Plan All Online (POP All Online) 1998-present by volume
IEEE Xplore All Conference Proceedings
IEEE Electronic Library
IEEE Proceedings Order Plans (POP All) 1998-Present
DatabaseTitleList
Database_xml – sequence: 1
  dbid: RIE
  name: IEEE Electronic Library
  url: https://ieeexplore.ieee.org/
  sourceTypes: Publisher
DeliveryMethod fulltext_linktorsrc
EISBN 9781467365246
1467365246
9781467365253
1467365254
EndPage 0051
ExternalDocumentID 7259440
Genre orig-research
GroupedDBID 6IE
6IL
CBEJK
RIE
RIL
ID FETCH-LOGICAL-i123t-96ea119d5518abf99659f719baa7bff0c8561986985275a9faba7f99d018e67e3
IEDL.DBID RIE
IngestDate Thu Jun 29 18:36:36 EDT 2023
IsPeerReviewed false
IsScholarly false
Language English
LinkModel DirectLink
MergedId FETCHMERGED-LOGICAL-i123t-96ea119d5518abf99659f719baa7bff0c8561986985275a9faba7f99d018e67e3
PageCount 5
ParticipantIDs ieee_primary_7259440
PublicationCentury 2000
PublicationDate 20150401
PublicationDateYYYYMMDD 2015-04-01
PublicationDate_xml – month: 04
  year: 2015
  text: 20150401
  day: 01
PublicationDecade 2010
PublicationTitle 2015 International Conference on Computation of Power, Energy, Information and Communication (ICCPEIC)
PublicationTitleAbbrev ICCPEIC
PublicationYear 2015
Publisher IEEE
Publisher_xml – name: IEEE
Score 1.5877964
Snippet This work describes the recognition of online handwritten Bengali characters using Deep Denoising Autoencoder with Multilayer Perceptron (MLP) trained through...
SourceID ieee
SourceType Publisher
StartPage 0047
SubjectTerms Backpropagation algorithms
Bengali Character
Character recognition
Classification
Computational modeling
Deep Network
Denoising Autoencoder
Handwriting recognition
Hidden Markov models
MLP
Numerical models
Title Recognition of online handwritten Bangla characters using hierarchical system with Denoising Autoencoders
URI https://ieeexplore.ieee.org/document/7259440
hasFullText 1
inHoldings 1
isFullTextHit
isPrint
link http://cvtisr.summon.serialssolutions.com/2.0.0/link/0/eLvHCXMwlV1LS8NAEF5q8eBJpRXf7MGjaTftZh9HjS32Uooo9Fb2Kbkk0qb6993ZpBXBi7ewDFmyQ5jHfvN9CN3pEBSN1iYhVowTmppR-KUoSSw1xBpqqHU2ik3w-Vwsl3LRQff7WRjnXASfuQE8xrt8W5kttMqGPOTqlIYC_YBz1sxqtdNwKZHDWZ4vJrMc4FrZoDX9pZkSQ8b0-H-bnaD-z-wdXuyjyinquLKHipcdzqcqceVxw2-Boev9Far7kPfiRwVyHNjsCJg3GCDt7xi0ruNtQXAGbnibMTRf8ZMrqyKaPGzrCvgsAdPcR2_TyWv-nLQiCUkRgk6dSOZUmkoLzGpKewkEgZ6nUivFtffEiJAhScGkyEY8U9IrrXgwsyQVjnE3PkPdsirdOcIjoZRQlNlQQlAvlQ7fTzMeXsUsGxN5gXpwTKuPhgdj1Z7Q5d_LV-gIPNGgXK5Rt15v3Q06NJ91sVnfRud9Axjnn-U
linkProvider IEEE
linkToHtml http://cvtisr.summon.serialssolutions.com/2.0.0/link/0/eLvHCXMwlV3NS8MwFA9jCnpS2cRvc_Bot3ZLm-SodWPDOYZM2G3kU3ppZev03zcv7SaCF28lPBqaR3kf-b3fD6E76YKiklIFoWb9gESq534pEgaaqFAroog22otN0OmULRZ81kD3u1kYY4wHn5kOPPq7fF2oDbTKutTl6oS4An0PlLPqaa16Hi4KeXecprPBOAXAVtypjX-ppvigMTz633bHqP0zfYdnu7hyghomb6HsdYv0KXJcWFwxXGDoe3-5-t5lvvhRgCAHVlsK5jUGUPs7BrVrf1_g3IEr5mYM7Vf8ZPIi8yYPm7IARktANbfR23AwT0dBLZMQZC7slAFPjIgiroFbTUjLgSLQ0ohLIai0NlTM5UicJZzFPRoLboUU1JnpMGImoaZ_ipp5kZszhHtMCCZIol0RQSwX0n0_ial7VaKTfsjPUQuOaflRMWEs6xO6-Hv5Fh2M5i-T5WQ8fb5Eh-CVCvNyhZrlamOu0b76LLP16sY78huYjaMu
openUrl ctx_ver=Z39.88-2004&ctx_enc=info%3Aofi%2Fenc%3AUTF-8&rfr_id=info%3Asid%2Fsummon.serialssolutions.com&rft_val_fmt=info%3Aofi%2Ffmt%3Akev%3Amtx%3Abook&rft.genre=proceeding&rft.title=2015+International+Conference+on+Computation+of+Power%2C+Energy%2C+Information+and+Communication+%28ICCPEIC%29&rft.atitle=Recognition+of+online+handwritten+Bangla+characters+using+hierarchical+system+with+Denoising+Autoencoders&rft.au=Pal%2C+Arghya&rft.au=Pawar%2C+J.+D.&rft.date=2015-04-01&rft.pub=IEEE&rft.spage=0047&rft.epage=0051&rft_id=info:doi/10.1109%2FICCPEIC.2015.7259440&rft.externalDocID=7259440