An optimized CNN system to recognize handwritten characters in ancient documents in Grantha script

An optical character recognition (OCR) system plays an important role in the digitization of ancient handwritten text document. Various adversaries of ancient documents such as ink stains, faded portion of text, humidity spots, and similar-shaped characters make the task of character recognition cha...

Celý popis

Uložené v:

Podrobná bibliografia
Vydané v:	International journal of information technology (Singapore. Online) Ročník 15; číslo 4; s. 1975 - 1983
Hlavní autori:	Jindal, Amar, Ghosh, Rajib
Médium:	Journal Article
Jazyk:	English
Vydavateľské údaje:	Singapore Springer Nature Singapore 01.04.2023 Springer Nature B.V
Predmet:	Artificial Intelligence Artificial neural networks Computer Imaging Computer Science Convolution Documents Handwriting recognition Image Processing and Computer Vision Machine Learning Neural networks Optical character recognition Optimization techniques Original Research Pattern Recognition and Graphics Software Engineering Vision India Optimized CNN Character recognition Grantha script Ancient handwritten documents
ISSN:	2511-2104, 2511-2112
On-line prístup:	Získať plný text
Tagy:	Pridať tag Žiadne tagy, Buďte prvý, kto otaguje tento záznam!

Abstract	An optical character recognition (OCR) system plays an important role in the digitization of ancient handwritten text document. Various adversaries of ancient documents such as ink stains, faded portion of text, humidity spots, and similar-shaped characters make the task of character recognition challenging and tedious. This research study proposes an optimized convolution neural network (CNN) based OCR system to recognize each and every character present in the ancient document handwritten in Grantha script. A set of convolutional layers present in the proposed system extracts the deep hierarchical feature vectors from the input character image. Two fully connected neural network (FCNN) layers have classified these feature vectors into its correct class. The values of the hyper-parameters of CNN architecture such as the number of filters in each convolution layer, size of the filter in each convolution layer, number of FCNN layers, and neurons in each FCNN layer have been optimized using the Bayesian optimization technique. The major contribution of this work is the proposal of an optimized CNN architecture to perform OCR in ancient documents in Grantha script. A character recognition accuracy of 99.30% has been obtained from the proposed OCR system on the ancient handwritten documents in Grantha script. The experimental results demonstrate that the proposed OCR method outperforms the existing state-of-the-art methods in this regard.
AbstractList	An optical character recognition (OCR) system plays an important role in the digitization of ancient handwritten text document. Various adversaries of ancient documents such as ink stains, faded portion of text, humidity spots, and similar-shaped characters make the task of character recognition challenging and tedious. This research study proposes an optimized convolution neural network (CNN) based OCR system to recognize each and every character present in the ancient document handwritten in Grantha script. A set of convolutional layers present in the proposed system extracts the deep hierarchical feature vectors from the input character image. Two fully connected neural network (FCNN) layers have classified these feature vectors into its correct class. The values of the hyper-parameters of CNN architecture such as the number of filters in each convolution layer, size of the filter in each convolution layer, number of FCNN layers, and neurons in each FCNN layer have been optimized using the Bayesian optimization technique. The major contribution of this work is the proposal of an optimized CNN architecture to perform OCR in ancient documents in Grantha script. A character recognition accuracy of 99.30% has been obtained from the proposed OCR system on the ancient handwritten documents in Grantha script. The experimental results demonstrate that the proposed OCR method outperforms the existing state-of-the-art methods in this regard. An optical character recognition (OCR) system plays an important role in the digitization of ancient handwritten text document. Various adversaries of ancient documents such as ink stains, faded portion of text, humidity spots, and similar-shaped characters make the task of character recognition challenging and tedious. This research study proposes an optimized convolution neural network (CNN) based OCR system to recognize each and every character present in the ancient document handwritten in Grantha script. A set of convolutional layers present in the proposed system extracts the deep hierarchical feature vectors from the input character image. Two fully connected neural network (FCNN) layers have classified these feature vectors into its correct class. The values of the hyper-parameters of CNN architecture such as the number of filters in each convolution layer, size of the filter in each convolution layer, number of FCNN layers, and neurons in each FCNN layer have been optimized using the Bayesian optimization technique. The major contribution of this work is the proposal of an optimized CNN architecture to perform OCR in ancient documents in Grantha script. A character recognition accuracy of 99.30% has been obtained from the proposed OCR system on the ancient handwritten documents in Grantha script. The experimental results demonstrate that the proposed OCR method outperforms the existing state-of-the-art methods in this regard.
Author	Ghosh, Rajib Jindal, Amar
Author_xml	– sequence: 1 givenname: Amar surname: Jindal fullname: Jindal, Amar organization: Department of Computer Science and Engineering, National Institute of Technology Patna – sequence: 2 givenname: Rajib orcidid: 0000-0002-8553-8656 surname: Ghosh fullname: Ghosh, Rajib email: rajib.ghosh@nitp.ac.in organization: Department of Computer Science and Engineering, National Institute of Technology Patna
BookMark	eNp9kE9LAzEQxYMo-K9fwFPA82om2exuj1K0CqVe9Byyk6SN2KQmKaKf3tUVBQ-e5jHzfjPDOyb7IQZLyBmwC2Csvcw1dC2rGBcVA163FeyRIy4BKg7A9380qw_JJGffMwG8EbKFI9JfBRq3xW_8uzV0tlzS_JaL3dASabIYV2EY0LUO5jX5UmyguNZJY7EpUx-oDuhtKNRE3G0G8dWcJx3KWtOMyW_LKTlw-jnbyXc9IY831w-z22pxP7-bXS0q5KKGSkwbI5DVEgyXbQ3oQGOvUQp0deOkaequbxrXM260mTrnOjSuF4xJ12CP4oScj3u3Kb7sbC7qKe5SGE4qwaXkIFrWDC4-ujDFnJN1apv8Rqc3BUx9xqnGONUQp_qKU8EAdX8g9EUXH0NJ2j__j4oRzcOdsLLp96t_qA8pXI0S
CitedBy_id	crossref_primary_10_1007_s11042_023_17697_5 crossref_primary_10_1186_s40494_024_01438_4 crossref_primary_10_1007_s41870_023_01529_8 crossref_primary_10_1007_s00521_024_10717_x crossref_primary_10_1080_1448837X_2025_2553938 crossref_primary_10_1007_s41870_024_02377_w
Cites_doi	10.1007/s12046-019-1126-9 10.1109/ACCESS.2020.2975023 10.1007/s11063-018-9913-6 10.1109/ACCESS.2019.2960161 10.1007/s11042-019-7620-6 10.1016/j.patcog.2019.03.030 10.1007/s11042-021-10775-6 10.1007/s00500-020-05018-z 10.1007/s00500-019-04596-x 10.1016/j.patrec.2020.05.026 10.1007/s00521-015-1972-2 10.1007/s42452-019-1340-4 10.1109/CVPR.2016.308 10.17632/y2s635w8wd.1 10.1155/2021/2491116 10.1007/s11042-022-13709-y 10.1109/CVPR.2016.90 10.1109/ICCMC.2017.8282574 10.1109/PDGC.2018.8745903 10.1109/DAS.2018.50 10.1109/DAS.2016.60 10.1109/CVPR.2017.195 10.1007/978-981-15-1084-7_19
ContentType	Journal Article
Copyright	The Author(s), under exclusive licence to Bharati Vidyapeeth's Institute of Computer Applications and Management 2023. Springer Nature or its licensor (e.g. a society or other partner) holds exclusive rights to this article under a publishing agreement with the author(s) or other rightsholder(s); author self-archiving of the accepted manuscript version of this article is solely governed by the terms of such publishing agreement and applicable law. The Author(s), under exclusive licence to Bharati Vidyapeeth's Institute of Computer Applications and Management 2023.
Copyright_xml	– notice: The Author(s), under exclusive licence to Bharati Vidyapeeth's Institute of Computer Applications and Management 2023. Springer Nature or its licensor (e.g. a society or other partner) holds exclusive rights to this article under a publishing agreement with the author(s) or other rightsholder(s); author self-archiving of the accepted manuscript version of this article is solely governed by the terms of such publishing agreement and applicable law. – notice: The Author(s), under exclusive licence to Bharati Vidyapeeth's Institute of Computer Applications and Management 2023.
DBID	AAYXX CITATION 3V. 7SC 7XB 8AL 8FD 8FE 8FG 8FK ABUWG AFKRA ARAPS AZQEC BENPR BGLVJ CCPQU DWQXO GNUQQ HCIFZ JQ2 K7- L7M L~C L~D M0N P5Z P62 PHGZM PHGZT PKEHL PQEST PQGLB PQQKQ PQUKI PRINS Q9U
DOI	10.1007/s41870-023-01247-1
DatabaseName	CrossRef ProQuest Central (Corporate) Computer and Information Systems Abstracts ProQuest Central (purchase pre-March 2016) Computing Database (Alumni Edition) Technology Research Database ProQuest SciTech Collection ProQuest Technology Collection ProQuest Central (Alumni) (purchase pre-March 2016) ProQuest Central (Alumni) ProQuest Central UK/Ireland Advanced Technologies & Computer Science Collection ProQuest Central Essentials ProQuest Central Technology collection ProQuest One Community College ProQuest Central ProQuest Central Student SciTech Premium Collection ProQuest Computer Science Collection Computer Science Database Advanced Technologies Database with Aerospace Computer and Information Systems Abstracts Academic Computer and Information Systems Abstracts Professional Computing Database ProQuest advanced technologies & aerospace journals ProQuest Advanced Technologies & Aerospace Collection ProQuest Central Premium ProQuest One Academic ProQuest One Academic Middle East (New) ProQuest One Academic Eastern Edition (DO NOT USE) One Applied & Life Sciences ProQuest One Academic (retired) ProQuest One Academic UKI Edition ProQuest Central China ProQuest Central Basic
DatabaseTitle	CrossRef Computer Science Database ProQuest Central Student Technology Collection Technology Research Database Computer and Information Systems Abstracts – Academic ProQuest One Academic Middle East (New) ProQuest Advanced Technologies & Aerospace Collection ProQuest Central Essentials ProQuest Computer Science Collection Computer and Information Systems Abstracts ProQuest Central (Alumni Edition) SciTech Premium Collection ProQuest One Community College ProQuest Central China ProQuest Central ProQuest One Applied & Life Sciences ProQuest Central Korea ProQuest Central (New) Advanced Technologies Database with Aerospace Advanced Technologies & Aerospace Collection ProQuest Computing ProQuest Central Basic ProQuest Computing (Alumni Edition) ProQuest One Academic Eastern Edition ProQuest Technology Collection ProQuest SciTech Collection Computer and Information Systems Abstracts Professional Advanced Technologies & Aerospace Database ProQuest One Academic UKI Edition ProQuest One Academic ProQuest Central (Alumni) ProQuest One Academic (New)
DatabaseTitleList	Computer Science Database
Database_xml	– sequence: 1 dbid: BENPR name: ProQuest Central url: https://www.proquest.com/central sourceTypes: Aggregation Database
DeliveryMethod	fulltext_linktorsrc
Discipline	Engineering Computer Science
EISSN	2511-2112
EndPage	1983
ExternalDocumentID	10_1007_s41870_023_01247_1
GeographicLocations	India
GeographicLocations_xml	– name: India
GroupedDBID	-EM 0R~ 406 AACDK AAHNG AAIAL AAJBT AANZL AASML AATNV AATVU AAUYE ABAKF ABDZT ABECU ABFTV ABJNI ABJOX ABKCH ABMQK ABQBU ABTEG ABTKH ABTMW ABXPI ACAOD ACDTI ACGFS ACHSB ACMLO ACOKC ACPIV ACZOJ ADHHG ADKNI ADKPE ADTPH ADURQ ADYFF ADZKW AEBTG AEFQL AEJRE AEMSY AEOHA AESKC AEVLU AEXYK AFBBN AFQWF AGDGC AGMZJ AGQEE AGRTI AHSBF AIAKS AIGIU AILAN AITGF AJRNO AJZVZ ALFXC ALMA_UNASSIGNED_HOLDINGS AMKLP AMXSW AMYLF AMYQR AXYYD BGNMA CSCUP DNIVK DPUIP EBLON EBS EIOEI EJD FERAY FIGPU FINBP FNLPD FSGXE GGCAI GJIRD IKXTQ IWAJR J-C JZLTJ KOV LLZTM M4Y NPVJJ NQJWS NU0 O9J PT4 RLLFE ROL RSV SISQX SJYHP SNE SNPRN SNX SOHCF SOJ SPISZ SRMVM SSLCW STPWE TSG UOJIU UTJUX UZXMN VFIZW Z7Z Z81 Z83 Z88 ZMTXR AAYXX ABBRH ABDBE ABFSG ABRTQ ABUWG ACSTC AEZWR AFDZB AFHIU AFKRA AFOHR AHPBZ AHWEU AIXLP ARAPS ATHPR AYFIA AZQEC BENPR BGLVJ CCPQU CITATION DWQXO GNUQQ HCIFZ K7- PHGZM PHGZT PQGLB 3V. 7SC 7XB 8AL 8FD 8FE 8FG 8FK JQ2 L7M L~C L~D M0N P62 PKEHL PQEST PQQKQ PQUKI PRINS Q9U
ID	FETCH-LOGICAL-c2341-396d3c0451d25741cf1acbac53cf46f5d648b66fb02dad9fff8cdfb3005f6cbc3
IEDL.DBID	RSV
ISSN	2511-2104
IngestDate	Sun Nov 30 04:09:22 EST 2025 Tue Nov 18 22:28:09 EST 2025 Sat Nov 29 03:11:47 EST 2025 Fri Feb 21 02:43:23 EST 2025
IsPeerReviewed	false
IsScholarly	true
Issue	4
Keywords	Optimized CNN Character recognition Grantha script Ancient handwritten documents
Language	English
LinkModel	DirectLink
MergedId	FETCHMERGED-LOGICAL-c2341-396d3c0451d25741cf1acbac53cf46f5d648b66fb02dad9fff8cdfb3005f6cbc3
Notes	ObjectType-Article-1 SourceType-Scholarly Journals-1 ObjectType-Feature-2 content type line 14
ORCID	0000-0002-8553-8656
PQID	3255213706
PQPubID	2034493
PageCount	9
ParticipantIDs	proquest_journals_3255213706 crossref_primary_10_1007_s41870_023_01247_1 crossref_citationtrail_10_1007_s41870_023_01247_1 springer_journals_10_1007_s41870_023_01247_1
PublicationCentury	2000
PublicationDate	20230400 2023-04-00 20230401
PublicationDateYYYYMMDD	2023-04-01
PublicationDate_xml	– month: 4 year: 2023 text: 20230400
PublicationDecade	2020
PublicationPlace	Singapore
PublicationPlace_xml	– name: Singapore – name: Heidelberg
PublicationSubtitle	An Official Journal of Bharati Vidyapeeth's Institute of Computer Applications and Management
PublicationTitle	International journal of information technology (Singapore. Online)
PublicationTitleAbbrev	Int. j. inf. tecnol
PublicationYear	2023
Publisher	Springer Nature Singapore Springer Nature B.V
Publisher_xml	– name: Springer Nature Singapore – name: Springer Nature B.V
References	Garg, Jindal, Singh (CR20) 2021; 13 Narang, Jindal, Kumar (CR18) 2019; 44 CR16 Narang, Jindal, Ahuja, Kumar (CR17) 2020; 24 CR15 CR14 Narang, Jindal, Kumar (CR3) 2019; 78 CR12 Ghosh, Vamshi, Kumar (CR1) 2019; 92 CR30 Kumar, Jindal, Jindal, Lehal (CR7) 2019; 50 Ma, Long, Duan, Zhang, Li, Zhao (CR22) 2020; 8 Garg, Jindal, Singh (CR21) 2022; 14 Ly, Nguyen, Nakagawa (CR10) 2020; 136 Narang, Kumar, Jindal (CR5) 2021; 80 Sharma, Dhaka (CR4) 2016; 27 Suganya, Murugavalli (CR8) 2020; 24 Jyothi, Rahiman (CR13) 2020; 15 CR2 CR6 CR29 CR28 CR9 Hussain (CR26) 2022; 14 CR27 Weldegebriel, Liu, Haq, Bugingo, Zhang (CR23) 2020; 8 Lakshmi, Sastry, Rajinikanth (CR11) 2017; 20 CR24 Joseph (CR19) 2020; 12 Demilew, Sekeroglu (CR25) 2019; 1 1247_CR14 1247_CR15 1247_CR16 FA Demilew (1247_CR25) 2019; 1 T Suganya (1247_CR8) 2020; 24 TV Lakshmi (1247_CR11) 2017; 20 1247_CR12 1247_CR2 SR Narang (1247_CR3) 2019; 78 1247_CR30 1247_CR6 R Ghosh (1247_CR1) 2019; 92 M Kumar (1247_CR7) 2019; 50 1247_CR9 FJJ Joseph (1247_CR19) 2020; 12 S Narang (1247_CR18) 2019; 44 R Jyothi (1247_CR13) 2020; 15 HT Weldegebriel (1247_CR23) 2020; 8 J Hussain (1247_CR26) 2022; 14 1247_CR24 NT Ly (1247_CR10) 2020; 136 L Ma (1247_CR22) 2020; 8 1247_CR27 SR Narang (1247_CR5) 2021; 80 SR Narang (1247_CR17) 2020; 24 MK Sharma (1247_CR4) 2016; 27 A Garg (1247_CR21) 2022; 14 A Garg (1247_CR20) 2021; 13 1247_CR28 1247_CR29
References_xml	– volume: 44 start-page: 1 issue: 6 year: 2019 end-page: 8 ident: CR18 article-title: Devanagari ancient documents recognition using statistical feature extraction techniques publication-title: Sādhanā doi: 10.1007/s12046-019-1126-9 – ident: CR14 – ident: CR2 – ident: CR16 – ident: CR12 – ident: CR30 – volume: 20 start-page: 143 issue: 1 year: 2017 end-page: 150 ident: CR11 article-title: A novel 3D approach to recognize Telugu palm leaf text publication-title: Eng Sci Technol Int J – volume: 8 start-page: 52641 year: 2020 end-page: 52651 ident: CR22 article-title: Segmentation and recognition for historical Tibetan document images publication-title: IEEE Access doi: 10.1109/ACCESS.2020.2975023 – ident: CR6 – ident: CR29 – volume: 50 start-page: 43 issue: 1 year: 2019 end-page: 56 ident: CR7 article-title: Improved recognition results of medieval handwritten Gurmukhi manuscripts using boosting and bagging methodologies publication-title: Neural Process Lett doi: 10.1007/s11063-018-9913-6 – volume: 14 start-page: 3457 issue: 7 year: 2022 end-page: 3469 ident: CR26 article-title: Image denoising to enhance character recognition using deep learning publication-title: Int J Inf Technol – ident: CR27 – volume: 8 start-page: 17804 year: 2020 end-page: 17818 ident: CR23 article-title: A new hybrid convolutional neural network and eXtreme gradient boosting classifier for recognizing handwritten Ethiopian characters publication-title: IEEE Access doi: 10.1109/ACCESS.2019.2960161 – volume: 78 start-page: 23255 year: 2019 end-page: 23280 ident: CR3 article-title: Drop flow method: an iterative algorithm for complete segmentation of devanagari ancient manuscripts publication-title: Multimed Tools Appl doi: 10.1007/s11042-019-7620-6 – volume: 12 start-page: 57 issue: 1 year: 2020 end-page: 64 ident: CR19 article-title: Effect of supervised learning methodologies in offline handwritten thai character recognition publication-title: Int J Inf Technol – volume: 14 start-page: 145 year: 2022 end-page: 153 ident: CR21 article-title: Degraded offline handwritten gurmukhi character recognition: study of various features and classifiers publication-title: Int J Inf Technol – ident: CR15 – volume: 92 start-page: 203 issue: 1 year: 2019 end-page: 218 ident: CR1 article-title: RNN based online handwritten word recognition in Devanagari and Bengali scripts using horizontal zoning publication-title: Pattern Recogn doi: 10.1016/j.patcog.2019.03.030 – ident: CR9 – volume: 80 start-page: 20671 issue: 13 year: 2021 end-page: 20686 ident: CR5 article-title: DeepNetDevanagari: a deep learning model for Devanagari ancient character recognition publication-title: Multimed Tools Appl doi: 10.1007/s11042-021-10775-6 – volume: 24 start-page: 17279 issue: 22 year: 2020 end-page: 17289 ident: CR17 article-title: On the recognition of Devanagari ancient handwritten characters using SIFT and Gabor features publication-title: Soft Comput doi: 10.1007/s00500-020-05018-z – volume: 24 start-page: 10933 issue: 14 year: 2020 end-page: 10941 ident: CR8 article-title: A hybrid group search optimization: firefly algorithm-based big data framework for ancient script recognition publication-title: Soft Comput doi: 10.1007/s00500-019-04596-x – volume: 136 start-page: 134 year: 2020 end-page: 141 ident: CR10 article-title: An attention-based row-column encoder-decoder model for text recognition in Japanese historical documents publication-title: Pattern Recogn Lett doi: 10.1016/j.patrec.2020.05.026 – ident: CR28 – volume: 27 start-page: 1817 year: 2016 end-page: 1829 ident: CR4 article-title: Pixel plot and trace based segmentation method for bilingual handwritten scripts using feedforward neural network publication-title: Neural Comput Appl doi: 10.1007/s00521-015-1972-2 – volume: 15 start-page: 827 issue: 8 year: 2020 end-page: 834 ident: CR13 article-title: Handwritten character recognition from ancient palm leaves using Gabor based MultiLayer Architecture:GMA publication-title: Int J Appl Eng Res – volume: 13 start-page: 2389 year: 2021 end-page: 2396 ident: CR20 article-title: Offline handwritten gurmukhi character recognition: k-nn vs. svm classifier publication-title: Int J Inf Technol – ident: CR24 – volume: 1 start-page: 1 issue: 11 year: 2019 end-page: 7 ident: CR25 article-title: Ancient Geez script recognition using deep learning publication-title: SN Appl Sci doi: 10.1007/s42452-019-1340-4 – volume: 78 start-page: 23255 year: 2019 ident: 1247_CR3 publication-title: Multimed Tools Appl doi: 10.1007/s11042-019-7620-6 – ident: 1247_CR30 doi: 10.1109/CVPR.2016.308 – volume: 24 start-page: 17279 issue: 22 year: 2020 ident: 1247_CR17 publication-title: Soft Comput doi: 10.1007/s00500-020-05018-z – volume: 8 start-page: 52641 year: 2020 ident: 1247_CR22 publication-title: IEEE Access doi: 10.1109/ACCESS.2020.2975023 – volume: 136 start-page: 134 year: 2020 ident: 1247_CR10 publication-title: Pattern Recogn Lett doi: 10.1016/j.patrec.2020.05.026 – volume: 1 start-page: 1 issue: 11 year: 2019 ident: 1247_CR25 publication-title: SN Appl Sci doi: 10.1007/s42452-019-1340-4 – volume: 14 start-page: 145 year: 2022 ident: 1247_CR21 publication-title: Int J Inf Technol – volume: 24 start-page: 10933 issue: 14 year: 2020 ident: 1247_CR8 publication-title: Soft Comput doi: 10.1007/s00500-019-04596-x – volume: 80 start-page: 20671 issue: 13 year: 2021 ident: 1247_CR5 publication-title: Multimed Tools Appl doi: 10.1007/s11042-021-10775-6 – ident: 1247_CR27 doi: 10.17632/y2s635w8wd.1 – ident: 1247_CR24 doi: 10.1155/2021/2491116 – ident: 1247_CR2 doi: 10.1007/s11042-022-13709-y – ident: 1247_CR16 – volume: 13 start-page: 2389 year: 2021 ident: 1247_CR20 publication-title: Int J Inf Technol – volume: 15 start-page: 827 issue: 8 year: 2020 ident: 1247_CR13 publication-title: Int J Appl Eng Res – volume: 12 start-page: 57 issue: 1 year: 2020 ident: 1247_CR19 publication-title: Int J Inf Technol – volume: 27 start-page: 1817 year: 2016 ident: 1247_CR4 publication-title: Neural Comput Appl doi: 10.1007/s00521-015-1972-2 – volume: 50 start-page: 43 issue: 1 year: 2019 ident: 1247_CR7 publication-title: Neural Process Lett doi: 10.1007/s11063-018-9913-6 – ident: 1247_CR28 doi: 10.1109/CVPR.2016.90 – ident: 1247_CR6 doi: 10.1109/ICCMC.2017.8282574 – ident: 1247_CR12 doi: 10.1109/PDGC.2018.8745903 – ident: 1247_CR14 doi: 10.1109/DAS.2018.50 – volume: 14 start-page: 3457 issue: 7 year: 2022 ident: 1247_CR26 publication-title: Int J Inf Technol – ident: 1247_CR9 doi: 10.1109/DAS.2016.60 – ident: 1247_CR29 doi: 10.1109/CVPR.2017.195 – ident: 1247_CR15 doi: 10.1007/978-981-15-1084-7_19 – volume: 20 start-page: 143 issue: 1 year: 2017 ident: 1247_CR11 publication-title: Eng Sci Technol Int J – volume: 44 start-page: 1 issue: 6 year: 2019 ident: 1247_CR18 publication-title: Sādhanā doi: 10.1007/s12046-019-1126-9 – volume: 8 start-page: 17804 year: 2020 ident: 1247_CR23 publication-title: IEEE Access doi: 10.1109/ACCESS.2019.2960161 – volume: 92 start-page: 203 issue: 1 year: 2019 ident: 1247_CR1 publication-title: Pattern Recogn doi: 10.1016/j.patcog.2019.03.030
SSID	ssib031263571 ssj0002710285
Score	2.2147255
Snippet	An optical character recognition (OCR) system plays an important role in the digitization of ancient handwritten text document. Various adversaries of ancient...
SourceID	proquest crossref springer
SourceType	Aggregation Database Enrichment Source Index Database Publisher
StartPage	1975
SubjectTerms	Artificial Intelligence Artificial neural networks Computer Imaging Computer Science Convolution Documents Handwriting recognition Image Processing and Computer Vision Machine Learning Neural networks Optical character recognition Optimization techniques Original Research Pattern Recognition and Graphics Software Engineering Vision
SummonAdditionalLinks	– databaseName: Computer Science Database dbid: K7- link: http://cvtisr.summon.serialssolutions.com/2.0.0/link/0/eLvHCXMwpV09T8MwELWgMMDAN6JQkAc2sKjtxEknVCEKU8UAElsUn2NRBCm0AaT-enyu0wISLKz5sJLc-e7Fd36PkGPnM6CEtsxECliUS8G0jRQTCjpgZK5FbLzYRNLvp_f3nZuw4DYObZV1TPSB2gwB18jPpMO-gsukrc5fXhmqRmF1NUhoLJIlLlwQxqJswmp_khyZVgLcefRFNkyn2NWIwJq5v50o7KPxu-kinqIKi8AGIxEljH_PVXMA-qNm6lNRb_2_L7FB1gIIpd2p12yShaLcIqtfqAm3ie6WdOjCyfNgUhh60e_TKeczrYY0NB1NCorL7h-jQeWAN4Wa-nlMByX1or9lRd0zvflddHjwyiXG6iGn01C1Q-56l7cX1yzoMTAQLtkx2VFGAhLSGDfRIw6W56BziCU489rYqCjVSlndFiY3HWttCsZqJMS3CjTIXdIoh2WxR2gKkLSN8-K40A5SQJ6i0IyV0uVTF7rjJuH1l88gkJWjZsZTNqNZ9tbKnLUyb62MN8nJ7J6XKVXHn1e3ahNlYdqOs7l9muS0NvL89O-j7f892gFZEd6vsOOnRRrV6K04JMvwXg3GoyPvtJ_Dy-_Z priority: 102 providerName: ProQuest
Title	An optimized CNN system to recognize handwritten characters in ancient documents in Grantha script
URI	https://link.springer.com/article/10.1007/s41870-023-01247-1 https://www.proquest.com/docview/3255213706
Volume	15
hasFullText	1
inHoldings	1
isFullTextHit
isPrint
journalDatabaseRights	– providerCode: PRVPQU databaseName: Computer Science Database customDbUrl: eissn: 2511-2112 dateEnd: 20241214 omitProxy: false ssIdentifier: ssj0002710285 issn: 2511-2104 databaseCode: K7- dateStart: 20230101 isFulltext: true titleUrlDefault: http://search.proquest.com/compscijour providerName: ProQuest – providerCode: PRVPQU databaseName: ProQuest advanced technologies & aerospace journals customDbUrl: eissn: 2511-2112 dateEnd: 20241214 omitProxy: false ssIdentifier: ssj0002710285 issn: 2511-2104 databaseCode: P5Z dateStart: 20230101 isFulltext: true titleUrlDefault: https://search.proquest.com/hightechjournals providerName: ProQuest – providerCode: PRVPQU databaseName: ProQuest Central customDbUrl: eissn: 2511-2112 dateEnd: 20241214 omitProxy: false ssIdentifier: ssj0002710285 issn: 2511-2104 databaseCode: BENPR dateStart: 20230101 isFulltext: true titleUrlDefault: https://www.proquest.com/central providerName: ProQuest – providerCode: PRVAVX databaseName: SpringerLINK Contemporary 1997-Present customDbUrl: eissn: 2511-2112 dateEnd: 99991231 omitProxy: false ssIdentifier: ssj0002710285 issn: 2511-2104 databaseCode: RSV dateStart: 20170301 isFulltext: true titleUrlDefault: https://link.springer.com/search?facet-content-type=%22Journal%22 providerName: Springer Nature
link	http://cvtisr.summon.serialssolutions.com/2.0.0/link/0/eLvHCXMwnV1JS8QwFH64HfTgLo7LkIM3DUyTNu0cVVxAKIMb4qU0Lw2OaEdmOgr-epNMOi6ooJce2jSUvJe3NO99H8CO0RkUTGqqQoE0zDmjUoeCMoFtVDyXLFKObCJO0-Tmpt3xTWGDutq9PpJ0lnrc7BYGiSVJYbb-h4UxNTnPdGTRZmyOfnFdaxEPLL6KD3Lu3dGadaK2ltGG09TkOKHvnvl-2s8e6j3s_HJS6hzQ8cL_Pn0R5n3ASfZHGrIEE0W5DAs1mQPxe3sZ5j4gE66A3C9Jz1iTx-5rochhmpIR5DOpesTXHL0WxP51f-l3KxN3E6yRnwekWxLH-VtWRPVw6Jro7M0T4xeru5yMLNUqXB0fXR6eUk_HQJEZX0d5WyiOFo9GmX0eBqiDHGWOEUcjXR0pESZSCC1bTOWqrbVOUGlp8fC1QIl8DabKXlmsA0kQ45YyShwV0kQUmCeWZ0ZzbtypsdxRA4JaBBl6rHJLmfGQjVGW3ZJmZkkzt6RZ0IDd8TtPI6SOX0dv1ZLN_K4dZNzkVyzgcUs0YK-W5Pvjn2fb-NvwTZhlThlsAdAWTFX9YbENM_hcdQf9JkwfHKWd8yZMnsXUXDvRbdNp-BvmkO_l
linkProvider	Springer Nature
linkToHtml	http://cvtisr.summon.serialssolutions.com/2.0.0/link/0/eLvHCXMw1V1Nb9QwEB2VggQc-EZdKOADnMBiYzve7AFVVaG0aol6KFLFJcTjWCyCbLubUtEfxW_sjJN0AYneeuCaDytxnmfGmZn3AJ4TZtAqF6Q3FqUptZIuGCuVxTF6XTqV-ig2Mcrz7OBgvLcEv_peGC6r7G1iNNR-ivyP_LWm2FclejS0a4dHklWjOLvaS2i0sNipfp7Qlm3-Zvstfd8XSm2-29_Ykp2qgERFJlvqsfUamVbFE1xNgiEp0ZWYaqSHDKm3JnPWBjdUvvTjEEKGPjimdQ8WHWoa9wpcNUYNWTFhL_3U41cnzOzShVdfY1KP3TdXUXIgL2l3Zbq-ndi9Z5KMVV8UFzQpM5LJn75xEfD-laONrm_z9v82aXfgVhdki_V2VdyFpaq-Bzd_o168D269FlMyl98np5UXG3kuWk5r0UxFV1R1WglOK5zMJg1tLAT21NZzMalFFDWuG0FzcBy7BPnge3L8zZdStKb4AXy8lJd8CMv1tK5WQGSIo6GnVZpWjkImLDMW0glaU7xArikdQNJ_6QI7MnbWBPlWnNNIR3QUhI4ioqNIBvDy_J7DlorkwqtXe0gUnVmaFws8DOBVD6rF6X-P9uji0Z7B9a39D7vF7na-8xhuqIhprm5aheVmdlw9gWv4o5nMZ0_jghHw-bLBdgY2iU_o
linkToPdf	http://cvtisr.summon.serialssolutions.com/2.0.0/link/0/eLvHCXMw1V1Lb9QwEB6VLUJwoFCKWGjBBziB1Y2dONkDQn0tVEXRqqJSbyEex2IRZMtuSkV_Gr-OseN0WyR664FrHlbifJ5HPPN9AC8JM6iEttzECnlcSsG1jRUXCodoZKlFYrzYRJrn2fHxcLwEv7teGFdW2dlEb6jNFN0_8k1Jsa-IZDpQmzaURYx3R-9OfnCnIOV2Wjs5jRYiB9WvM0rf5m_3d-lbvxJitPdp5wMPCgMcBZlvLofKSHQUK4agG0dooxJ1iYlEemCbGBVnWimrB8KUZmitzdBY7SjerUKNksa9BcuppKSnB8vbe_n4sEOzjBzPSwi2vvotPufMXU2lC-s55Vpx6OLxvXxxlDkNGOHKm0Sc8uiqp1yEv3_t2HpHOFr5n6fwAdwP4TfbatfLQ1iq6lW4d4mU8RHorZpNyZB-n5xXhu3kOWvZrlkzZaHc6rxibsPhbDZpKOVg2JFez9mkZl7uuG4Yzcep7x90B99TSNB8KVlrpNfg6EZe8jH06mldPQGWIaYDQ-s3qTQFU1hmTmLHSkmRBDmtpA9R99ULDDTtTi3kW3FBMO2RUhBSCo-UIurD64t7TlqSkmuvXu_gUQSDNS8W2OjDmw5gi9P_Hu3p9aO9gDuEseLjfn7wDO4KD29X9rQOvWZ2Wm3AbfzZTOaz52H1MPh802j7A74HWek
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%3Ajournal&rft.genre=article&rft.atitle=An+optimized+CNN+system+to+recognize+handwritten+characters+in+ancient+documents+in+Grantha+script&rft.jtitle=International+journal+of+information+technology+%28Singapore.+Online%29&rft.au=Jindal%2C+Amar&rft.au=Ghosh%2C+Rajib&rft.date=2023-04-01&rft.issn=2511-2104&rft.eissn=2511-2112&rft.volume=15&rft.issue=4&rft.spage=1975&rft.epage=1983&rft_id=info:doi/10.1007%2Fs41870-023-01247-1&rft.externalDBID=n%2Fa&rft.externalDocID=10_1007_s41870_023_01247_1
thumbnail_l	http://covers-cdn.summon.serialssolutions.com/index.aspx?isbn=/lc.gif&issn=2511-2104&client=summon
thumbnail_m	http://covers-cdn.summon.serialssolutions.com/index.aspx?isbn=/mc.gif&issn=2511-2104&client=summon
thumbnail_s	http://covers-cdn.summon.serialssolutions.com/index.aspx?isbn=/sc.gif&issn=2511-2104&client=summon