Developing adaptive Yolov5-based Telugu handwritten character segmentation and classification framework using Enhanced Chef-Based Optimization Algorithm and Deep Learning Networks

Handwritten character recognition through automated techniques is one of the recent innovations in the industry, as it helps in interpreting historical documents, digital scripts, and large records. Deep learning techniques are effective in recognizing complex image patterns like handwritten Telugu...

Celý popis

Uložené v:
Podrobná bibliografia
Vydané v:Computers & electrical engineering Ročník 126; s. 110533
Hlavní autori: Sastry, M. Kiran, Aparna, S.
Médium: Journal Article
Jazyk:English
Vydavateľské údaje: Elsevier Ltd 01.08.2025
Predmet:
ISSN:0045-7906
On-line prístup:Získať plný text
Tagy: Pridať tag
Žiadne tagy, Buďte prvý, kto otaguje tento záznam!
Abstract Handwritten character recognition through automated techniques is one of the recent innovations in the industry, as it helps in interpreting historical documents, digital scripts, and large records. Deep learning techniques are effective in recognizing complex image patterns like handwritten Telugu scripts, and however, inherent variability in writing styles, unique characteristics, limited data pose a challenging recognition environment. Defining a robust segmentation and classification tool with intelligent deep-learning techniques is one of the possible solutions for handling the variability and challenges within handwritten character recognition. So, this paper presented an effective Telugu handwritten character segmentation and classification model for handling the challenges in recognition of variable length sequences. Initially, the handwritten images are acquired from online data sources and are inputted into the Adaptive Yolov5 (A-YoloV5) model for the segmentation process. Here, the Enhanced Chef-Based Optimization Algorithm (ECOA) is developed for improving the performance of YoloV5 platform and reduces complexity in training. Then, the Adaptive Yolov5 (A-YoloV5) segments the telugu characters from the input handwritten images. After extracting ROI, the extracted images are sent into the newly developed Convolutional Neural Networks with Residual Attention-based Long Short-Term Memory layer (CNN-RA-LSTM) model for classification of the handwritten images. This network combines the CNN and LSTM networks with added residual layers to effectively extract the sequential features and then categorize the text. The efficacy of the CNN-RA-LSTM and A-Yolov5 model is compared with recent Telugu handwritten character recognition and has resulted in 95.41 % text recognition accuracy.
AbstractList Handwritten character recognition through automated techniques is one of the recent innovations in the industry, as it helps in interpreting historical documents, digital scripts, and large records. Deep learning techniques are effective in recognizing complex image patterns like handwritten Telugu scripts, and however, inherent variability in writing styles, unique characteristics, limited data pose a challenging recognition environment. Defining a robust segmentation and classification tool with intelligent deep-learning techniques is one of the possible solutions for handling the variability and challenges within handwritten character recognition. So, this paper presented an effective Telugu handwritten character segmentation and classification model for handling the challenges in recognition of variable length sequences. Initially, the handwritten images are acquired from online data sources and are inputted into the Adaptive Yolov5 (A-YoloV5) model for the segmentation process. Here, the Enhanced Chef-Based Optimization Algorithm (ECOA) is developed for improving the performance of YoloV5 platform and reduces complexity in training. Then, the Adaptive Yolov5 (A-YoloV5) segments the telugu characters from the input handwritten images. After extracting ROI, the extracted images are sent into the newly developed Convolutional Neural Networks with Residual Attention-based Long Short-Term Memory layer (CNN-RA-LSTM) model for classification of the handwritten images. This network combines the CNN and LSTM networks with added residual layers to effectively extract the sequential features and then categorize the text. The efficacy of the CNN-RA-LSTM and A-Yolov5 model is compared with recent Telugu handwritten character recognition and has resulted in 95.41 % text recognition accuracy.
ArticleNumber 110533
Author Aparna, S.
Sastry, M. Kiran
Author_xml – sequence: 1
  givenname: M. Kiran
  surname: Sastry
  fullname: Sastry, M. Kiran
  email: kmatti@gitam.in
– sequence: 2
  givenname: S.
  surname: Aparna
  fullname: Aparna, S.
  email: ashivamp@gitam.edu
BookMark eNqNkMtOxCAUhllo4vUd8AE6QkuZcanjNZnoRheuCD097TC20AAzRl_LF5RaFy5dEU74v__wHZE96ywScsbZjDMuzzczcP2AHQLadpazvJxxzsqi2COHjIkym18weUCOQtiwdJd8cUi-rnGHnRuMbamu9RDNDumr69yuzCodsKbP2G3bLV1rW797EyNaCmvtNUT0NGDbo406GmdpekGh0yGYxsA0arzu8d35N7oNY8WNTRxI1OUam-zqp-Aplfbmcwpcdq1LLev-h3aNONAVam_H8CPGERVOyH6ju4Cnv-cxebm9eV7eZ6unu4fl5SqDXM5jlouGQZlLUUAFyIumlCCwEpAGBZSiqqBKckDUBV-wxbzmWIiK50KinMtaFMfkYuKCdyF4bNTgTa_9h-JMjcbVRv0xrkbjajKessspi2nBnUGvAhgcv248QlS1M_-gfANUmJlU
Cites_doi 10.1109/TMM.2022.3143324
10.1109/TPAMI.2004.74
10.1109/TPAMI.2008.88
10.1109/ACCESS.2021.3115606
10.1109/LSP.2019.2895967
10.1109/ACCESS.2022.3208959
10.1109/ACCESS.2022.3201560
10.1109/TPAMI.2006.103
10.1109/TPAMI.2007.1090
10.1109/TSMCB.2004.837588
10.1109/ACCESS.2023.3310819
10.1109/TMM.2020.3025696
10.1109/TCBB.2018.2814586
10.1038/s41598-022-19313-2
10.1109/ACCESS.2021.3123726
10.1109/ACCESS.2020.3039003
10.1109/TPAMI.2011.264
10.1007/s42979-025-03677-z
10.3390/s21082811
10.1109/ACCESS.2023.3260632
10.1109/ACCESS.2020.2970438
10.1109/TPAMI.2007.70734
10.1016/j.asoc.2012.11.026
10.1109/ACCESS.2019.2930799
10.1109/TNNLS.2019.2956965
10.1109/ACCESS.2023.3263721
10.11591/ijece.v13i1.pp413-424
10.1109/ACCESS.2021.3104731
10.1007/s10489-020-01893-z
10.1109/JIOT.2019.2947448
10.1002/int.22535
10.1109/ACCESS.2018.2795104
10.1016/j.asoc.2025.112937
ContentType Journal Article
Copyright 2025
Copyright_xml – notice: 2025
DBID AAYXX
CITATION
DOI 10.1016/j.compeleceng.2025.110533
DatabaseName CrossRef
DatabaseTitle CrossRef
DatabaseTitleList
DeliveryMethod fulltext_linktorsrc
Discipline Engineering
ExternalDocumentID 10_1016_j_compeleceng_2025_110533
S0045790625004768
GroupedDBID --K
--M
.DC
.~1
0R~
1B1
1~.
1~5
29F
4.4
457
4G.
5GY
5VS
7-5
71M
8P~
9JN
AAEDT
AAEDW
AAIKJ
AAKOC
AALRI
AAOAW
AAQFI
AAQXK
AATTM
AAXKI
AAXUO
AAYFN
AAYWO
ABBOA
ABEFU
ABFNM
ABJNI
ABMAC
ABWVN
ABXDB
ACDAQ
ACGFO
ACGFS
ACNNM
ACRLP
ACRPL
ACVFH
ACZNC
ADBBV
ADCNI
ADEZE
ADJOM
ADMUD
ADNMO
ADTZH
AEBSH
AECPX
AEIPS
AEKER
AENEX
AEUPX
AFFNX
AFJKZ
AFPUW
AFTJW
AGCQF
AGHFR
AGQPQ
AGUBO
AGYEJ
AHHHB
AHJVU
AHZHX
AIALX
AIEXJ
AIGII
AIIUN
AIKHN
AITUG
AKBMS
AKRWK
AKYEP
ALMA_UNASSIGNED_HOLDINGS
AMRAJ
ANKPU
AOUOD
APXCP
ASPBG
AVWKF
AXJTR
AZFZN
BJAXD
BKOJK
BLXMC
CS3
DU5
EBS
EFJIC
EFKBS
EJD
EO8
EO9
EP2
EP3
FDB
FEDTE
FGOYB
FIRID
FNPLU
FYGXN
G-2
G-Q
GBLVA
GBOLZ
HLZ
HVGLF
HZ~
IHE
J1W
JJJVA
KOM
LG9
LY7
M41
MO0
N9A
O-L
O9-
OAUVE
OZT
P-8
P-9
P2P
PC.
PQQKQ
Q38
R2-
ROL
RPZ
RXW
SBC
SDF
SDG
SDP
SES
SET
SEW
SPC
SPCBC
SST
SSV
SSZ
T5K
TAE
TN5
UHS
VOH
WH7
WUQ
XPP
ZMT
~G-
~S-
9DU
AAYXX
ACLOT
CITATION
EFLBG
~HD
ID FETCH-LOGICAL-c267t-24f0c52643cbce13f56c4eb4c43c3c54bbcb533c4d318087d1e34b1246e676d43
ISICitedReferencesCount 0
ISICitedReferencesURI http://www.webofscience.com/api/gateway?GWVersion=2&SrcApp=Summon&SrcAuth=ProQuest&DestLinkType=CitingArticles&DestApp=WOS_CPL&KeyUT=001521399700003&url=https%3A%2F%2Fcvtisr.summon.serialssolutions.com%2F%23%21%2Fsearch%3Fho%3Df%26include.ft.matches%3Dt%26l%3Dnull%26q%3D
ISSN 0045-7906
IngestDate Sat Nov 29 07:43:43 EST 2025
Sat Aug 23 17:12:41 EDT 2025
IsPeerReviewed true
IsScholarly true
Keywords Enhanced Chef-Based Optimization Algorithm
Convolutional neural networks with res-attention-long short-term memory layer
Telugu handwritten character segmentation and classification
Adaptive Yolov5
Language English
LinkModel OpenURL
MergedId FETCHMERGED-LOGICAL-c267t-24f0c52643cbce13f56c4eb4c43c3c54bbcb533c4d318087d1e34b1246e676d43
ParticipantIDs crossref_primary_10_1016_j_compeleceng_2025_110533
elsevier_sciencedirect_doi_10_1016_j_compeleceng_2025_110533
PublicationCentury 2000
PublicationDate August 2025
2025-08-00
PublicationDateYYYYMMDD 2025-08-01
PublicationDate_xml – month: 08
  year: 2025
  text: August 2025
PublicationDecade 2020
PublicationTitle Computers & electrical engineering
PublicationYear 2025
Publisher Elsevier Ltd
Publisher_xml – name: Elsevier Ltd
References Sahare, Dhok (bib0006) 2018; 6
Abdollahzadeh, Soleimanian Gharehchopogh, Mirjalili (bib0041) 2021; 36
Wang, Yin, Liu (bib0009) Aug. 2012; 34
Zeng, Liu (bib0007) May 2008; 30
Mukku, Santhosh (bib0020) 2024; 32
Zhao, Lan, Niu, Zhu, Qian, Tang (bib0038) 2021; 9
Liu, Hu, Chen, Wu, You (bib0011) Nov. 2020; 31
Berriche, Alqahtani, Rekik (bib0026) 9 December 2023
Wang, Yang, Ding, Li (bib0036) 2021; 9
Liu (bib0010) Aug. 2007; 29
Buddaraju Revathi, Marapatla, Veeramanikanta, Dinesh, Supraja (bib0019) 2024; 13
Ullah, Ullah, Hussain, Ahmad Khan, Baik (bib0033) 2021; 21
Sahlol, Abd Elaziz, Al-Qaness, Kim (bib0021) 2020; 8
Zhang, Bi, Chen, Wang, Han, Cai (bib0013) Feb. 2020; 7
Song, Li, Lyu, Cai (bib0015) Feb. 2005; 35
Trojovská, Dehghani (bib0031) 2022; 12
Fang, Shang, Xu (bib0034) 1 May-June 2019; 16
Channegowda, Karthik, Srinivasaiah, Shivaraj (bib0037) 2023; 13
Shabir, Islam, Jan, Khan, Rahman, Zeb, Ahmad (bib0005) 2021; 9
Zimmermann, Chappelier, Bunke (bib0003) May 2006; 28
Li, Yang, Chen, Hu, Wang, Ding, Ma (bib0014) 2023; 25
Banavatu, Parthasarathy (bib0018) 2025; 174
Xue, Abhayaratne (bib0035) 2023; 11
Wu, Chen, Xiao, Li, Liu, Hu (bib0012) 2021; 23
El Abbadi (bib0030) 2023; 2
Sadollah, Bahreininejad, Eskandar, Hamdi (bib0039) 2013; 13
Sahay, Coustaty (bib0023) 2023; 11
Bhattacharya, Chaudhuri (bib0008) March 2009; 31
Hashim, Hussain, Houssein, Mabrouk, Al-Atabany (bib0040) 2021; 51
Karthik, Srikanta Murthy (bib0028) 2019; 22
Kang, Kim (bib0016) Sept. 2004; 26
Thara, Gaddam, Ramakurthi, Basava, Thupakala, Dhanya (bib0029) 2025; 6
Rasheed, Ali, Zafar, Shabbir, Sajid, Mahmood (bib0001) 2022; 10
Ott, Rügamer, Heublein, Bischl, Mutschler (bib0004) 2023; 11
Xu, Wang, Li, Pan (bib0022) 2019; 7
Wu, Chen, You, Xiao (bib0025) April 2019; 26
Gonwirat, Surinta (bib0002) 2022; 10
De Sousa Neto, Bezerra, Lima, Toselli (bib0017) 2020; 8
Verma, Kumar (bib0027) 2018; 88
Moudgil, Singh, Gautam, Rani, Shah (bib0024) June 2023; 4
Bhardwaj (bib0032) 2020; 17
Wang (10.1016/j.compeleceng.2025.110533_bib0036) 2021; 9
Channegowda (10.1016/j.compeleceng.2025.110533_bib0037) 2023; 13
Sahay (10.1016/j.compeleceng.2025.110533_bib0023) 2023; 11
Sahare (10.1016/j.compeleceng.2025.110533_bib0006) 2018; 6
Bhattacharya (10.1016/j.compeleceng.2025.110533_bib0008) 2009; 31
Kang (10.1016/j.compeleceng.2025.110533_bib0016) 2004; 26
Banavatu (10.1016/j.compeleceng.2025.110533_bib0018) 2025; 174
Karthik (10.1016/j.compeleceng.2025.110533_bib0028) 2019; 22
Shabir (10.1016/j.compeleceng.2025.110533_bib0005) 2021; 9
Zimmermann (10.1016/j.compeleceng.2025.110533_bib0003) 2006; 28
Ott (10.1016/j.compeleceng.2025.110533_bib0004) 2023; 11
Wang (10.1016/j.compeleceng.2025.110533_bib0009) 2012; 34
Liu (10.1016/j.compeleceng.2025.110533_bib0011) 2020; 31
Gonwirat (10.1016/j.compeleceng.2025.110533_bib0002) 2022; 10
Fang (10.1016/j.compeleceng.2025.110533_bib0034) 2019; 16
Li (10.1016/j.compeleceng.2025.110533_bib0014) 2023; 25
Liu (10.1016/j.compeleceng.2025.110533_bib0010) 2007; 29
Verma (10.1016/j.compeleceng.2025.110533_bib0027) 2018; 88
Rasheed (10.1016/j.compeleceng.2025.110533_bib0001) 2022; 10
Zhang (10.1016/j.compeleceng.2025.110533_bib0013) 2020; 7
Trojovská (10.1016/j.compeleceng.2025.110533_bib0031) 2022; 12
Thara (10.1016/j.compeleceng.2025.110533_bib0029) 2025; 6
Bhardwaj (10.1016/j.compeleceng.2025.110533_bib0032) 2020; 17
Hashim (10.1016/j.compeleceng.2025.110533_bib0040) 2021; 51
Song (10.1016/j.compeleceng.2025.110533_bib0015) 2005; 35
Ullah (10.1016/j.compeleceng.2025.110533_bib0033) 2021; 21
Mukku (10.1016/j.compeleceng.2025.110533_bib0020) 2024; 32
Zhao (10.1016/j.compeleceng.2025.110533_bib0038) 2021; 9
Berriche (10.1016/j.compeleceng.2025.110533_bib0026) 2023
Abdollahzadeh (10.1016/j.compeleceng.2025.110533_bib0041) 2021; 36
Zeng (10.1016/j.compeleceng.2025.110533_bib0007) 2008; 30
Xu (10.1016/j.compeleceng.2025.110533_bib0022) 2019; 7
Wu (10.1016/j.compeleceng.2025.110533_bib0012) 2021; 23
Moudgil (10.1016/j.compeleceng.2025.110533_bib0024) 2023; 4
Xue (10.1016/j.compeleceng.2025.110533_bib0035) 2023; 11
De Sousa Neto (10.1016/j.compeleceng.2025.110533_bib0017) 2020; 8
Sadollah (10.1016/j.compeleceng.2025.110533_bib0039) 2013; 13
Buddaraju Revathi (10.1016/j.compeleceng.2025.110533_bib0019) 2024; 13
Sahlol (10.1016/j.compeleceng.2025.110533_bib0021) 2020; 8
El Abbadi (10.1016/j.compeleceng.2025.110533_bib0030) 2023; 2
Wu (10.1016/j.compeleceng.2025.110533_bib0025) 2019; 26
References_xml – volume: 13
  year: 2024
  ident: bib0019
  article-title: Optical character recognition for Telugu handwritten text using SqueezeNet convolutional neural networks model
  publication-title: Int J Adv Appl Sci
– year: 9 December 2023
  ident: bib0026
  article-title: Hybrid Arabic Handwritten character segmentation using Cnn and graph theory algorithm
  publication-title: J. King Saud University-Computer and Information Sciences
– volume: 11
  start-page: 28856
  year: 2023
  end-page: 28872
  ident: bib0035
  article-title: Region-of-interest aware 3D ResNet for classification of COVID-19 chest computerised tomography scans
  publication-title: IEEE Access
– volume: 10
  start-page: 102629
  year: 2022
  end-page: 102645
  ident: bib0001
  article-title: Handwritten urdu characters and digits recognition using transfer learning and augmentation with AlexNet
  publication-title: IEEE Access
– volume: 30
  start-page: 767
  year: May 2008
  end-page: 780
  ident: bib0007
  article-title: Markov random field-based statistical character structure modeling for handwritten Chinese character recognition
  publication-title: IEEE Trans Pattern Anal Mach Intell
– volume: 2
  start-page: 13
  year: 2023
  end-page: 27
  ident: bib0030
  article-title: Scene text detection and recognition by using multi-level features extractions based on you only once version five (YOLOv5) and maximally stable extremal regions (MSERs) with optical character recognition (OCR)
  publication-title: Al-Salam J Eng
– volume: 31
  start-page: 4637
  year: Nov. 2020
  end-page: 4648
  ident: bib0011
  article-title: Stroke sequence-dependent deep convolutional neural network for online handwritten Chinese character recognition
  publication-title: IEEE Trans Neural Netw Learn Syst
– volume: 26
  start-page: 1185
  year: Sept. 2004
  end-page: 1196
  ident: bib0016
  article-title: Utilization of hierarchical, stochastic relationship modeling for Hangul character recognition
  publication-title: IEEE trans pattern anal mach intell
– volume: 6
  start-page: 136
  year: 2025
  ident: bib0029
  article-title: TeluguScriptify: A custom deep learning model for handwritten Telugu text recognition and tool development
  publication-title: SN Comput Sci
– volume: 35
  start-page: 2
  year: Feb. 2005
  end-page: 11
  ident: bib0015
  article-title: Recognition of merged characters based on forepart prediction, necessity-sufficiency matching, and character-adaptive masking
  publication-title: IEEE Trans Syst, Man, and Cybernetics, Part B (Cybernetics)
– volume: 25
  start-page: 2140
  year: 2023
  end-page: 2152
  ident: bib0014
  article-title: Fast and robust online handwritten Chinese character recognition with deep spatial and contextual information fusion network
  publication-title: IEEE Trans Multimedia
– volume: 13
  start-page: 2592
  year: 2013
  end-page: 2612
  ident: bib0039
  article-title: Mine blast algorithm: A new population based algorithm for solving constrained engineering optimization problems
  publication-title: Appl Soft Comput
– volume: 10
  start-page: 90133
  year: 2022
  end-page: 90148
  ident: bib0002
  article-title: DeblurGAN-CNN: effective image denoising and recognition for noisy handwritten characters
  publication-title: IEEE Access
– volume: 88
  start-page: 297
  year: 2018
  end-page: 307
  ident: bib0027
  article-title: An efficient writing-zone identification technique for online handwritten Gurmukhi character recognition
  publication-title: Proceed. Nat Acad Sciences.
– volume: 28
  start-page: 818
  year: May 2006
  end-page: 821
  ident: bib0003
  article-title: Offline grammar-based recognition of handwritten sentences
  publication-title: IEEE Trans Pattern Mach Intell
– volume: 12
  year: 2022
  ident: bib0031
  article-title: A new human-based metahurestic optimization method based on mimicking cooking training
  publication-title: Sci Rep
– volume: 4
  start-page: 47
  year: June 2023
  end-page: 54
  ident: bib0024
  article-title: Handwritten devanagari manuscript characters recognition using capsnet
  publication-title: Int J Cognit Comput Eng
– volume: 6
  start-page: 10603
  year: 2018
  end-page: 10617
  ident: bib0006
  article-title: Multilingual character segmentation and recognition schemes for Indian document images
  publication-title: IEEE Access
– volume: 34
  start-page: 1469
  year: Aug. 2012
  end-page: 1481
  ident: bib0009
  article-title: Handwritten chinese text recognition by integrating multiple contexts
  publication-title: IEEE Trans Pattern Anal Mach Intell
– volume: 11
  start-page: 33682
  year: 2023
  end-page: 33696
  ident: bib0023
  article-title: An enhanced prototypical network architecture for few-shot handwritten Urdu character recognition
  publication-title: IEEE Access
– volume: 31
  start-page: 444
  year: March 2009
  end-page: 457
  ident: bib0008
  article-title: Handwritten numeral databases of Indian scripts and multistage recognition of mixed numerals
  publication-title: IEEE Trans Pattern Anal Mach Intell
– volume: 22
  year: 2019
  ident: bib0028
  article-title: Deep belief network based approach to recognize handwritten Kannada characters using distributed average of gradients
  publication-title: Cluster Comput
– volume: 36
  start-page: 5887
  year: 2021
  end-page: 5958
  ident: bib0041
  article-title: Artificial gorilla troops optimizer: a new nature-inspired metaheuristic algorithm for global optimization problems
  publication-title: Int J Intell Syst
– volume: 9
  start-page: 132301
  year: 2021
  end-page: 132310
  ident: bib0036
  article-title: A residual-attention offline handwritten Chinese text recognition based on fully convolutional neural networks
  publication-title: IEEE Access
– volume: 7
  start-page: 102039
  year: 2019
  end-page: 102053
  ident: bib0022
  article-title: Recognition of handwritten Chinese characters based on concept learning
  publication-title: IEEE Access
– volume: 9
  start-page: 160238
  year: 2021
  end-page: 160248
  ident: bib0005
  article-title: Real-time Pashto handwritten character recognition using salient geometric and spectral features
  publication-title: IEEE Access
– volume: 51
  start-page: 1531
  year: 2021
  end-page: 1551
  ident: bib0040
  article-title: Archimedes optimization algorithm: a new metaheuristic algorithm for solving optimization problems
  publication-title: Appl Intell
– volume: 11
  start-page: 94148
  year: 2023
  end-page: 94172
  ident: bib0004
  article-title: Auxiliary cross-modal representation learning with triplet loss functions for online handwriting recognition
  publication-title: IEEE Access
– volume: 8
  start-page: 23011
  year: 2020
  end-page: 23021
  ident: bib0021
  article-title: Handwritten Arabic optical character recognition approach based on hybrid whale optimization algorithm with neighborhood rough set
  publication-title: IEEE Access
– volume: 8
  start-page: 208543
  year: 2020
  end-page: 208553
  ident: bib0017
  article-title: HDSR-Flor: A robust end-to-end system to solve the handwritten digit string recognition problem in real complex scenarios
  publication-title: IEEE Access
– volume: 174
  year: 2025
  ident: bib0018
  article-title: Heuristic-aided fusion serial cascaded deep network for handwritten character recognition from handwritten images using optimization strategy
  publication-title: Appl Soft Comput
– volume: 9
  start-page: 125540
  year: 2021
  end-page: 125549
  ident: bib0038
  article-title: Detection and location of safety protective wear in power substation operation using wear-enhanced YOLOv3 algorithm
  publication-title: IEEE Access
– volume: 32
  year: 2024
  ident: bib0020
  article-title: Tri-stage offline Telugu character recognition system based on fusion of HOG and ULBP
  publication-title: Measure.: Sensors
– volume: 23
  start-page: 3427
  year: 2021
  end-page: 3440
  ident: bib0012
  article-title: LCSegNet: an efficient semantic segmentation network for large-scale complex Chinese character recognition
  publication-title: IEEE Trans Multimedia
– volume: 26
  start-page: 597
  year: April 2019
  end-page: 601
  ident: bib0025
  article-title: Unconstrained offline handwritten word recognition by position embedding integrated ResNets model
  publication-title: IEEE Signal Process Lett
– volume: 17
  start-page: 7965
  year: 2020
  end-page: 7984
  ident: bib0032
  article-title: Handwritten Devanagari character recognition using deep learning-convolutional neural network (CNN) model
  publication-title: PalArch's J Archaeol Egypt/Egyptol
– volume: 21
  year: 2021
  ident: bib0033
  article-title: An efficient anomaly recognition framework using an attention residual LSTM in surveillance videos
  publication-title: Sensors
– volume: 7
  start-page: 960
  year: Feb. 2020
  end-page: 970
  ident: bib0013
  article-title: SmartHandwriting: handwritten Chinese character recognition with Smartwatch
  publication-title: IEEE Internet Things J
– volume: 13
  start-page: 413
  year: 2023
  end-page: 424
  ident: bib0037
  article-title: Customized mask region based convolutional neural networks for un-uniformed shape text detection and text recognition
  publication-title: Int J Electr Comp Eng (IjECE)
– volume: 29
  start-page: 1465
  year: Aug. 2007
  end-page: 1469
  ident: bib0010
  article-title: Normalization-cooperated gradient feature extraction for handwritten character recognition
  publication-title: IEEE Trans Pattern Anal Mach Intell
– volume: 16
  start-page: 1020
  year: 1 May-June 2019
  end-page: 1028
  ident: bib0034
  article-title: Prediction of protein backbone torsion angles using deep residual inception neural networks
  publication-title: IEEE/ACM Trans Comput Biol Bioinform
– volume: 25
  start-page: 2140
  year: 2023
  ident: 10.1016/j.compeleceng.2025.110533_bib0014
  article-title: Fast and robust online handwritten Chinese character recognition with deep spatial and contextual information fusion network
  publication-title: IEEE Trans Multimedia
  doi: 10.1109/TMM.2022.3143324
– volume: 26
  start-page: 1185
  issue: 9
  year: 2004
  ident: 10.1016/j.compeleceng.2025.110533_bib0016
  article-title: Utilization of hierarchical, stochastic relationship modeling for Hangul character recognition
  publication-title: IEEE trans pattern anal mach intell
  doi: 10.1109/TPAMI.2004.74
– volume: 31
  start-page: 444
  issue: 3
  year: 2009
  ident: 10.1016/j.compeleceng.2025.110533_bib0008
  article-title: Handwritten numeral databases of Indian scripts and multistage recognition of mixed numerals
  publication-title: IEEE Trans Pattern Anal Mach Intell
  doi: 10.1109/TPAMI.2008.88
– volume: 9
  start-page: 132301
  year: 2021
  ident: 10.1016/j.compeleceng.2025.110533_bib0036
  article-title: A residual-attention offline handwritten Chinese text recognition based on fully convolutional neural networks
  publication-title: IEEE Access
  doi: 10.1109/ACCESS.2021.3115606
– volume: 13
  issue: 3
  year: 2024
  ident: 10.1016/j.compeleceng.2025.110533_bib0019
  article-title: Optical character recognition for Telugu handwritten text using SqueezeNet convolutional neural networks model
  publication-title: Int J Adv Appl Sci
– volume: 2
  start-page: 13
  issue: 1
  year: 2023
  ident: 10.1016/j.compeleceng.2025.110533_bib0030
  article-title: Scene text detection and recognition by using multi-level features extractions based on you only once version five (YOLOv5) and maximally stable extremal regions (MSERs) with optical character recognition (OCR)
  publication-title: Al-Salam J Eng
– volume: 26
  start-page: 597
  issue: 4
  year: 2019
  ident: 10.1016/j.compeleceng.2025.110533_bib0025
  article-title: Unconstrained offline handwritten word recognition by position embedding integrated ResNets model
  publication-title: IEEE Signal Process Lett
  doi: 10.1109/LSP.2019.2895967
– volume: 10
  start-page: 102629
  year: 2022
  ident: 10.1016/j.compeleceng.2025.110533_bib0001
  article-title: Handwritten urdu characters and digits recognition using transfer learning and augmentation with AlexNet
  publication-title: IEEE Access
  doi: 10.1109/ACCESS.2022.3208959
– volume: 10
  start-page: 90133
  year: 2022
  ident: 10.1016/j.compeleceng.2025.110533_bib0002
  article-title: DeblurGAN-CNN: effective image denoising and recognition for noisy handwritten characters
  publication-title: IEEE Access
  doi: 10.1109/ACCESS.2022.3201560
– volume: 28
  start-page: 818
  issue: 5
  year: 2006
  ident: 10.1016/j.compeleceng.2025.110533_bib0003
  article-title: Offline grammar-based recognition of handwritten sentences
  publication-title: IEEE Trans Pattern Mach Intell
  doi: 10.1109/TPAMI.2006.103
– volume: 88
  start-page: 297
  year: 2018
  ident: 10.1016/j.compeleceng.2025.110533_bib0027
  article-title: An efficient writing-zone identification technique for online handwritten Gurmukhi character recognition
  publication-title: Proceed. Nat Acad Sciences.
– volume: 29
  start-page: 1465
  issue: 8
  year: 2007
  ident: 10.1016/j.compeleceng.2025.110533_bib0010
  article-title: Normalization-cooperated gradient feature extraction for handwritten character recognition
  publication-title: IEEE Trans Pattern Anal Mach Intell
  doi: 10.1109/TPAMI.2007.1090
– year: 2023
  ident: 10.1016/j.compeleceng.2025.110533_bib0026
  article-title: Hybrid Arabic Handwritten character segmentation using Cnn and graph theory algorithm
  publication-title: J. King Saud University-Computer and Information Sciences
– volume: 35
  start-page: 2
  issue: 1
  year: 2005
  ident: 10.1016/j.compeleceng.2025.110533_bib0015
  article-title: Recognition of merged characters based on forepart prediction, necessity-sufficiency matching, and character-adaptive masking
  publication-title: IEEE Trans Syst, Man, and Cybernetics, Part B (Cybernetics)
  doi: 10.1109/TSMCB.2004.837588
– volume: 11
  start-page: 94148
  year: 2023
  ident: 10.1016/j.compeleceng.2025.110533_bib0004
  article-title: Auxiliary cross-modal representation learning with triplet loss functions for online handwriting recognition
  publication-title: IEEE Access
  doi: 10.1109/ACCESS.2023.3310819
– volume: 23
  start-page: 3427
  year: 2021
  ident: 10.1016/j.compeleceng.2025.110533_bib0012
  article-title: LCSegNet: an efficient semantic segmentation network for large-scale complex Chinese character recognition
  publication-title: IEEE Trans Multimedia
  doi: 10.1109/TMM.2020.3025696
– volume: 16
  start-page: 1020
  issue: 3
  year: 2019
  ident: 10.1016/j.compeleceng.2025.110533_bib0034
  article-title: Prediction of protein backbone torsion angles using deep residual inception neural networks
  publication-title: IEEE/ACM Trans Comput Biol Bioinform
  doi: 10.1109/TCBB.2018.2814586
– volume: 12
  issue: 1
  year: 2022
  ident: 10.1016/j.compeleceng.2025.110533_bib0031
  article-title: A new human-based metahurestic optimization method based on mimicking cooking training
  publication-title: Sci Rep
  doi: 10.1038/s41598-022-19313-2
– volume: 32
  year: 2024
  ident: 10.1016/j.compeleceng.2025.110533_bib0020
  article-title: Tri-stage offline Telugu character recognition system based on fusion of HOG and ULBP
  publication-title: Measure.: Sensors
– volume: 9
  start-page: 160238
  year: 2021
  ident: 10.1016/j.compeleceng.2025.110533_bib0005
  article-title: Real-time Pashto handwritten character recognition using salient geometric and spectral features
  publication-title: IEEE Access
  doi: 10.1109/ACCESS.2021.3123726
– volume: 8
  start-page: 208543
  year: 2020
  ident: 10.1016/j.compeleceng.2025.110533_bib0017
  article-title: HDSR-Flor: A robust end-to-end system to solve the handwritten digit string recognition problem in real complex scenarios
  publication-title: IEEE Access
  doi: 10.1109/ACCESS.2020.3039003
– volume: 4
  start-page: 47
  year: 2023
  ident: 10.1016/j.compeleceng.2025.110533_bib0024
  article-title: Handwritten devanagari manuscript characters recognition using capsnet
  publication-title: Int J Cognit Comput Eng
– volume: 34
  start-page: 1469
  issue: 8
  year: 2012
  ident: 10.1016/j.compeleceng.2025.110533_bib0009
  article-title: Handwritten chinese text recognition by integrating multiple contexts
  publication-title: IEEE Trans Pattern Anal Mach Intell
  doi: 10.1109/TPAMI.2011.264
– volume: 6
  start-page: 136
  issue: 2
  year: 2025
  ident: 10.1016/j.compeleceng.2025.110533_bib0029
  article-title: TeluguScriptify: A custom deep learning model for handwritten Telugu text recognition and tool development
  publication-title: SN Comput Sci
  doi: 10.1007/s42979-025-03677-z
– volume: 21
  issue: 8
  year: 2021
  ident: 10.1016/j.compeleceng.2025.110533_bib0033
  article-title: An efficient anomaly recognition framework using an attention residual LSTM in surveillance videos
  publication-title: Sensors
  doi: 10.3390/s21082811
– volume: 11
  start-page: 28856
  year: 2023
  ident: 10.1016/j.compeleceng.2025.110533_bib0035
  article-title: Region-of-interest aware 3D ResNet for classification of COVID-19 chest computerised tomography scans
  publication-title: IEEE Access
  doi: 10.1109/ACCESS.2023.3260632
– volume: 8
  start-page: 23011
  year: 2020
  ident: 10.1016/j.compeleceng.2025.110533_bib0021
  article-title: Handwritten Arabic optical character recognition approach based on hybrid whale optimization algorithm with neighborhood rough set
  publication-title: IEEE Access
  doi: 10.1109/ACCESS.2020.2970438
– volume: 17
  start-page: 7965
  issue: 6
  year: 2020
  ident: 10.1016/j.compeleceng.2025.110533_bib0032
  article-title: Handwritten Devanagari character recognition using deep learning-convolutional neural network (CNN) model
  publication-title: PalArch's J Archaeol Egypt/Egyptol
– volume: 30
  start-page: 767
  issue: 5
  year: 2008
  ident: 10.1016/j.compeleceng.2025.110533_bib0007
  article-title: Markov random field-based statistical character structure modeling for handwritten Chinese character recognition
  publication-title: IEEE Trans Pattern Anal Mach Intell
  doi: 10.1109/TPAMI.2007.70734
– volume: 13
  start-page: 2592
  issue: 5
  year: 2013
  ident: 10.1016/j.compeleceng.2025.110533_bib0039
  article-title: Mine blast algorithm: A new population based algorithm for solving constrained engineering optimization problems
  publication-title: Appl Soft Comput
  doi: 10.1016/j.asoc.2012.11.026
– volume: 7
  start-page: 102039
  year: 2019
  ident: 10.1016/j.compeleceng.2025.110533_bib0022
  article-title: Recognition of handwritten Chinese characters based on concept learning
  publication-title: IEEE Access
  doi: 10.1109/ACCESS.2019.2930799
– volume: 31
  start-page: 4637
  issue: 11
  year: 2020
  ident: 10.1016/j.compeleceng.2025.110533_bib0011
  article-title: Stroke sequence-dependent deep convolutional neural network for online handwritten Chinese character recognition
  publication-title: IEEE Trans Neural Netw Learn Syst
  doi: 10.1109/TNNLS.2019.2956965
– volume: 11
  start-page: 33682
  year: 2023
  ident: 10.1016/j.compeleceng.2025.110533_bib0023
  article-title: An enhanced prototypical network architecture for few-shot handwritten Urdu character recognition
  publication-title: IEEE Access
  doi: 10.1109/ACCESS.2023.3263721
– volume: 13
  start-page: 413
  issue: 1
  year: 2023
  ident: 10.1016/j.compeleceng.2025.110533_bib0037
  article-title: Customized mask region based convolutional neural networks for un-uniformed shape text detection and text recognition
  publication-title: Int J Electr Comp Eng (IjECE)
  doi: 10.11591/ijece.v13i1.pp413-424
– volume: 22
  issue: 2
  year: 2019
  ident: 10.1016/j.compeleceng.2025.110533_bib0028
  article-title: Deep belief network based approach to recognize handwritten Kannada characters using distributed average of gradients
  publication-title: Cluster Comput
– volume: 9
  start-page: 125540
  year: 2021
  ident: 10.1016/j.compeleceng.2025.110533_bib0038
  article-title: Detection and location of safety protective wear in power substation operation using wear-enhanced YOLOv3 algorithm
  publication-title: IEEE Access
  doi: 10.1109/ACCESS.2021.3104731
– volume: 51
  start-page: 1531
  year: 2021
  ident: 10.1016/j.compeleceng.2025.110533_bib0040
  article-title: Archimedes optimization algorithm: a new metaheuristic algorithm for solving optimization problems
  publication-title: Appl Intell
  doi: 10.1007/s10489-020-01893-z
– volume: 7
  start-page: 960
  issue: 2
  year: 2020
  ident: 10.1016/j.compeleceng.2025.110533_bib0013
  article-title: SmartHandwriting: handwritten Chinese character recognition with Smartwatch
  publication-title: IEEE Internet Things J
  doi: 10.1109/JIOT.2019.2947448
– volume: 36
  start-page: 5887
  year: 2021
  ident: 10.1016/j.compeleceng.2025.110533_bib0041
  article-title: Artificial gorilla troops optimizer: a new nature-inspired metaheuristic algorithm for global optimization problems
  publication-title: Int J Intell Syst
  doi: 10.1002/int.22535
– volume: 6
  start-page: 10603
  year: 2018
  ident: 10.1016/j.compeleceng.2025.110533_bib0006
  article-title: Multilingual character segmentation and recognition schemes for Indian document images
  publication-title: IEEE Access
  doi: 10.1109/ACCESS.2018.2795104
– volume: 174
  year: 2025
  ident: 10.1016/j.compeleceng.2025.110533_bib0018
  article-title: Heuristic-aided fusion serial cascaded deep network for handwritten character recognition from handwritten images using optimization strategy
  publication-title: Appl Soft Comput
  doi: 10.1016/j.asoc.2025.112937
SSID ssj0004618
Score 2.3821943
Snippet Handwritten character recognition through automated techniques is one of the recent innovations in the industry, as it helps in interpreting historical...
SourceID crossref
elsevier
SourceType Index Database
Publisher
StartPage 110533
SubjectTerms Adaptive Yolov5
Convolutional neural networks with res-attention-long short-term memory layer
Enhanced Chef-Based Optimization Algorithm
Telugu handwritten character segmentation and classification
Title Developing adaptive Yolov5-based Telugu handwritten character segmentation and classification framework using Enhanced Chef-Based Optimization Algorithm and Deep Learning Networks
URI https://dx.doi.org/10.1016/j.compeleceng.2025.110533
Volume 126
WOSCitedRecordID wos001521399700003&url=https%3A%2F%2Fcvtisr.summon.serialssolutions.com%2F%23%21%2Fsearch%3Fho%3Df%26include.ft.matches%3Dt%26l%3Dnull%26q%3D
hasFullText 1
inHoldings 1
isFullTextHit
isPrint
journalDatabaseRights – providerCode: PRVESC
  databaseName: Elsevier SD Freedom Collection Journals 2021
  issn: 0045-7906
  databaseCode: AIEXJ
  dateStart: 19950101
  customDbUrl:
  isFulltext: true
  dateEnd: 99991231
  titleUrlDefault: https://www.sciencedirect.com
  omitProxy: false
  ssIdentifier: ssj0004618
  providerName: Elsevier
link http://cvtisr.summon.serialssolutions.com/2.0.0/link/0/eLvHCXMwtV3ZjtMwFLVKByF4QGwjhk1G4i1KlSZO3EjzUoYiNg1IU1B5ihzHaTtqM1G3mU_hP_hBrrfEwyJAiJeoihrbyjmxr6_OuUboWc4B5jIq_IBB-EbysvBTAd-ViGNYrxijTKktPr2jx8eDyST90Ol8sV6Y3YJW1eDiIq3_K9RwD8CW1tm_gLtpFG7AbwAdrgA7XP8I-BetDYoVrFbSoM8wxe1iXy5ZhTcWi-1068mU-flqvoGgWdp_ddlmby2mS2NH0jJlLsNrqScyqkQr5vK2KsswqmZaQ3A0E6X_XHXwHjpdGn-nN1xMz6CX2dKInkVta7pOpdtYNrV2I2R7zMRakVKf0qOIJNrKiU1aiMmj6lROt-e9na9apg9rZtxuJz03sRHGjazOZNus46aVN6kZnMgSm0FyaQbXpvsfVgOdmDiVYNZyvDDQnuxJeh9iXX_ju2LbJ7J92TxEhgGBrdgVtBdS2HR10d7w9WjyxvHc9vUqb8ZzDT1ttYO_6PDnsY8Tz4xvoZtmI4KHmkC3UUdUd9ANpzzlXfS1pRK2VMIulbCmEnaohBsqYZdKGP6BL1MJN1TCikrYUgm3VMIulXBDJdWapBK2VMKWSvfQx5ej8dEr3xzy4fMwoRs_JGXAYwjLI55z0Y_KOOFE5ITDjYjHJM95Dq-OkwJWn2BAi76ISA5RaSISmhQk2kfd6qwS9xEOQxZQGvTzMuWElwnjIaehILyfEk5JeYBC-_qzWtdyyazI8TRzMMskZpnG7AAdWqAyE5TqYDMDlv3-8Qf_9vhDdL39NB6h7ma1FY_RVb7bzNerJ4aT3wAgT8MK
linkProvider Elsevier
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=Developing+adaptive+Yolov5-based+Telugu+handwritten+character+segmentation+and+classification+framework+using+Enhanced+Chef-Based+Optimization+Algorithm+and+Deep+Learning+Networks&rft.jtitle=Computers+%26+electrical+engineering&rft.au=Sastry%2C+M.+Kiran&rft.au=Aparna%2C+S.&rft.date=2025-08-01&rft.pub=Elsevier+Ltd&rft.issn=0045-7906&rft.volume=126&rft_id=info:doi/10.1016%2Fj.compeleceng.2025.110533&rft.externalDocID=S0045790625004768
thumbnail_l http://covers-cdn.summon.serialssolutions.com/index.aspx?isbn=/lc.gif&issn=0045-7906&client=summon
thumbnail_m http://covers-cdn.summon.serialssolutions.com/index.aspx?isbn=/mc.gif&issn=0045-7906&client=summon
thumbnail_s http://covers-cdn.summon.serialssolutions.com/index.aspx?isbn=/sc.gif&issn=0045-7906&client=summon