Recognition of handwritten digits by image processing methods and classification models

OCR (Optical Character Recognition) is a line of research within image processing for which many techniques and methodologies have been developed. Set of pixels recognized based on the digitalized image and this study presents an iterative process that consists of five phases of the OCR. For this pu...

Full description

Autores:
amelec, viloria
Rico, Reinaldo
Pineda, Omar
Tipo de recurso:
http://purl.org/coar/resource_type/c_816b
Fecha de publicación:
2020
Institución:
Corporación Universidad de la Costa
Repositorio:
REDICUC - Repositorio CUC
Idioma:
eng
OAI Identifier:
oai:repositorio.cuc.edu.co:11323/7271
Acceso en línea:
https://hdl.handle.net/11323/7271
https://repositorio.cuc.edu.co/
Palabra clave:
Classification models
Genetic algorithm
Image processing
Methods
Recognition of handwritten digits
Rights
closedAccess
License
Attribution-NonCommercial-NoDerivatives 4.0 International
id RCUC2_8dba36c44bf5ffaf5c1a0b1dc164611c
oai_identifier_str oai:repositorio.cuc.edu.co:11323/7271
network_acronym_str RCUC2
network_name_str REDICUC - Repositorio CUC
repository_id_str
dc.title.spa.fl_str_mv Recognition of handwritten digits by image processing methods and classification models
title Recognition of handwritten digits by image processing methods and classification models
spellingShingle Recognition of handwritten digits by image processing methods and classification models
Classification models
Genetic algorithm
Image processing
Methods
Recognition of handwritten digits
title_short Recognition of handwritten digits by image processing methods and classification models
title_full Recognition of handwritten digits by image processing methods and classification models
title_fullStr Recognition of handwritten digits by image processing methods and classification models
title_full_unstemmed Recognition of handwritten digits by image processing methods and classification models
title_sort Recognition of handwritten digits by image processing methods and classification models
dc.creator.fl_str_mv amelec, viloria
Rico, Reinaldo
Pineda, Omar
dc.contributor.author.spa.fl_str_mv amelec, viloria
Rico, Reinaldo
Pineda, Omar
dc.subject.spa.fl_str_mv Classification models
Genetic algorithm
Image processing
Methods
Recognition of handwritten digits
topic Classification models
Genetic algorithm
Image processing
Methods
Recognition of handwritten digits
description OCR (Optical Character Recognition) is a line of research within image processing for which many techniques and methodologies have been developed. Set of pixels recognized based on the digitalized image and this study presents an iterative process that consists of five phases of the OCR. For this purpose, several image processing methods are applied, as well as two variable selection methods, and several supervised automated learning methods are explored. Among the classification models, those of deep learning stand out for their novelty and enormous potential.
publishDate 2020
dc.date.accessioned.none.fl_str_mv 2020-11-11T22:46:13Z
dc.date.available.none.fl_str_mv 2020-11-11T22:46:13Z
dc.date.issued.none.fl_str_mv 2020
dc.date.embargoEnd.none.fl_str_mv 2021-05-07
dc.type.spa.fl_str_mv Pre-Publicación
dc.type.coar.spa.fl_str_mv http://purl.org/coar/resource_type/c_816b
dc.type.content.spa.fl_str_mv Text
dc.type.driver.spa.fl_str_mv info:eu-repo/semantics/preprint
dc.type.redcol.spa.fl_str_mv http://purl.org/redcol/resource_type/ARTOTR
dc.type.version.spa.fl_str_mv info:eu-repo/semantics/acceptedVersion
format http://purl.org/coar/resource_type/c_816b
status_str acceptedVersion
dc.identifier.issn.spa.fl_str_mv 2194-5357
dc.identifier.uri.spa.fl_str_mv https://hdl.handle.net/11323/7271
dc.identifier.instname.spa.fl_str_mv Corporación Universidad de la Costa
dc.identifier.reponame.spa.fl_str_mv REDICUC - Repositorio CUC
dc.identifier.repourl.spa.fl_str_mv https://repositorio.cuc.edu.co/
identifier_str_mv 2194-5357
Corporación Universidad de la Costa
REDICUC - Repositorio CUC
url https://hdl.handle.net/11323/7271
https://repositorio.cuc.edu.co/
dc.language.iso.none.fl_str_mv eng
language eng
dc.relation.references.spa.fl_str_mv Boufenar, C., Kerboua, A., Batouche, M.: Investigation on deep learning for off-line handwritten Arabic character recognition. Cogn. Syst. Res. 50, 180–195 (2018)
Dasgupta, J., Bhattacharya, K., Chanda, B.: A holistic approach for Off-line handwritten cursive word recognition using directional feature based on Arnold transform. Pattern Recogn. Lett. 79, 73–79 (2016)
Jangid, M., Srivastava, S.: Handwritten devanagari character recognition using layer-wise training of deep convolutional neural networks and adaptive gradient methods. J. Imaging 4(2), 41 (2018)
Tarawneh, A.S., Hassanat, A.B., Chetverikov, D., Lendak, I., Verma, C.: Invoice classification using deep features and machine learning techniques. In: 2019 IEEE Jordan International Joint Conference on Electrical Engineering and Information Technology (JEEIT), pp. 855–859. IEEE, April 2019
Niu, X.X., Suen, C.Y.: A novel hybrid CNN–SVM classifier for recognizing handwritten digits. Pattern Recogn. 45(4), 1318–1325 (2012)
Wang, Z., Wang, R., Gao, J., Gao, Z., Liang, Y.: Fault recognition using an ensemble classifier based on Dempster-Shafer Theory. Pattern Recogn. 99, 107079 (2020)
Zhou, B., Ghose, T., Lukowicz, P.: Expressure: detect expressions related to emotional and cognitive activities using forehead textile pressure mechanomyography. Sensors 20(3), 730 (2020)
Schmidhuber, J.: Deep learning in neural networks: an overview. Neural Netw. 61, 85–117 (2015)
Mohiuddin, K., Mao, J.: A comparative study of different classifiers for handprinted character recognition. Pattern Recogn. Practice IV, 437–448 (2014)
Le Cun, Y., Cortes, C.: MNIST handwritten digit database. AT&T Labs. http://yann.lecun.com/exdb/mnist. Accessed: 20 Dec 2019
Viloria, A., Acuña, G.C., Franco, D.J.A., Hernández-Palma, H., Fuentes, J.P., Rambal, E.P.: Integration of data mining techniques to PostgreSQL database manager system. Procedia Comput. Sci. 155, 575–580 (2019)
Viloria, A., Lezama, O.B.P.: Improvements for determining the number of clusters in k-means for innovation databases in SMEs. ANT/EDI40, pp. 1201–1206 (2019)
Varela, N., Silva, J., Gonzalez, F.M., Palencia, P., Palma, H.H., Pineda, O.B.: Method for the recovery of images in databases of rice grains from visual content. Procedia Comput. Sci. 170, 983–988 (2020)
Koresh, M.H.J.D., Deva, J.: Computer vision based traffic sign sensing for smart transport. J. Innov. Image Process. (JIIP) 1(01), 11–19 (2019)
Zhang, B., Fu, M., Yan, H.: A nonlinear neural network model of mixture of local principal component analysis: application to handwritten digits recognition. Pattern Recogn. 34(2), 203–214 (2001)
Ghosh, A., Pavate, A., Gholam, V., Shenoy, G., Mahadik, S.: Steady model for classification of handwritten digit recognition. In: Sharma, R., Mishra, M., Nayak, J., Naik, B., Pelusi, D. (eds.) Innovation in Electrical Power Engineering, Communication, and Computing Technology. LNEE, vol. 630, pp. 401–412. Springer, Singapore (2020). https://ezproxy.cuc.edu.co:2067/10.1007/978-981-15-2305-2_32
Garg, A., Gupta, D., Saxena, S., Sahadev, P.P.: Validation of random dataset using an efficient CNN model trained on MNIST handwritten dataset. In: 2019 6th International Conference on Signal Processing and Integrated Networks (SPIN), pp. 602–606. IEEE, March 2019
El-Sawy, A., Hazem, E.B., Loey, M.: CNN for handwritten arabic digits recognition based on LeNet-5. In: International Conference on Advanced Intelligent Systems and Informatics, pp. 566–575. Springer, Cham, October 2016
Paul, O.: Image pre-processing on NumtaDB for Bengali handwritten digit recognition. In: 2018 International Conference on Bangla Speech and Language Processing (ICBSLP), pp. 1–6. IEEE, September 2018
Shamsuddin, M.R., Abdul-Rahman, S., Mohamed, A.: Exploratory analysis of MNIST handwritten digit for machine learning modelling. In: International Conference on Soft Computing in Data Science, pp. 134–145. Springer, Singapore, August 2018
Pujari, P., Majhi, B.: Recognition of Odia handwritten digits using gradient based feature extraction method and clonal selection algorithm. Int. J. Rough Sets Data Anal. (IJRSDA) 6(2), 19–33 (2019)
Shawon, A., Rahman, M.J.U., Mahmud, F., Zaman, M.A.: Bangla handwritten digit recognition using deep CNN for large and unbiased dataset. In: 2018 International Conference on Bangla Speech and Language Processing (ICBSLP), pp. 1–6. IEEE, September 2018
Makkar, T., Kumar, Y., Dubey, A.K., Rocha, Á., Goyal, A.: Analogizing time complexity of KNN and CNN in recognizing handwritten digits. In: 2017 Fourth International Conference on Image Information Processing (ICIIP), pp. 1–6. IEEE, December 2017
Rizvi, M., Raza, H., Tahzeeb, S., Jaffry, S.: Optical character recognition based intelligent database management system for examination process control. In: 2019 16th International Bhurban Conference on Applied Sciences and Technology (IBCAST), pp. 500–507. IEEE, January 2019
dc.rights.spa.fl_str_mv Attribution-NonCommercial-NoDerivatives 4.0 International
dc.rights.uri.spa.fl_str_mv http://creativecommons.org/licenses/by-nc-nd/4.0/
dc.rights.accessrights.spa.fl_str_mv info:eu-repo/semantics/closedAccess
dc.rights.coar.spa.fl_str_mv http://purl.org/coar/access_right/c_14cb
rights_invalid_str_mv Attribution-NonCommercial-NoDerivatives 4.0 International
http://creativecommons.org/licenses/by-nc-nd/4.0/
http://purl.org/coar/access_right/c_14cb
eu_rights_str_mv closedAccess
dc.format.mimetype.spa.fl_str_mv application/pdf
dc.publisher.spa.fl_str_mv Corporación Universidad de la Costa
dc.source.spa.fl_str_mv Advances in Intelligent Systems and Computing
institution Corporación Universidad de la Costa
dc.source.url.spa.fl_str_mv https://www.scopus.com/record/display.uri?eid=2-s2.0-85089245515&doi=10.1007%2f978-3-030-51859-2_2&origin=inward&txGid=1f85feb85a61963014477b3db2a85ca2
bitstream.url.fl_str_mv https://repositorio.cuc.edu.co/bitstreams/35e72af5-4589-4662-88ed-ce70091885c5/download
https://repositorio.cuc.edu.co/bitstreams/1954a5cd-ee9a-45e1-93cb-23738e597009/download
https://repositorio.cuc.edu.co/bitstreams/a2fea821-51b1-44aa-a336-498ca89c749d/download
https://repositorio.cuc.edu.co/bitstreams/2608d7a2-6a11-4798-a1a4-378585117465/download
https://repositorio.cuc.edu.co/bitstreams/847b2060-fb16-4bde-9a8b-3a3c59583665/download
bitstream.checksum.fl_str_mv 901eebede791aea851a1d3253a9c28bd
4460e5956bc1d1639be9ae6146a50347
e30e9215131d99561d40d6b0abbe9bad
b393388ab08df34db63379346806ea40
248e9fdf6776b358ad557a6fb45f3589
bitstream.checksumAlgorithm.fl_str_mv MD5
MD5
MD5
MD5
MD5
repository.name.fl_str_mv Repositorio de la Universidad de la Costa CUC
repository.mail.fl_str_mv repdigital@cuc.edu.co
_version_ 1811760816068755456
spelling amelec, viloriaRico, ReinaldoPineda, Omar2020-11-11T22:46:13Z2020-11-11T22:46:13Z20202021-05-072194-5357https://hdl.handle.net/11323/7271Corporación Universidad de la CostaREDICUC - Repositorio CUChttps://repositorio.cuc.edu.co/OCR (Optical Character Recognition) is a line of research within image processing for which many techniques and methodologies have been developed. Set of pixels recognized based on the digitalized image and this study presents an iterative process that consists of five phases of the OCR. For this purpose, several image processing methods are applied, as well as two variable selection methods, and several supervised automated learning methods are explored. Among the classification models, those of deep learning stand out for their novelty and enormous potential.amelec, viloria-will be generated-orcid-0000-0003-2673-6350-600Rico, Reinaldo-will be generated-orcid-0000-0002-0730-4838-600Pineda, Omar-will be generated-orcid-0000-0002-8239-3906-600application/pdfengCorporación Universidad de la CostaAttribution-NonCommercial-NoDerivatives 4.0 Internationalhttp://creativecommons.org/licenses/by-nc-nd/4.0/info:eu-repo/semantics/closedAccesshttp://purl.org/coar/access_right/c_14cbAdvances in Intelligent Systems and Computinghttps://www.scopus.com/record/display.uri?eid=2-s2.0-85089245515&doi=10.1007%2f978-3-030-51859-2_2&origin=inward&txGid=1f85feb85a61963014477b3db2a85ca2Classification modelsGenetic algorithmImage processingMethodsRecognition of handwritten digitsRecognition of handwritten digits by image processing methods and classification modelsPre-Publicaciónhttp://purl.org/coar/resource_type/c_816bTextinfo:eu-repo/semantics/preprinthttp://purl.org/redcol/resource_type/ARTOTRinfo:eu-repo/semantics/acceptedVersionBoufenar, C., Kerboua, A., Batouche, M.: Investigation on deep learning for off-line handwritten Arabic character recognition. Cogn. Syst. Res. 50, 180–195 (2018)Dasgupta, J., Bhattacharya, K., Chanda, B.: A holistic approach for Off-line handwritten cursive word recognition using directional feature based on Arnold transform. Pattern Recogn. Lett. 79, 73–79 (2016)Jangid, M., Srivastava, S.: Handwritten devanagari character recognition using layer-wise training of deep convolutional neural networks and adaptive gradient methods. J. Imaging 4(2), 41 (2018)Tarawneh, A.S., Hassanat, A.B., Chetverikov, D., Lendak, I., Verma, C.: Invoice classification using deep features and machine learning techniques. In: 2019 IEEE Jordan International Joint Conference on Electrical Engineering and Information Technology (JEEIT), pp. 855–859. IEEE, April 2019Niu, X.X., Suen, C.Y.: A novel hybrid CNN–SVM classifier for recognizing handwritten digits. Pattern Recogn. 45(4), 1318–1325 (2012)Wang, Z., Wang, R., Gao, J., Gao, Z., Liang, Y.: Fault recognition using an ensemble classifier based on Dempster-Shafer Theory. Pattern Recogn. 99, 107079 (2020)Zhou, B., Ghose, T., Lukowicz, P.: Expressure: detect expressions related to emotional and cognitive activities using forehead textile pressure mechanomyography. Sensors 20(3), 730 (2020)Schmidhuber, J.: Deep learning in neural networks: an overview. Neural Netw. 61, 85–117 (2015)Mohiuddin, K., Mao, J.: A comparative study of different classifiers for handprinted character recognition. Pattern Recogn. Practice IV, 437–448 (2014)Le Cun, Y., Cortes, C.: MNIST handwritten digit database. AT&T Labs. http://yann.lecun.com/exdb/mnist. Accessed: 20 Dec 2019Viloria, A., Acuña, G.C., Franco, D.J.A., Hernández-Palma, H., Fuentes, J.P., Rambal, E.P.: Integration of data mining techniques to PostgreSQL database manager system. Procedia Comput. Sci. 155, 575–580 (2019)Viloria, A., Lezama, O.B.P.: Improvements for determining the number of clusters in k-means for innovation databases in SMEs. ANT/EDI40, pp. 1201–1206 (2019)Varela, N., Silva, J., Gonzalez, F.M., Palencia, P., Palma, H.H., Pineda, O.B.: Method for the recovery of images in databases of rice grains from visual content. Procedia Comput. Sci. 170, 983–988 (2020)Koresh, M.H.J.D., Deva, J.: Computer vision based traffic sign sensing for smart transport. J. Innov. Image Process. (JIIP) 1(01), 11–19 (2019)Zhang, B., Fu, M., Yan, H.: A nonlinear neural network model of mixture of local principal component analysis: application to handwritten digits recognition. Pattern Recogn. 34(2), 203–214 (2001)Ghosh, A., Pavate, A., Gholam, V., Shenoy, G., Mahadik, S.: Steady model for classification of handwritten digit recognition. In: Sharma, R., Mishra, M., Nayak, J., Naik, B., Pelusi, D. (eds.) Innovation in Electrical Power Engineering, Communication, and Computing Technology. LNEE, vol. 630, pp. 401–412. Springer, Singapore (2020). https://ezproxy.cuc.edu.co:2067/10.1007/978-981-15-2305-2_32Garg, A., Gupta, D., Saxena, S., Sahadev, P.P.: Validation of random dataset using an efficient CNN model trained on MNIST handwritten dataset. In: 2019 6th International Conference on Signal Processing and Integrated Networks (SPIN), pp. 602–606. IEEE, March 2019El-Sawy, A., Hazem, E.B., Loey, M.: CNN for handwritten arabic digits recognition based on LeNet-5. In: International Conference on Advanced Intelligent Systems and Informatics, pp. 566–575. Springer, Cham, October 2016Paul, O.: Image pre-processing on NumtaDB for Bengali handwritten digit recognition. In: 2018 International Conference on Bangla Speech and Language Processing (ICBSLP), pp. 1–6. IEEE, September 2018Shamsuddin, M.R., Abdul-Rahman, S., Mohamed, A.: Exploratory analysis of MNIST handwritten digit for machine learning modelling. In: International Conference on Soft Computing in Data Science, pp. 134–145. Springer, Singapore, August 2018Pujari, P., Majhi, B.: Recognition of Odia handwritten digits using gradient based feature extraction method and clonal selection algorithm. Int. J. Rough Sets Data Anal. (IJRSDA) 6(2), 19–33 (2019)Shawon, A., Rahman, M.J.U., Mahmud, F., Zaman, M.A.: Bangla handwritten digit recognition using deep CNN for large and unbiased dataset. In: 2018 International Conference on Bangla Speech and Language Processing (ICBSLP), pp. 1–6. IEEE, September 2018Makkar, T., Kumar, Y., Dubey, A.K., Rocha, Á., Goyal, A.: Analogizing time complexity of KNN and CNN in recognizing handwritten digits. In: 2017 Fourth International Conference on Image Information Processing (ICIIP), pp. 1–6. IEEE, December 2017Rizvi, M., Raza, H., Tahzeeb, S., Jaffry, S.: Optical character recognition based intelligent database management system for examination process control. In: 2019 16th International Bhurban Conference on Applied Sciences and Technology (IBCAST), pp. 500–507. IEEE, January 2019PublicationORIGINALRECOGNITION OF HANDWRITTEN DIGITS BY IMAGE PROCESSING METHODS AND CLASSIFICATION MODELS.pdfRECOGNITION OF HANDWRITTEN DIGITS BY IMAGE PROCESSING METHODS AND CLASSIFICATION MODELS.pdfapplication/pdf178862https://repositorio.cuc.edu.co/bitstreams/35e72af5-4589-4662-88ed-ce70091885c5/download901eebede791aea851a1d3253a9c28bdMD51CC-LICENSElicense_rdflicense_rdfapplication/rdf+xml; charset=utf-8805https://repositorio.cuc.edu.co/bitstreams/1954a5cd-ee9a-45e1-93cb-23738e597009/download4460e5956bc1d1639be9ae6146a50347MD52LICENSElicense.txtlicense.txttext/plain; charset=utf-83196https://repositorio.cuc.edu.co/bitstreams/a2fea821-51b1-44aa-a336-498ca89c749d/downloade30e9215131d99561d40d6b0abbe9badMD53THUMBNAILRECOGNITION OF HANDWRITTEN DIGITS BY IMAGE PROCESSING METHODS AND CLASSIFICATION MODELS.pdf.jpgRECOGNITION OF HANDWRITTEN DIGITS BY IMAGE PROCESSING METHODS AND CLASSIFICATION MODELS.pdf.jpgimage/jpeg37752https://repositorio.cuc.edu.co/bitstreams/2608d7a2-6a11-4798-a1a4-378585117465/downloadb393388ab08df34db63379346806ea40MD54TEXTRECOGNITION OF HANDWRITTEN DIGITS BY IMAGE PROCESSING METHODS AND CLASSIFICATION MODELS.pdf.txtRECOGNITION OF HANDWRITTEN DIGITS BY IMAGE PROCESSING METHODS AND CLASSIFICATION MODELS.pdf.txttext/plain862https://repositorio.cuc.edu.co/bitstreams/847b2060-fb16-4bde-9a8b-3a3c59583665/download248e9fdf6776b358ad557a6fb45f3589MD5511323/7271oai:repositorio.cuc.edu.co:11323/72712024-09-17 12:49:21.84http://creativecommons.org/licenses/by-nc-nd/4.0/Attribution-NonCommercial-NoDerivatives 4.0 Internationalopen.accesshttps://repositorio.cuc.edu.coRepositorio de la Universidad de la Costa CUCrepdigital@cuc.edu.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