Method for the recovery of indexed images in databases from visual content

The techniques of content-based image recovery (CBIR) provide a solution to a problem of information retrieval that may arise as follows: from an image of interest to recover or obtain similar images from among those present in a large collection, using only features or features extracted from said...

Full description

Autores:
amelec, viloria
Varela Izquierdo, Noel
Vargas, Jesús
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:11323/7276
Acceso en línea:
https://hdl.handle.net/11323/7276
https://repositorio.cuc.edu.co/
Palabra clave:
Convolutional neural networks
Global descriptors
Image retrieval
Information retrieval
Rights
closedAccess
License
Attribution-NonCommercial-NoDerivatives 4.0 International
id RCUC2_7bfceba2a1c326a741096d72e1678d80
oai_identifier_str oai:repositorio.cuc.edu.co:11323/7276
network_acronym_str RCUC2
network_name_str REDICUC - Repositorio CUC
repository_id_str
dc.title.spa.fl_str_mv Method for the recovery of indexed images in databases from visual content
title Method for the recovery of indexed images in databases from visual content
spellingShingle Method for the recovery of indexed images in databases from visual content
Convolutional neural networks
Global descriptors
Image retrieval
Information retrieval
title_short Method for the recovery of indexed images in databases from visual content
title_full Method for the recovery of indexed images in databases from visual content
title_fullStr Method for the recovery of indexed images in databases from visual content
title_full_unstemmed Method for the recovery of indexed images in databases from visual content
title_sort Method for the recovery of indexed images in databases from visual content
dc.creator.fl_str_mv amelec, viloria
Varela Izquierdo, Noel
Vargas, Jesús
Pineda, Omar
dc.contributor.author.spa.fl_str_mv amelec, viloria
Varela Izquierdo, Noel
Vargas, Jesús
Pineda, Omar
dc.subject.spa.fl_str_mv Convolutional neural networks
Global descriptors
Image retrieval
Information retrieval
topic Convolutional neural networks
Global descriptors
Image retrieval
Information retrieval
description The techniques of content-based image recovery (CBIR) provide a solution to a problem of information retrieval that may arise as follows: from an image of interest to recover or obtain similar images from among those present in a large collection, using only features or features extracted from said images Banuchitra and Kungumaraj (Int J Eng Comput Sci (IJECS) 5 (2016) [1]). Similar images are understood as those in which the same object or scene is observed with variations in perspective, lighting conditions or scale. The stored images are preprocessed and then their corresponding descriptors are indexed. The query image is also preprocessed to extract its descriptor, which is then compared to those stored by applying appropriate similarity measures, which allow the recovery of those images that are similar to the query image. In the present work, a method was developed for the recovery of indexed images in databases from their visual content, without the need to make textual annotations. Feature vectors were obtained from visual contents using artificial neural network techniques with deep learning.
publishDate 2020
dc.date.accessioned.none.fl_str_mv 2020-11-12T17:33:39Z
dc.date.available.none.fl_str_mv 2020-11-12T17:33:39Z
dc.date.issued.none.fl_str_mv 2020
dc.date.embargoEnd.none.fl_str_mv 2021-01-31
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/11323/7276
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/11323/7276
https://repositorio.cuc.edu.co/
dc.language.iso.none.fl_str_mv eng
language eng
dc.relation.references.spa.fl_str_mv Banuchitra S, Kungumaraj K (2016) A comprehensive survey of content based image retrieval techniques. Int J Eng Comput Sci (IJECS) 5 (2016). https://ezproxy.cuc.edu.co:2067/10.18535/ijecs/v5i8.26. https://www.ijecs.in
Simonyan K, Zisserman A (2014) Very deep convolutional networks for large-scale image recognition. arXiv preprint arXiv:1409.1556
Szegedy C, Liu W, Jia Y, Sermanet P, Reed SE, Anguelov D, Erhan D, Vanhoucke V, Rabinovich A (2014) Going Deeper with Convolutions. CoRR, abs/1409.4842. http://arxiv.org/abs/1409.4842
Szegedy C, Vanhoucke V, Ioffe S, Shlens J, Wojna Z (2016) Rethinking the inception architecture for computer vision. In: Proceedings of the IEEE conference on computer vision and pattern recognition, pp 2818–2826
Satish Tunga D, Jayadevappa D, Gururaj. C (2015) A comparative study of content based image retrieval trends and approaches. Int J Image Proc (IJIP) 9(3):127
Tzelepi M, Tefas A (2018) Deep convolutional learning for content based image retrieval. Neuro-computing 275:2467–2478
Vakhitov A, Kuzmin A, Lempitsky V (2016) Internet-based image retrieval using end-to-end trained deep distributions. arXiv preprint arXiv:1612.07697
Chen L, Zhang Y, Song ZL, Miao Z (2013) Automatic web services classification based on rough set theory. J Central South Univ 20:2708–2714
Pineda Lezama O, Gómez Dorta R (2017) Techniques of multivariate statistical analysis: an application for the Honduran banking sector. Innovare: J Sci Technol 5(2):61–75
Viloria A, Lis-Gutiérrez JP, Gaitán-Angulo M, Godoy ARM, Moreno GC, Kamatkar SJ (2018) Methodology for the design of a student pattern recognition tool to facilitate the teaching—learning process through knowledge data discovery (big data). In: Tan Y, Shi Y, Tang Q (eds) Data mining and big data. DMBD 2018. Lecture notes in computer science, vol 10943. Springer, Cham
Zhu F et al (2009) IBM Cloud computing powering a smarter planet. Libro Cloud Computing, Volumen 599.51/2009, pp 621–625
Mohanty R, Ravi V, Patra MR (2010) Web-services classification using intelligent techniques. Expert Syst Appl 37(7):5484–5490
Thames L, Schaefer D (2016) Softwaredefined cloud manufacturing for industry 4.0. Procedía CIRP, 52:12–17
Viloria A, Neira-Rodado D, Lezama OBP (2019) Recovery of scientific data using intelligent distributed data warehouse. ANT/EDI40 1249–1254
Schweidel DA, Knox G (2013) Incorporating direct marketing activity into latent attrition models. Mark Sci 31(3):471–487
Setnes M, Kaymak U (2001) Fuzzy modeling of client preference from large data sets: an application to target selection in direct marketing. Fuzzy Syst, IEEE Trans 9(1):153–163
Viloria A, Lezama OBP (2019) Improvements for determining the number of clusters in k-means for innovation databases in SMEs. ANT/EDI40 1201–1206
Nisa R, Qamar U (2014) A text mining based approach for web service classification. Inf Syst e-Business Manage 1–18
Wu J, Chen L, Zheng Z, Lyu MR, Wu Z (2014) Clustering web services to facilitate service discovery. Knowl Inf Syst 38(1):207–229
Alderson J (2015) A markerless motion capture technique for sport performance analysis and injury prevention: toward a big data, machine learning future. J Sci Med Sport 19:e79. https://ezproxy.cuc.edu.co:2067/10.1016/j.jsams.2015.12.192
Alcalá R, Alcalá-Fdez J, Herrera F (2007) A proposal for the genetic lateral tuning of linguistic fuzzy systems and its interaction with rule selection. IEEE Trans Fuzzy Syst 15(4):616–635
Elsaid A, Salem R, Abdul-Kader H (2017) A dynamic stakeholder classification and prioritization based on hybrid rough-fuzzy method. J Software Eng 11:143–159
Molina R, Calle FR, Gazzano JD, Petrino R, Lopez JCL (2019) Implementation of search process for a content-based image retrieval application on system on chip. In: 2019 X southern conference on programmable logic (SPL). IEEE, pp 97–102
Maur HK, Faridkot P, Jain, P (2019) Content based image retrieval system using K-means clustering algorithm and SVM classifier technique
Pothoff WJ, Price TG, Prasolov V (2020) U.S. Patent No. 10,565,070. U.S. Patent and Trademark Office, Washington, DC
Poplawska J, Labib A, Reed DM, Ishizaka A (2015) Stakeholder profile definition and salience measurement with fuzzy logic and visual analytics applied to corporate social responsibility case study. J Clean Prod 105:103–115. https://ezproxy.cuc.edu.co:2067/10.1016/j.jclepro.2014.10.095
Paulin M et al (2017) Convolutional patch representations for image retrieval: an unsupervised approach. Int J Comput Vis 165–166
Chandrasekhar V, Lin J, Liao Q, Morere O, Veillard A, Duan L, Poggio T (2017) Compression of deep neural networks for image instance retrieval. arXiv preprint arXiv:1701.04923
Zhang T, Qi G-J, Tang J, Wang J (2015) Sparse composite quantization. In: Proceedings of the IEEE conference on computer vision and pattern recognition, pp 4548–4556
Gong Y, Wang L, Guo R, Lazebnik S (2014) Multi-scale orderless pooling of deep convolutional activation features. In: European conference on computer vision. Springer, pp 392–407
Jegou H, Perronnin F, Douze M, Sanchez J, Perez P, Schmid C (2012) Aggregating local image descriptors into compact codes. IEEE Trans Pattern Anal Mach Intell 34(9):1704–1716
Perronnin F, Larlus D (2015) Fisher vectors meet neural networks: a hybrid classification architecture. In: Proceedings of the IEEE conference on computer vision and pattern recognition, pp 3743–3752
Jegou H, Zisserman A (2014) Triangulation embedding and democratic aggregation for image search. In: Proceedings of the IEEE conference on computer vision and pattern recognition, pp 3310–3317
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/inward/record.uri?eid=2-s2.0-85090096092&doi=10.1007%2f978-981-15-6876-3_40&partnerID=40&md5=b1a210aefb1d5c3ecab03113a88361a6
bitstream.url.fl_str_mv https://repositorio.cuc.edu.co/bitstreams/e0dff2a5-f7bb-456a-b20b-3e761819c905/download
https://repositorio.cuc.edu.co/bitstreams/7dc75141-0fba-4be3-95ef-27fd826a065b/download
https://repositorio.cuc.edu.co/bitstreams/ecb59d60-dc1a-453e-9623-822377ae3762/download
https://repositorio.cuc.edu.co/bitstreams/93d1b016-f184-4cd2-8882-96a2785fdc59/download
https://repositorio.cuc.edu.co/bitstreams/30843c87-0a48-4ec2-b101-a450c47b79d2/download
bitstream.checksum.fl_str_mv 4460e5956bc1d1639be9ae6146a50347
e30e9215131d99561d40d6b0abbe9bad
826aa3a325f18192e9f21f330bc1906b
308606f6676e1cde3b8dcba4daaedf8a
e62376da717472052789c98c3bc402d7
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_ 1828166864381935616
spelling amelec, viloriaVarela Izquierdo, NoelVargas, JesúsPineda, Omar2020-11-12T17:33:39Z2020-11-12T17:33:39Z20202021-01-312194-5357https://hdl.handle.net/11323/7276Corporación Universidad de la CostaREDICUC - Repositorio CUChttps://repositorio.cuc.edu.co/The techniques of content-based image recovery (CBIR) provide a solution to a problem of information retrieval that may arise as follows: from an image of interest to recover or obtain similar images from among those present in a large collection, using only features or features extracted from said images Banuchitra and Kungumaraj (Int J Eng Comput Sci (IJECS) 5 (2016) [1]). Similar images are understood as those in which the same object or scene is observed with variations in perspective, lighting conditions or scale. The stored images are preprocessed and then their corresponding descriptors are indexed. The query image is also preprocessed to extract its descriptor, which is then compared to those stored by applying appropriate similarity measures, which allow the recovery of those images that are similar to the query image. In the present work, a method was developed for the recovery of indexed images in databases from their visual content, without the need to make textual annotations. Feature vectors were obtained from visual contents using artificial neural network techniques with deep learning.amelec, viloria-will be generated-orcid-0000-0003-2673-6350-600Varela Izquierdo, Noel-will be generated-orcid-0000-0001-7036-4414-600Vargas, JesúsPineda, 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/inward/record.uri?eid=2-s2.0-85090096092&doi=10.1007%2f978-981-15-6876-3_40&partnerID=40&md5=b1a210aefb1d5c3ecab03113a88361a6Convolutional neural networksGlobal descriptorsImage retrievalInformation retrievalMethod for the recovery of indexed images in databases from visual contentPre-Publicaciónhttp://purl.org/coar/resource_type/c_816bTextinfo:eu-repo/semantics/preprinthttp://purl.org/redcol/resource_type/ARTOTRinfo:eu-repo/semantics/acceptedVersionBanuchitra S, Kungumaraj K (2016) A comprehensive survey of content based image retrieval techniques. Int J Eng Comput Sci (IJECS) 5 (2016). https://ezproxy.cuc.edu.co:2067/10.18535/ijecs/v5i8.26. https://www.ijecs.inSimonyan K, Zisserman A (2014) Very deep convolutional networks for large-scale image recognition. arXiv preprint arXiv:1409.1556Szegedy C, Liu W, Jia Y, Sermanet P, Reed SE, Anguelov D, Erhan D, Vanhoucke V, Rabinovich A (2014) Going Deeper with Convolutions. CoRR, abs/1409.4842. http://arxiv.org/abs/1409.4842Szegedy C, Vanhoucke V, Ioffe S, Shlens J, Wojna Z (2016) Rethinking the inception architecture for computer vision. In: Proceedings of the IEEE conference on computer vision and pattern recognition, pp 2818–2826Satish Tunga D, Jayadevappa D, Gururaj. C (2015) A comparative study of content based image retrieval trends and approaches. Int J Image Proc (IJIP) 9(3):127Tzelepi M, Tefas A (2018) Deep convolutional learning for content based image retrieval. Neuro-computing 275:2467–2478Vakhitov A, Kuzmin A, Lempitsky V (2016) Internet-based image retrieval using end-to-end trained deep distributions. arXiv preprint arXiv:1612.07697Chen L, Zhang Y, Song ZL, Miao Z (2013) Automatic web services classification based on rough set theory. J Central South Univ 20:2708–2714Pineda Lezama O, Gómez Dorta R (2017) Techniques of multivariate statistical analysis: an application for the Honduran banking sector. Innovare: J Sci Technol 5(2):61–75Viloria A, Lis-Gutiérrez JP, Gaitán-Angulo M, Godoy ARM, Moreno GC, Kamatkar SJ (2018) Methodology for the design of a student pattern recognition tool to facilitate the teaching—learning process through knowledge data discovery (big data). In: Tan Y, Shi Y, Tang Q (eds) Data mining and big data. DMBD 2018. Lecture notes in computer science, vol 10943. Springer, ChamZhu F et al (2009) IBM Cloud computing powering a smarter planet. Libro Cloud Computing, Volumen 599.51/2009, pp 621–625Mohanty R, Ravi V, Patra MR (2010) Web-services classification using intelligent techniques. Expert Syst Appl 37(7):5484–5490Thames L, Schaefer D (2016) Softwaredefined cloud manufacturing for industry 4.0. Procedía CIRP, 52:12–17Viloria A, Neira-Rodado D, Lezama OBP (2019) Recovery of scientific data using intelligent distributed data warehouse. ANT/EDI40 1249–1254Schweidel DA, Knox G (2013) Incorporating direct marketing activity into latent attrition models. Mark Sci 31(3):471–487Setnes M, Kaymak U (2001) Fuzzy modeling of client preference from large data sets: an application to target selection in direct marketing. Fuzzy Syst, IEEE Trans 9(1):153–163Viloria A, Lezama OBP (2019) Improvements for determining the number of clusters in k-means for innovation databases in SMEs. ANT/EDI40 1201–1206Nisa R, Qamar U (2014) A text mining based approach for web service classification. Inf Syst e-Business Manage 1–18Wu J, Chen L, Zheng Z, Lyu MR, Wu Z (2014) Clustering web services to facilitate service discovery. Knowl Inf Syst 38(1):207–229Alderson J (2015) A markerless motion capture technique for sport performance analysis and injury prevention: toward a big data, machine learning future. J Sci Med Sport 19:e79. https://ezproxy.cuc.edu.co:2067/10.1016/j.jsams.2015.12.192Alcalá R, Alcalá-Fdez J, Herrera F (2007) A proposal for the genetic lateral tuning of linguistic fuzzy systems and its interaction with rule selection. IEEE Trans Fuzzy Syst 15(4):616–635Elsaid A, Salem R, Abdul-Kader H (2017) A dynamic stakeholder classification and prioritization based on hybrid rough-fuzzy method. J Software Eng 11:143–159Molina R, Calle FR, Gazzano JD, Petrino R, Lopez JCL (2019) Implementation of search process for a content-based image retrieval application on system on chip. In: 2019 X southern conference on programmable logic (SPL). IEEE, pp 97–102Maur HK, Faridkot P, Jain, P (2019) Content based image retrieval system using K-means clustering algorithm and SVM classifier techniquePothoff WJ, Price TG, Prasolov V (2020) U.S. Patent No. 10,565,070. U.S. Patent and Trademark Office, Washington, DCPoplawska J, Labib A, Reed DM, Ishizaka A (2015) Stakeholder profile definition and salience measurement with fuzzy logic and visual analytics applied to corporate social responsibility case study. J Clean Prod 105:103–115. https://ezproxy.cuc.edu.co:2067/10.1016/j.jclepro.2014.10.095Paulin M et al (2017) Convolutional patch representations for image retrieval: an unsupervised approach. Int J Comput Vis 165–166Chandrasekhar V, Lin J, Liao Q, Morere O, Veillard A, Duan L, Poggio T (2017) Compression of deep neural networks for image instance retrieval. arXiv preprint arXiv:1701.04923Zhang T, Qi G-J, Tang J, Wang J (2015) Sparse composite quantization. In: Proceedings of the IEEE conference on computer vision and pattern recognition, pp 4548–4556Gong Y, Wang L, Guo R, Lazebnik S (2014) Multi-scale orderless pooling of deep convolutional activation features. In: European conference on computer vision. Springer, pp 392–407Jegou H, Perronnin F, Douze M, Sanchez J, Perez P, Schmid C (2012) Aggregating local image descriptors into compact codes. IEEE Trans Pattern Anal Mach Intell 34(9):1704–1716Perronnin F, Larlus D (2015) Fisher vectors meet neural networks: a hybrid classification architecture. In: Proceedings of the IEEE conference on computer vision and pattern recognition, pp 3743–3752Jegou H, Zisserman A (2014) Triangulation embedding and democratic aggregation for image search. In: Proceedings of the IEEE conference on computer vision and pattern recognition, pp 3310–3317PublicationCC-LICENSElicense_rdflicense_rdfapplication/rdf+xml; charset=utf-8805https://repositorio.cuc.edu.co/bitstreams/e0dff2a5-f7bb-456a-b20b-3e761819c905/download4460e5956bc1d1639be9ae6146a50347MD52LICENSElicense.txtlicense.txttext/plain; charset=utf-83196https://repositorio.cuc.edu.co/bitstreams/7dc75141-0fba-4be3-95ef-27fd826a065b/downloade30e9215131d99561d40d6b0abbe9badMD53ORIGINALMETHOD FOR THE RECOVERY OF INDEXED IMAGES IN DATABASES FROM VISUAL CONTENT.pdfMETHOD FOR THE RECOVERY OF INDEXED IMAGES IN DATABASES FROM VISUAL CONTENT.pdfapplication/pdf6620https://repositorio.cuc.edu.co/bitstreams/ecb59d60-dc1a-453e-9623-822377ae3762/download826aa3a325f18192e9f21f330bc1906bMD51THUMBNAILMETHOD FOR THE RECOVERY OF INDEXED IMAGES IN DATABASES FROM VISUAL CONTENT.pdf.jpgMETHOD FOR THE RECOVERY OF INDEXED IMAGES IN DATABASES FROM VISUAL CONTENT.pdf.jpgimage/jpeg47991https://repositorio.cuc.edu.co/bitstreams/93d1b016-f184-4cd2-8882-96a2785fdc59/download308606f6676e1cde3b8dcba4daaedf8aMD54TEXTMETHOD FOR THE RECOVERY OF INDEXED IMAGES IN DATABASES FROM VISUAL CONTENT.pdf.txtMETHOD FOR THE RECOVERY OF INDEXED IMAGES IN DATABASES FROM VISUAL CONTENT.pdf.txttext/plain1414https://repositorio.cuc.edu.co/bitstreams/30843c87-0a48-4ec2-b101-a450c47b79d2/downloade62376da717472052789c98c3bc402d7MD5511323/7276oai:repositorio.cuc.edu.co:11323/72762024-09-17 14:19:25.009http://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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