Show simple item record

dc.contributor.authorCeballos, William Armandospa
dc.contributor.authorSalazar, Luis Eduardospa
dc.contributor.authorOviedo Carrascal, Ana Isabelspa
dc.date.accessioned2020-10-27T00:20:47Z
dc.date.available2020-10-27T00:20:47Z
dc.date.issued2009-06-01
dc.identifier.issn2539-2115
dc.identifier.issn1657-2831
dc.identifier.urihttp://hdl.handle.net/20.500.12749/8969
dc.description.abstractLa World Wide Web, o simplemente web, es un sistema lógico de acceso y búsqueda de información disponible en Internet cuyas unidades informativas son las páginas web. La web ha facilitado la publicación de gran cantidad de información accesible desde cualquier lugar del mundo; sin embargo, parte del contenido ofrecido como la pornografía, es considerado inapropiado para algunos usuarios.  Para aportar al filtrado de pornografía en la web, este trabajo propone el desarrollo de un clasificador de páginas web basado en la evaluación de las imágenes presentes en el contenido de la página. La evaluación de las imágenes es realizada en tres vías: extracción de características de las regiones de piel, análisis de textura y descriptores de forma de la imagen. Los tres tipos de evaluación del contenido de las imágenes son utilizados para entrenar tres clasificadores con máquinas de soporte vectorial (SVM). Los resultados de clasificación son unidos en un ensamble realizado por un metaclasificador por medio de la siguiente política: si al menos uno de los tres clasificadores concluye que la imagen es pornográfica, entonces la imagen es considerada como tal. Al evaluar todas las imágenes contenidas en una página web, se utiliza la siguiente política: si la página web presenta un porcentaje de imágenes pornográficas superior al 30%, entonces la página es considerada como pornográfica. La implementación realizada es evaluada sobre un conjunto de 5000 páginas web diversas, obteniendo una exactitud del 84.6 % en el reconocimiento de contenido pornográfico a través del contenido de las imágenes.spa
dc.format.mimetypeapplication/pdfspa
dc.language.isospaspa
dc.publisherUniversidad Autónoma de Bucaramanga UNAB
dc.relationhttps://revistas.unab.edu.co/index.php/rcc/article/view/1135/1105
dc.relation.urihttps://revistas.unab.edu.co/index.php/rcc/article/view/1135
dc.rightsDerechos de autor 2009 Revista Colombiana de Computación
dc.rights.urihttp://creativecommons.org/licenses/by-nc-sa/4.0/*
dc.sourceRevista Colombiana de Computación; Vol. 10 Núm. 1 (2009): Revista Colombiana de Computación; 26-44
dc.subjectClasificación de páginas web pornográficas
dc.subjectMáquinas de soporte vectorial
dc.subjectDetección de pornografía
dc.subjectAprendizaje supervisado
dc.subjectEspacios de color
dc.titleClasificador de páginas web pornográficas basado en el contenido de las imágenes
dc.title.translatedSorter of pornographic web pages based on the content of the imageseng
dc.type.driverinfo:eu-repo/semantics/article
dc.type.localArtículospa
dc.type.coarhttp://purl.org/coar/resource_type/c_7a1f
dc.subject.keywordsRating of pornographic websiteseng
dc.subject.keywordsVector support machineseng
dc.subject.keywordsDetection of pornographyeng
dc.subject.keywordsSupervised learningeng
dc.subject.keywordsColor spaceseng
dc.subject.keywordsPornographic web pages classificationeng
dc.subject.keywordsSupport vector machineseng
dc.subject.keywordsSupervised learningeng
dc.subject.keywordsColour spaceseng
dc.identifier.instnameinstname:Universidad Autónoma de Bucaramanga UNABspa
dc.type.hasversionInfo:eu-repo/semantics/publishedVersion
dc.rights.accessrightsinfo:eu-repo/semantics/openAccessspa
dc.relation.referencesL. L. Cao, X. L. Li, N. H. Yu, Z. K. Liu, “Naked People Retrieval Based on Adaboost Learning,” International Conference on Machine learning and Cybernetics vol. 2, pp. 1133 - 1138, 2002.
dc.relation.referencesY. Chan, R. Harvey, D. Smith, “Building systems to block pornography,” In Challenge of Image Retrieval, BCS Electronic Workshops in Computing series, pp. 34-40, 1999.
dc.relation.referencesH. D. Cheng, X. H. Jiang, Y. Sun, J. Wang, “Color image segmentation: advance and prospects,” Pattern Recognition 34, pp. 2259–2281, 2001.
dc.relation.referencesL. F. Costa and R. Cesar, “Shape Analysis and Classification:Theory and Practice,” CRC Press, cap 6, 2001.
dc.relation.referencesC. Cusano, C. Brambilla, R. Schettini, G. Ciocca, “On the Detection of pornographic digital images,” Visual Communications and Image Processing (VCIP2003), vol. 5150, pp. 2105-2113, 2003.
dc.relation.referencesL. Duan, G. Cui, W. Gao, H. Zhang, “Adult image detection method base-on skin colour model and support vector machine,” Asian Conference on Computer Vision, pp. 797-800, 2002
dc.relation.referencesM. Fleck, D. A. Forsyth, C. Bregler, “Finding Naked People,”Proceedings European Conference on Computer Vision andPattern Recognition, pp. 593-602, 1996
dc.relation.referencesM. R. Girgis, T. M. Mahmoud, Tarek, "An Approach to Image Extraction and Accurate Skin Detection from Web Pages," International Journal of Computer Science and Engineering,Vol 1, no. 2, pp. 88-96, 2007.
dc.relation.referencesR. C. González & R.E. Woods, “Digital Image Processing,” Prentice Hall, 2002.
dc.relation.referencesM. Hammami, Y. Chahir and L. Chen, "Webguard: Web based adult content detection and filtering system," in Proceedings of the International Conference on Web Intelligence (WI'2003), pp. 574 – 578, 2003.
dc.relation.referencesR.M. Haralick and K. Shantnugam and I. Dinstein. “Textural features for image classification”, IEEE Trans. SMC, vol 3 no 6, p610-6211. 97
dc.relation.referencesL. Hunt, The invention of pornography, Zone Books, New 42 William Armando Ceballos, Luis Eduardo Salazar y Ana Isabel Oviedo York, 1993.
dc.relation.referencesO. Ivanciuc “Aplications of Support Vector Machines in Chemistry,” In: Reviews in Computational Chemistry, Vol 23, Eds.:K.B. Lipkowitz and T.R. Cundari. Wiley-VCH, Weinheim, pp. 291-400, 2007
dc.relation.referencesS. Jayaram, S. Schmugge, M.C. Shin, L.V. Tsap, “Effect of Colour spa c e Tr ansforma tion, the Illuminanc e Component,and Colour Modelling on Skin Detection,”CVPR, pp. 813-818, 2004.
dc.relation.referencesF. Jiao, W. Gao, L. Duan, G. Cui, “Detecting Adult Image using Multiple Features,” International Conferences on Info-tech & Info-net 2001 (ICII 2001), vol. 3, pp. 378-383, 2001.
dc.relation.referencesT. Joachims, “Text categorization with support vector machines: learning with many relevant features”, en Proceedings of ECML-98, 10th European Conference on ML, number 1398 in Lecture Notes in Computer Science, Springer Verlag, Heidelberg, DE, 1998, pp.137-142.
dc.relation.referencesP. Kakumanu, S. Makrogiannis, N. Bourbakis, “A survey of skin-colour modelling and detection methods,” Pattern Recognition, vol. 40, pp. 1106-1122, 2007.
dc.relation.referencesW. Kelly, A. Donnellan, D. Molloy, "Areview of skin detection techniques for objectionable images," the 7th Information Technology and Telecommunication Conference, pp. 40- 49, 2007.
dc.relation.referencesI. Kunttu, L. Lepistö, J. Rauhamaa, A. Visa, “Multiscale Fourier Descriptor for Shape Classification,” Proceedings of 12th International Conference on Image Analysis and Processing, pp. 536-541, 2003
dc.relation.referencesJ.S. Lee, Y.M. Kuo, P.C. Chung, E.L.Chen, “Naked image detection based on adaptive and extensible skin colour model,”Pattern Recognition, vol. 40, Issue 8, pp.2261–2270,2006.
dc.relation.referencesK.M. Liang, S.D. Scott, M. Waqas, “Detecting pornographic images,” Asian Conference on Computer Vision ACCV, pp. 497-502, 2004
dc.relation.referencesB. S. Manjunath, J. R. Ohm, V. V. Vasudevan, A. Yamada, “Color and texture descriptors,” IEEE Trans. CSVT 11, vol 6, pp. 703–715, 2001.
dc.relation.referencesJ. S. Payne, L. Hepplewhite, T. J. Stonham, “Perceptually based metrics for the evaluation of textural image retrieval methods,” Multimedia Computing and Systems, IEEE International Conference on, vol 2, pp. 793-797, 1999.
dc.relation.referencesH. Rowley, Y.Jing, S. Baluja, “Large scale image-based adult43 Clasificador de Páginas Web Pornográficas Basado en el Contenido de las Imágenes content filtering”, VISAPP2006, pp. 290-296.
dc.relation.referencesJ. C. Russ, “The Image Processing Handbook,” 3rd ed., CRC Press, Boca Raton, FL
dc.relation.referencesF. Sebastiani, Machine Learning in Automated Text Categorization. En: ACM Computing Surveys, p.p 1-47, 2002.
dc.relation.referencesS. Sural, G. Qian, S. Pramanik, “Segmentation and histogram generation using the HSV color space for image retrieval,” Proceedings of the IEEE International Conference on Image Processing, IEEE, Rochester, pp. 589–592, 2002.
dc.relation.referencesJ. Z. Wang, J. Li, G. Wiederhold, O. Firschein, “System for Sc r e e n i n g O b j e c ti o n a b l e Ima g e s, ” Comp u t e r Communications Journal, vol. 21, no. 15, pp. 1355-1360, Elsevier, 1998.
dc.relation.referencesS. Xuanjing, W. Wei, Q. Qingji, “The Filtering of Internet Images Based on Detecting Erotogenic-part”, Natural Computation, 2007. ICNC 2007. Third International Conference on, Volume 2, 24-27 Aug. 2007 Page(s):732 – 736.
dc.relation.referencesQ. F. Zheng, M. J. Zhang, W. Q. Wang, “Shape-based Adult Images Detection,” Third International Conference on Image and Graphics ICIG2004, Hong Kong, China, pp. 150-153, 2004.
dc.relation.referencesH. Zhu, S. Zhou, J. Wang, Z. Yin, “An algorithm of pornographic image detection,” in Fourth International Conference on Image and Graphics, Sichuan, China, pp. 81-84, 2007.
dc.contributor.cvlacOviedo Carrascal, Ana Isabel [0000636550]spa
dc.contributor.googlescholarOviedo Carrascal, Ana Isabel [8P8UdrgAAAAJ]spa
dc.contributor.orcidOviedo Carrascal, Ana Isabel [0000-0002-7105-7819]spa
dc.contributor.researchgateOviedo Carrascal, Ana Isabel [Ana-Oviedo-Carrascal]spa
dc.subject.lembAprendizaje supervisadospa
dc.subject.lembMáquinas de vectores de soportespa
dc.subject.lembPornografíaspa
dc.subject.lembEspacios de colorspa
dc.subject.lembPaginas webspa
dc.identifier.repourlrepourl:https://repository.unab.edu.co
dc.description.abstractenglishThe World Wide Web, or web, is an information access and search logic system available on the Internet whose informative units are web pages. The web has facilitated the publication of big amount of information accessible from anywhere in the world; however, part of this content such as pornography is regarded inappropriate for some users. To contribute to the pornography filtering on web, this paper proposes the development of a web pages classifier based on the evaluation of the images present in the webpage content. The images evaluation is done in three ways: features extraction of skin regions, texture analysis and by the shape descriptors of the image. The three types of the images content evaluation are used to train three classifiers with Support Vector Machines (SVM). The results of the SVM classification are put together in an assembly made by a metaclassifier through the following policy: if at least one of the classifiers finds that the image is pornographic, then the image is regarded as such. When assessing all the images contained in a webpage, the next policy is applied: if the webpage present a percentage above 30%, then the webpage is regarded as pornographic. The implementation done is evaluated on a set of 5000 web pages with some information kinds, getting an accuracy of 84.6% in the recognition of pornographic content through the content of the images.eng
dc.subject.proposalClasificación de páginas web pornográficasspa
dc.subject.proposalMáquinas de soporte vectorialspa
dc.subject.proposalDetección de pornografíaspa
dc.subject.proposalAprendizaje supervisadospa
dc.subject.proposalespacios de colorSPA
dc.type.redcolhttp://purl.org/redcol/resource_type/CJournalArticle
dc.rights.creativecommonsAttribution-NonCommercial-ShareAlike 4.0 International*


Files in this item

Thumbnail

This item appears in the following Collection(s)

Show simple item record

Attribution-NonCommercial-ShareAlike 4.0 International
Except where otherwise noted, this item's license is described as Attribution-NonCommercial-ShareAlike 4.0 International