Retinal image enhancement via a multiscale morphological approach with OCCO filter.

Retinal images are widely used for diagnosis and eye disease detection. However, due to the acquisition process, retinal images often have problems such as low contrast, blurry details or artifacts. These problems may severely affect the diagnosis. Therefore, it is very impor tant to enhance the vis...

Descripció completa

Guardat en:
Dades bibliogràfiques
Autor principal: Mello Román, Julio César (author)
Altres autors: Vázquez Noguera, José Luis (author), García Torres, Miguel (author), Castillo, Veronica Elisa (author), Castro Matto, Ingrid (author)
Format: article
Idioma:anglès
Publicat: 2020
Matèries:
Accés en línia:http://hdl.handle.net/20.500.14066/3797
Etiquetes: Afegir etiqueta
Sense etiquetes, Sigues el primer a etiquetar aquest registre!
_version_ 1870612072881979392
author Mello Román, Julio César
author2 Vázquez Noguera, José Luis
García Torres, Miguel
Castillo, Veronica Elisa
Castro Matto, Ingrid
author2_role author
author
author
author
author_browse Castillo, Veronica Elisa
Castro Matto, Ingrid
García Torres, Miguel
Mello Román, Julio César
Vázquez Noguera, José Luis
author_facet Mello Román, Julio César
Vázquez Noguera, José Luis
García Torres, Miguel
Castillo, Veronica Elisa
Castro Matto, Ingrid
author_role author
bitstream.checksum.fl_str_mv b504faa21a83742a693862d4c8fa242f
858b22fda432bd774e469302988c1974
3c1fc99d1854f7a6d743680049fa6438
bitstream.checksumAlgorithm.fl_str_mv MD5
MD5
MD5
bitstream.url.fl_str_mv http://repositorio.conacyt.gov.py/bitstream/20.500.14066/3797/1/PINV18-846art1.pdf
http://repositorio.conacyt.gov.py/bitstream/20.500.14066/3797/2/license.txt
http://repositorio.conacyt.gov.py/bitstream/20.500.14066/3797/3/PINV18-846art1.pdf.txt
dc.contributor.other.es.fl_str_mv Universidad Nacional de Concepción - Facultad de Medicina (PY)
Universidad Pablo de Olavide (ES)
dc.creator.none.fl_str_mv Mello Román, Julio César
Vázquez Noguera, José Luis
García Torres, Miguel
Castillo, Veronica Elisa
Castro Matto, Ingrid
dc.date.accessioned.none.fl_str_mv 2022-04-29T23:13:33Z
dc.date.available.none.fl_str_mv 2022-04-29T23:13:33Z
dc.date.issued.none.fl_str_mv 2020
dc.identifier.doi.es.fl_str_mv 10.1007/978-3-030-68285-9_18
dc.identifier.uri.none.fl_str_mv http://hdl.handle.net/20.500.14066/3797
dc.language.iso.es.fl_str_mv eng
dc.relation.projectCONACYT.es.fl_str_mv PINV18-846
dc.rights.accessRights.es.fl_str_mv info:eu-repo/semantics/openAccess
dc.subject.classification.es.fl_str_mv 1303 I+D en relación con las Ciencias médicas
dc.subject.other.es.fl_str_mv RETINAL IMAGES
CONTRAST ENHANCEMENT
MATHEMATICAL MOR PHOLOGY
TOP-HAT TRANSFORM
dc.title.es.fl_str_mv Retinal image enhancement via a multiscale morphological approach with OCCO filter.
dc.type.es.fl_str_mv info:eu-repo/semantics/article
info:eu-repo/semantics/publishedVersion
description Retinal images are widely used for diagnosis and eye disease detection. However, due to the acquisition process, retinal images often have problems such as low contrast, blurry details or artifacts. These problems may severely affect the diagnosis. Therefore, it is very impor tant to enhance the visual quality of such images. Contrast enhancement is a pre-processing applied to images to improve their visual quality. This technique betters the identification of retinal structures in degraded reti nal images. In this work, a novel algorithm based on multi-scale mathe matical morphology is presented. First, the original image is blurred us ing the Open-Close Close-Open (OCCO) filter to reduce any artifacts in the image. Next, multiple bright and dark features are extracted from the filtered image by the Top-Hat transform. Finally, the maximum bright values are added to the original image and the maximum dark values are subtracted from the original image, previously adjusted by a weight. The algorithm was tested on 397 retinal images from the public STARE database. The proposed algorithm was compared with state of the art al gorithms and results show that the proposal is more efficient in improving contrast, maintaining similarity with the original image and introducing less distortion than the other algorithms. According to ophthalmologists, the algorithm, by improving retinal images, provides greater clarity in the blood vessels of the retina and would facilitate the identification of pathologies.
eu_rights_str_mv openAccess
format article
id CONACYT_e36e7f1d9c81285ad80628d47ab615fb
identifier_str_mv 10.1007/978-3-030-68285-9_18
language eng
network_acronym_str CONACYT
network_name_str Repositorio Institucional CONACYT
oai_identifier_str oai:repositorio.conacyt.gov.py:20.500.14066/3797
publishDate 2020
publishDateSort 2020
repository.mail.fl_str_mv repositorio.institucional@conacyt.gov.py
repository.name.fl_str_mv Repositorio Institucional CONACYT
repository_id_str
spelling 11bddad9-f33b-43c9-8169-2cb6feaa29de6001144600386292aa-adcb-4977-a6aa-08b85eb571e060084782119-1768-4c44-838e-440839f303d8600e22e0e61-768d-40bd-8ba2-641719f6ac1a600Universidad Nacional de Concepción - Facultad de Medicina (PY)Universidad Pablo de Olavide (ES)2022-04-29T23:13:33Z2022-04-29T23:13:33Z2020http://hdl.handle.net/20.500.14066/379710.1007/978-3-030-68285-9_18Retinal images are widely used for diagnosis and eye disease detection. However, due to the acquisition process, retinal images often have problems such as low contrast, blurry details or artifacts. These problems may severely affect the diagnosis. Therefore, it is very impor tant to enhance the visual quality of such images. Contrast enhancement is a pre-processing applied to images to improve their visual quality. This technique betters the identification of retinal structures in degraded reti nal images. In this work, a novel algorithm based on multi-scale mathe matical morphology is presented. First, the original image is blurred us ing the Open-Close Close-Open (OCCO) filter to reduce any artifacts in the image. Next, multiple bright and dark features are extracted from the filtered image by the Top-Hat transform. Finally, the maximum bright values are added to the original image and the maximum dark values are subtracted from the original image, previously adjusted by a weight. The algorithm was tested on 397 retinal images from the public STARE database. The proposed algorithm was compared with state of the art al gorithms and results show that the proposal is more efficient in improving contrast, maintaining similarity with the original image and introducing less distortion than the other algorithms. According to ophthalmologists, the algorithm, by improving retinal images, provides greater clarity in the blood vessels of the retina and would facilitate the identification of pathologies.Consejo Nacional de Ciencia y TecnologíaPROCIENCIAeng1303 I+D en relación con las Ciencias médicasRETINAL IMAGESCONTRAST ENHANCEMENTMATHEMATICAL MOR PHOLOGYTOP-HAT TRANSFORMRetinal image enhancement via a multiscale morphological approach with OCCO filter.info:eu-repo/semantics/articleinfo:eu-repo/semantics/publishedVersion186Information Technology and SystemsPINV18-846info:eu-repo/semantics/openAccess177Mello Román, Julio CésarVázquez Noguera, José LuisGarcía Torres, MiguelCastillo, Veronica ElisaCastro Matto, IngridORIGINALPINV18-846art1.pdfPINV18-846art1.pdfPINV18-846art1application/pdf1417664http://repositorio.conacyt.gov.py/bitstream/20.500.14066/3797/1/PINV18-846art1.pdfb504faa21a83742a693862d4c8fa242fMD51LICENSElicense.txtlicense.txttext/plain; charset=utf-81698http://repositorio.conacyt.gov.py/bitstream/20.500.14066/3797/2/license.txt858b22fda432bd774e469302988c1974MD52TEXTPINV18-846art1.pdf.txtPINV18-846art1.pdf.txtExtracted texttext/plain20475http://repositorio.conacyt.gov.py/bitstream/20.500.14066/3797/3/PINV18-846art1.pdf.txt3c1fc99d1854f7a6d743680049fa6438MD5320.500.14066/3797oai:repositorio.conacyt.gov.py:20.500.14066/37972026-02-12 19:30:32.318Repositorio Institucional CONACYTrepositorio.institucional@conacyt.gov.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
spellingShingle Retinal image enhancement via a multiscale morphological approach with OCCO filter.
Mello Román, Julio César
1303 I+D en relación con las Ciencias médicas
RETINAL IMAGES
CONTRAST ENHANCEMENT
MATHEMATICAL MOR PHOLOGY
TOP-HAT TRANSFORM
status_str publishedVersion
title Retinal image enhancement via a multiscale morphological approach with OCCO filter.
title_full Retinal image enhancement via a multiscale morphological approach with OCCO filter.
title_fullStr Retinal image enhancement via a multiscale morphological approach with OCCO filter.
title_full_unstemmed Retinal image enhancement via a multiscale morphological approach with OCCO filter.
title_short Retinal image enhancement via a multiscale morphological approach with OCCO filter.
title_sort Retinal image enhancement via a multiscale morphological approach with OCCO filter.
topic 1303 I+D en relación con las Ciencias médicas
RETINAL IMAGES
CONTRAST ENHANCEMENT
MATHEMATICAL MOR PHOLOGY
TOP-HAT TRANSFORM
url http://hdl.handle.net/20.500.14066/3797