A q-extension of sigmoid functions and the application for enhancement of ultrasound images

dc.contributor.authorRodrigues P.S.
dc.contributor.authorWachs-Lopes G.
dc.contributor.authorSantos R.M.
dc.contributor.authorColtri E.
dc.contributor.authorGiraldi G.A.
dc.date.accessioned2019-08-17T20:00:30Z
dc.date.available2019-08-17T20:00:30Z
dc.date.issued2019
dc.description.abstract© 2019 by the authors.This paper proposes the q-sigmoid functions, which are variations of the sigmoid expressions and an analysis of their application to the process of enhancing regions of interest in digital images. These new functions are based on the non-extensive Tsallis statistics, arising in the field of statistical mechanics through the use of q-exponential functions. The potential of q-sigmoids for image processing is demonstrated in tasks of region enhancement in ultrasound images which are highly affected by speckle noise. Before demonstrating the results in real images, we study the asymptotic behavior of these functions and the effect of the obtained expressions when processing synthetic images. In both experiments, the q-sigmoids overcame the original sigmoid functions, as well as two other well-known methods for the enhancement of regions of interest: slicing and histogram equalization. These results show that q-sigmoids can be used as a preprocessing step in pipelines including segmentation as demonstrated for the Otsu algorithm and deep learning approaches for further feature extractions and analyses.
dc.description.abstractalternativeThis paper proposes the q-sigmoid functions, which are variations of the sigmoid expressions and an analysis of their application to the process of enhancing regions of interest in digital images. These new functions are based on the non-extensive Tsallis statistics, arising in the field of statistical mechanics through the use of q-exponential functions. The potential of q-sigmoids for image processing is demonstrated in tasks of region enhancement in ultrasound images which are highly affected by speckle noise. Before demonstrating the results in real images, we study the asymptotic behavior of these functions and the effect of the obtained expressions when processing synthetic images. In both experiments, the q-sigmoids overcame the original sigmoid functions, as well as two other well-known methods for the enhancement of regions of interest: slicing and histogram equalization. These results show that q-sigmoids can be used as a preprocessing step in pipelines including segmentation as demonstrated for the Otsu algorithm and deep learning approaches for further feature extractions and analysesen
dc.description.firstpage1
dc.description.issuenumber4
dc.description.lastpage21
dc.description.volume21
dc.identifier.citationRodrigues, Paulo; LOPES, Guilherme; SANTOS, R. M.; COLTRI, E.; GIRALDI, G. A. A q-Extension of sigmoid functions and the application for enhancement of ultrasound images. Entropy, v. 21, n. 4, p. 1-21, 2019.
dc.identifier.doi10.3390/e21040430
dc.identifier.issn1099-4300
dc.identifier.urihttps://repositorio.fei.edu.br/handle/FEI/1013
dc.identifier.urlhttps://www.mdpi.com/1099-4300/21/4/430
dc.relation.ispartofEntropy
dc.rightsAcesso Aberto
dc.rights.licenseEste é um artigo publicado em acesso aberto sob uma licença Creative Commons (CC BY 4.0). Fonte:<https://creativecommons.org/licenses/by/4.0/>. Acesso em: 22 out 2019
dc.subject.otherlanguageContrast enhancement
dc.subject.otherlanguageQ-exponential
dc.subject.otherlanguageQ-Gaussian
dc.subject.otherlanguageQ-sigmoid
dc.subject.otherlanguageSigmoid
dc.subject.otherlanguageTsallis statistics
dc.subject.otherlanguageUltra-sound images
dc.titleA q-extension of sigmoid functions and the application for enhancement of ultrasound images
dc.typeArtigo
fei.scopus.citations8
fei.scopus.eid2-s2.0-85065580282
fei.scopus.updated2024-03-04
fei.scopus.urlhttps://www.scopus.com/inward/record.uri?partnerID=HzOxMe3b&scp=85065580282&origin=inward
Arquivos
Pacote Original
Agora exibindo 1 - 1 de 1
Carregando...
Imagem de Miniatura
Nome:
RI_1013.pdf
Tamanho:
1.43 MB
Formato:
Adobe Portable Document Format
Coleções