Image reconstruction by means of F-transform

Perfilieva, Irina; Vlašánek, Pavel

doi:10.1016/j.knosys.2014.04.007

Cited by 28 publications

(15 citation statements)

References 16 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…For future re- search, we would like to extend the idea for heuristic and probability estimation of the reconstructed part specifically aimed to medical usage. [10]; d) i) n) image inpainted by Navier-Stokes [8]; e) j) o) image inpainted by FMM [9].…”

Section: Resultsmentioning

confidence: 99%

“…We propose a fuzzy based approach to solve image inpainting task [10]. Let us describe fuzzy transform (Ftransform) [11] given by a fuzzy partition satisfying following definition.…”

Section: F-transformmentioning

confidence: 99%

“…According to formula (8), the computation takes particular component F kl and spread it to the appropriate region of O with respect to A k and B l . For details see [10].…”

Section: F-transformmentioning

confidence: 99%

“…This algorithm works well for photos [12,13,10,14] but not so sufficiently for low depth color images. The reason is in isotropic nature of the algorithm where different regions are mixed together in the inpainted area Ω.…”

Section: F-transformmentioning

confidence: 99%

“…Let us compare the novel technique with basic principle of the enhanced diffusion idea [10], Navier-Stokes [8] and FMM [9]. The various outputs can be seen in Fig.…”

Section: Qualitative Comparisonmentioning

confidence: 99%

See 4 more Smart Citations

Fuzzy image inpainting aimed to medical images

Vlašánek¹

2018

WSCG 2018 - Full Papers Proceedings

Self Cite

View full text Add to dashboard Cite

This paper focuses on a reconstruction of low color depth images using fuzzy mathematics. For demonstration purposes, we chose medical images taken from magnetic resonance imaging (MRI) and computed tomography (CT). The proposed technique is based on idea of diffusion where pixels surrounding damaged region are used to determine the corrupted ones. As it is illustrated, the classical diffusion techniques are not so effective. In the paper, we describe the reason why and propose the solution in a form of the new algorithm. The algorithm is demonstrated and visually compared with another ones.

show abstract

Section: Resultsmentioning

confidence: 99%

“…We propose a fuzzy based approach to solve image inpainting task [10]. Let us describe fuzzy transform (Ftransform) [11] given by a fuzzy partition satisfying following definition.…”

Section: F-transformmentioning

confidence: 99%

“…According to formula (8), the computation takes particular component F kl and spread it to the appropriate region of O with respect to A k and B l . For details see [10].…”

Section: F-transformmentioning

confidence: 99%

Section: F-transformmentioning

confidence: 99%

“…Let us compare the novel technique with basic principle of the enhanced diffusion idea [10], Navier-Stokes [8] and FMM [9]. The various outputs can be seen in Fig.…”

Section: Qualitative Comparisonmentioning

confidence: 99%

See 3 more Smart Citations