Accès libre

Smoothing vs. sharpening of colour images: Together or separated

Cristina Pérez-Benito
Cristina Pérez-Benito
, 
Samuel Morillas
Samuel Morillas
, 
Cristina Jordán
Cristina Jordán
 et 
J. Alberto Conejero
J. Alberto Conejero
   | 30 juin 2017
Applied Mathematics and Nonlinear Sciences's Cover Image
À propos de cet article
Article précédent
Article suivant
Citez
Publié en ligne: 30 juin 2017
Pages: 299 - 316
Reçu: 16 févr. 2017
Accepté: 30 juin 2017
DOI: https://doi.org/10.21042/AMNS.2017.1.00025
Mots clés
© 2017 Cristina Pérez-Benito, Samuel Morillas, Cristina Jordán, J. Alberto Conejero, published by Sciendo
This work is licensed under the Creative Commons Attribution-NonCommercial-NoDerivatives 3.0 License.

Fig. 1

Results under different smoothing methods applied to Lenna image corrupted by a Gaussian noise with standard deviation σ = 10.
Results under different smoothing methods applied to Lenna image corrupted by a Gaussian noise with standard deviation σ = 10.

Fig. 2

Results under different smoothing methods applied to Parrots image corrupted by a Gaussian noise with standard deviation σ = 20.
Results under different smoothing methods applied to Parrots image corrupted by a Gaussian noise with standard deviation σ = 20.

Fig. 3

Histogram of a gray-scale image of Lenna and the histogram of the resulting image after having applied HE.
Histogram of a gray-scale image of Lenna and the histogram of the resulting image after having applied HE.

Fig. 4

Comparation between a gray-scale image of Lenna and the resulting image after having applied HE.
Comparation between a gray-scale image of Lenna and the resulting image after having applied HE.

Fig. 5

Comparation between HE applied over RGB channels separately and over L channel in Lab space.
Comparation between HE applied over RGB channels separately and over L channel in Lab space.

Fig. 6

Original image of Lenna and the output images obtained after applying BPDFHE and CLAHE methods.
Original image of Lenna and the output images obtained after applying BPDFHE and CLAHE methods.

Fig. 7

First row, original Parrot image, filtered with UM and with CLAHE. Second row, a little detail region.
First row, original Parrot image, filtered with UM and with CLAHE. Second row, a little detail region.

Fig. 8

First row, original image, original image blurred with Gaussian noise with σ = 10, filtered image with BF and finally ouput of BF and posterior CLAHE. Second row, original and noisy image, the enhanced image with CLAHE and finally output of CLAHE and posterior BF.
First row, original image, original image blurred with Gaussian noise with σ = 10, filtered image with BF and finally ouput of BF and posterior CLAHE. Second row, original and noisy image, the enhanced image with CLAHE and finally output of CLAHE and posterior BF.

Fig. 9

First row, original images and original images blurred with Gaussian noise with σ = 10. Second row, the result of applying CLAHE and subsequently BF to both images and then the opposite approach, BF and subsequently CLAHE.
First row, original images and original images blurred with Gaussian noise with σ = 10. Second row, the result of applying CLAHE and subsequently BF to both images and then the opposite approach, BF and subsequently CLAHE.

Fig. 10

Denoising results for Lenna image corrupted by Gaussian noise with standard deviation σ = 20.
Denoising results for Lenna image corrupted by Gaussian noise with standard deviation σ = 20.

Fig. 11

Results of smoothing & sharpening with different methods an image corrupted by Gaussian noise with σ = 30.
Results of smoothing & sharpening with different methods an image corrupted by Gaussian noise with σ = 30.

Fig. 12

First row, Lenna image corrupted by Gaussian noise with standard deviations σ = 10, σ = 20 and σ = 30. Second row, the output of Fuzzy Network filter. Third row, output of BM3DShar and in the last one, the output of TeD-FAB.
First row, Lenna image corrupted by Gaussian noise with standard deviations σ = 10, σ = 20 and σ = 30. Second row, the output of Fuzzy Network filter. Third row, output of BM3DShar and in the last one, the output of TeD-FAB.
eISSN:
2444-8656
Langue:
Anglais
Périodicité:
2 fois par an
Sujets de la revue:
Life Sciences, other, Mathematics, Applied Mathematics, General Mathematics, Physics
RSS Feed de la revue