Adaptive shock filter for image super-resolution and enhancement

Xiao, Jinsheng; Pang, Guanlin; Zhang, Yongqin; Kuang, Yuli; Yan, Yunhui; Wang, Yixiang

doi:10.1016/j.jvcir.2016.06.015

Cited by 24 publications

(12 citation statements)

References 27 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…In this section, we will examine the efficiency of the AFSF model. Also, we compare the performance of the AFSF with four popular methods, ADSF, 22 Korn, 24 AADSF, 23 and ASF 21 . We use eight test images, seven real and one synthetic, listed as follows: Lena, Peppers, Woman, House, Cameraman, Lake, and Barbara and Crown synthetic image.…”

Section: Resultsmentioning

confidence: 99%

“…Xiao et al 21 proposed an adaptive shocking filtering (ASF) model as follows:

u_{t} = - false(1 - g false(false| u_{η} false| false) false) . \tanh false(G_{σ} * u_{η η} false) u_{η} + c_{ξ} u_{ξ ξ},

where

g false(x false) = \exp false(- \frac{x^{2}}{c_{η}} false)

is edging stop function and c ξ and c η are constants. This model is similar to previous models, and only the shock filter and diffusion coefficients have been changed.…”

Section: Related Workmentioning

confidence: 99%

“…In spite of reducing the staircase effect, this idea causes insufficient deblurring of the edges. Xiao et al 21 by replacing F ( s ) = sign ( s ) with

F false(s false) = \tanh false(s false)

have been tried to create a trade off between power of deblurring and reducing staircase effect, but their model does not change adaptively with respect to image features. Also, other models based on shock filter have been proposed to demonstrate this problem such as previous studies 22‐24 .…”

Section: Introductionmentioning

confidence: 99%

See 2 more Smart Citations

Image deblurring using adaptive fractional‐order shock filter

Irandoust‐pakchin

Babapour

Lakestani

2020

Math Methods in App Sciences

View full text Add to dashboard Cite

In this paper, a novel image enhancement model based on shock filter for image deblurring is proposed in three cases. For the weight of shock filter, the fractional‐order derivative of initial blurry image is used. This fractional‐order weight can be adjusted adaptively according to the gradient of blurred image. Compared with the traditional integer‐order shock filter, the proposed model creates less staircase effect, whereas the enhancement and deblurring of the resulted images are efficiently good. Stability properties of the proposed method are studied theoretically, and also to show the validity of stability studies results, some numerical experiments are presented. The three cases of proposed method are compared with together and with other methods. Different test images are used to show the validity of these cases. Numerical experiments confirm the efficiency of these cases.

show abstract

Section: Resultsmentioning

confidence: 99%

“…Xiao et al 21 proposed an adaptive shocking filtering (ASF) model as follows:

u_{t} = - false(1 - g false(false| u_{η} false| false) false) . \tanh false(G_{σ} * u_{η η} false) u_{η} + c_{ξ} u_{ξ ξ},

where

g false(x false) = \exp false(- \frac{x^{2}}{c_{η}} false)

is edging stop function and c ξ and c η are constants. This model is similar to previous models, and only the shock filter and diffusion coefficients have been changed.…”

Section: Related Workmentioning

confidence: 99%

“…In spite of reducing the staircase effect, this idea causes insufficient deblurring of the edges. Xiao et al 21 by replacing F ( s ) = sign ( s ) with

F false(s false) = \tanh false(s false)

Section: Introductionmentioning

confidence: 99%

See 1 more Smart Citation

Image deblurring using adaptive fractional‐order shock filter

Irandoust‐pakchin

Babapour

Lakestani

2020

Math Methods in App Sciences

View full text Add to dashboard Cite

show abstract

“…These PDE-based algorithms employed Anisotropic Diffusion (AD) [ 25 ], forward and backward Diffusion (FABD) [ 8 , 24 ] and Total Variation Regularization (TVR) [ 9 ]. In the proposed work, we utilize the shock filter [ 26 ] to achieve faster smoothing and sharpening in the image.…”

Section: Background and Motivationmentioning

confidence: 99%

“…We subsequently perform nonlinear smoothing to de-emphasize the roughness of the background texture while preserving the crack features. This is achieved using the adaptive shock filter algorithm proposed by Xiao et al [ 26 ].…”

Section: Proposed Approachesmentioning

confidence: 99%

Automated crack segmentation via saturation channel thresholding, area classification and fusion of modified level set segmentation with Canny edge detection

Nnolim

2020

Heliyon

View full text Add to dashboard Cite

Automatic detection of complex cracks on rough concrete surfaces via image processing is a challenging task. The most current effective methods involve deep learning schemes. These are usually computationally and structurally complex. Recently, relatively simplified algorithms were developed for effective segmentation of crack features. However, these approaches still could not consistently and accurately extract such features from extremely noisy images of rough concrete surfaces with complex crack patterns. This study describes crack feature segmentation algorithms based on wavelet coefficient adjustment, nonlinear filter pre-processing, saturation channel extraction, adaptive threshold-based edge detection and fuzzy clustering-based area classification. Additional modifications include a new energy function for active contour segmentation algorithm. Adaptive localized mask generation is also proposed for automatic region-based segmentation. Furthermore, a binary fusion stage is incorporated for improved edge feature extraction. The quantitative and visual evaluation of the proposed schemes show improvement in results compared to several recent state-of-the-art algorithms.

show abstract