Structure tensor adaptive total variation for image restoration

Prasath, V. B. Surya; Thanh, Dang N. H.

doi:10.3906/elk-1802-76

Cited by 31 publications

(18 citation statements)

References 16 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…We notice a lack of edge continuity, see for example in the images -Brain, Grape, and Lena top of the cap region, this is due to the fact that the augmented multiscale gradient maps can obtain lower values due to small scale oscillation compared to the uniform background pixels. A remedy to this can be to augment other differential operators such as the structure tensor [10], [14] or higher order derivatives. Table 2 shows the Entropy and Pratt's figure of merit (FoM) metric for the test images considered here.…”

Section: A Setup Parameters and Error Metricsmentioning

confidence: 99%

Multiscale Gradient Maps Augmented Fisher Information-Based Image Edge Detection

et al. 2020

Self Cite

View full text Add to dashboard Cite

Image edge detection is an important task in image processing and pattern recognition. Edges in digital images signify image discontinuities and traditionally gradient information is utilized in finding possible edge pixels. In this work, we consider a fusion approach using multiscale gradient maps along with non-parametric Fisher information which is recently used in edge detection. By using multiscale gradient maps we obtain better edge localization and robust edge maps and local thresholding with Fisher information helps obtain better detection. Experimental results on a variety of digital images and performance evaluation undertaken in comparison with edge detectors from the literature show the advantage of the proposed approach.

show abstract

Section: A Setup Parameters and Error Metricsmentioning

confidence: 99%

Multiscale Gradient Maps Augmented Fisher Information-Based Image Edge Detection

et al. 2020

Self Cite

View full text Add to dashboard Cite

show abstract

“…In (10), the weight update is performed by the average of the square of the loss function gradient and the mean square M s of the previous weight. Furthermore, (11) uses the mean square value of the previous weight, loss function gradient with learning rate η and numerical stabiliser ϵ.…”

Section: Optimisation Algorithm and Cost Functionmentioning

confidence: 99%

“…Some of the recent spatial and transform domain methodologies are based on wavelet [8], total variation models [9, 10], robust block PCA [11], and fuzzy hysteresis smoothing [12]. Discrete wavelet transform (DWT) is a multi‐resolution analysis technique that uses a basis function and an appropriate thresholding operator on approximation and detail coefficients.…”

Section: Introductionmentioning

confidence: 99%

PReLU and edge‐aware filter‐based image denoiser using convolutional neural network

Thakur

Yadav

Gupta

2020

IET Image Processing

View full text Add to dashboard Cite

Convolutional neural networks (CNNs) based on the discriminative learning model have been widely used for image denoising. In this study, a feed-forward denoising CNN (DnCNN) with a parametric rectified linear unit (PReLU) is used to improve the denoising performance. PReLU enhances the model fitting of the DnCNN network without affecting computational cost. This network learns the leaky parameter of negative inputs in an activation function and therefore finds a proper slope in a negative direction. The proposed denoising network is based on residual learning, which comprises repeated convolutional and PReLU units along with batch normalisation. Residual learning with batch normalisation accelerates the network training, which can be used for blind Gaussian denoising. In this network, feature maps are processed by principal component analysis and transferred to subsequent convolution layers. An adaptive bilateral filter further processes the output image of the proposed CNN for image smoothening and sharpening. The mean and variance of the Gaussian kernel of adaptive filter vary from pixel to pixel. The performance of this network is analysed on BSD-68 and Set-12 datasets, and it exhibits an improvement in peak signal-to-noise ratio and structural similarity index metric and visual representation over other state-of-the-art methods.

show abstract

“…To compare the inpainting result of the proposed method to other similar inpainting methods, it is necessary to assess image quality after inpainting based on the error metrics. The popular error metrics are PSNR and SSIM that were used in many works [20,21,22,23,24,25,26,27]: = 10 log 10 2,…”

Section: Image Quality Assessment Metricsmentioning

confidence: 99%

An Adaptive Image Inpainting Method Based on the Weighted Mean

Hai

Hieu

Thanh

et al. 2019

IJCAI

View full text Add to dashboard Cite

Imaging inpainting is the process of digitally filling-in missing pixel values in images and requires carefully crafted image analysis tools. In this work, we propose an adaptive image inpainting method based on the weighted mean. The weighted mean is assessed to be better than the median because, for the case of the weighted mean, we can exclude the values of the corrupted pixels from evaluating values to fill those corrupted pixels. In the experiments, we implement the algorithm on an open dataset with various corrupted masks and we also compare the inpainting result by the proposed method to other similar inpainting methods-the harmonic inpainting method and the inpainting by directional median filtersto prove its own effectiveness to restore small, medium as well as fairly large corrupted regions. This comparison will be handled based on two of the most popular image quality assessment error metrics, such as the peak signal to noise ratio, and structural similarity. Further, since the proposed inpainting method is non-iterative, it is suitable for implementations to process big imagery that traditionally require higher computational costs, such as the large, high-resolution images or video sequences. Povzetek: Opisana je novo razvita metoda določanja manjkajočih točk v sliki s pomočjo uteženega povprečja.

show abstract

Structure tensor adaptive total variation for image restoration

Cited by 31 publications

References 16 publications

Multiscale Gradient Maps Augmented Fisher Information-Based Image Edge Detection

Multiscale Gradient Maps Augmented Fisher Information-Based Image Edge Detection

PReLU and edge‐aware filter‐based image denoiser using convolutional neural network

An Adaptive Image Inpainting Method Based on the Weighted Mean

Contact Info

Product

Resources

About