A hybrid neuro-fuzzy filter for edge preserving restoration of images corrupted by impulse noise

Yüksel, Mehmet Emin

doi:10.1109/tip.2005.863941

Cited by 77 publications

(45 citation statements)

References 45 publications

Supporting

Mentioning

Contrasting

Unclassified

Order By: Relevance

“…But when the images are highly corrupted, discovering the rulebase structure becomes quite difficult. In order to overcome this difficult, many methods based on neuro-fuzzy system are proposed [19]- [23], which make full use of the ability of neural networks to learn from examples. With suitable and sufficient training, they can preserve the image details during noise removal.…”

mentioning

confidence: 99%

A Detection Statistic for Random-Valued Impulse Noise

Dong

Chan

2007

IEEE Trans. on Image Process.

248

176

View full text Add to dashboard Cite

This paper proposes an image statistic for detecting random-valued impulse noise. By this statistic, we can identify most of the noisy pixels in the corrupted images. Combining it with an edge-preserving regularization, we obtain a powerful two-stage method for denoising random-valued impulse noise even for noise level as high as 60%. Simulation results show that our method is significantly better than a number of existing techniques in terms of image restoration and noise detection. Index Termsrandom-valued impulse noise, noise detector, edge-preserving regularization, image denoising.

show abstract

mentioning

confidence: 99%

A Detection Statistic for Random-Valued Impulse Noise

Dong

Chan

2007

IEEE Trans. on Image Process.

248

176

View full text Add to dashboard Cite

show abstract

“…It can be extended into other fields such as archeology, Medical Image processing, Remote sensing etc. The existing system is available for reducing fat-tailed noise like impulse noise [35,36]. Median filter [37,38,39] and Low-pass filters are in job at present.…”

Section: Resultsmentioning

confidence: 99%

“…This comparative study mainly aims at Gaussian Noise [1,2] which is also good at removing other Noises like Impulsive [3,4] and Multiplicative Noise [5]. Impulsive Noise consists of random occurrences of energy spikes having random amplitude and spectral content.…”

Section: Introductionmentioning

confidence: 99%

A Comparative Study of Gaussian Noise Removal Methodologies for Gray Scale Images

Tulin¹

2017

IJCA

View full text Add to dashboard Cite

Image filtering is a technique to preserve important signal elements such as edges, smoothing the details of the image to make images appear clear and sharpener. Among all the non linear concepts to suppress Gaussian noise the fuzzy logic based approaches are important as they are capable of reasoning with vague and uncertain information. In this study, have made comparative study with the existing noise reduction methods where the images contaminated with Gaussian noise and found the best result by using fuzzy image filter with the help of fuzzy rules which make use of membership functions. In this article, to perform fuzzy smoothing, fuzzy derivative concept is also applied. This method provides better input for further image processing techniques. It also increases the contrast of the images, fine details and sharpening the edges as well. This comparative study, is made by numerical measures and visual inspection.

show abstract

“…In this paper, 5 Note that there is no strict restriction to choose the types and the number of input filters connected to NF. One can choose any other type of filter(s) or the number of filters without too much consideration, differently from the hybrid filter based on neurofuzzy system [18]. In that rule-based hybrid filter, the number of rules could be exponentially increased as the number of input filters.…”

Section: Proposed Hybrid Filter Based On Neural Networkmentioning

confidence: 99%

Hybrid Filter Based on Neural Networks for Removing Quantum Noise in Low-Dose Medical X-ray CT Images

Keunho

Lee

2015

Int. J. Fuzzy Log. Intell. Syst.

View full text Add to dashboard Cite

The main source of noise in computed tomography (CT) images is a quantum noise, which results from statistical fluctuations of X-ray quanta reaching the detector. This paper proposes a neural network (NN) based hybrid filter for removing quantum noise. The proposed filter consists of bilateral filters (BFs), a single or multiple neural edge enhancer(s) (NEE), and a neural filter (NF) to combine them. The BFs take into account the difference in value from the neighbors, to preserve edges while smoothing. The NEE is used to clearly enhance the desired edges from noisy images. The NF acts like a fusion operator, and attempts to construct an enhanced output image. Several measurements are used to evaluate the image quality, like the root mean square error (RMSE), the improvement in signal to noise ratio (ISNR), the standard deviation ratio (MSR), and the contrast to noise ratio (CNR). Also, the modulation transfer function (MTF) is used as a means of determining how well the edge structure is preserved. In terms of all those measurements and means, the proposed filter shows better performance than the guided filter, and the nonlocal means (NLM) filter. In addition, there is no severe restriction to select the number of inputs for the fusion operator differently from the neuro-fuzzy system. Therefore, without concerning too much about the filter selection for fusion, one could apply the proposed hybrid filter to various images with different modalities, once the corresponding noise characteristics are explored.

show abstract

A hybrid neuro-fuzzy filter for edge preserving restoration of images corrupted by impulse noise

Cited by 77 publications

References 45 publications

A Detection Statistic for Random-Valued Impulse Noise

A Detection Statistic for Random-Valued Impulse Noise

A Comparative Study of Gaussian Noise Removal Methodologies for Gray Scale Images

Hybrid Filter Based on Neural Networks for Removing Quantum Noise in Low-Dose Medical X-ray CT Images

Contact Info

Product

Resources

About