Adaptive median filters: new algorithms and results

Hwang, Humor; Haddad, R.A.

doi:10.1109/83.370679

Cited by 1,060 publications

(549 citation statements)

References 4 publications

Supporting

Mentioning

547

Contrasting

Unclassified

Order By: Relevance

“…Works like [20], [21] or [22] also exploit the fact that it is possible to identify with good accuracy candidate noisy samples, so as to avoid changing samples that are not corrupted, and sometimes to exclude noisy samples from some computations. Impulse noise strongly impacts image gradients, and therefore the variational approach of [23] (see also [24]) is well-suited.…”

Section: Introductionmentioning

confidence: 99%

The iDUDE Framework for Grayscale Image Denoising

Motta

Ordentlich

Ramírez

et al. 2011

IEEE Trans. on Image Process.

View full text Add to dashboard Cite

Image denosing, impulse noise, discrete universal denoising, dudeWe present an extension of the Discrete Universal DEnoiser (DUDE) specialized for the denoising of grayscale images. The original DUDE is a low-complexity algorithm aimed at recovering discrete sequences corrupted by discrete memoryless noise of known statistical characteristics. It is universal, in the sense of asymptotically achieving, without access to any information on the statistics of the clean sequence, the same performance as the best denoiser that does have access to such information. The denoising performance of the DUDE, however, is poor on grayscale images of practical size. The difficulty lies in the fact that one of the DUDE's key components is the determination of conditional empirical probability distributions of image samples, given the sample values in their neighborhood. When the alphabet is moderately large (as is the case with grayscale images), even for a small-sized neighborhood, the required distributions would be estimated from a large collection of sparse statistics, resulting in poor estimates that would cause the algorithm to fall significantly short of the asymptotically optimal performance. The present work enhances the basic DUDE scheme by incorporating statistical modeling tools that have proven successful in addressing similar issues in lossless image compression. The enhanced framework is tested on additive and non-additive noise, and shown to yield powerful denoisers that significantly surpass the state of the art in the case of non-additive noise, and perform well for Gaussian noise. AbstractWe present an extension of the Discrete Universal DEnoiser (DUDE) specialized for the denoising of grayscale images. The original DUDE is a low-complexity algorithm aimed at recovering discrete sequences corrupted by discrete memoryless noise of known statistical characteristics. It is universal, in the sense of asymptotically achieving, without access to any information on the statistics of the clean sequence, the same performance as the best denoiser that does have access to such information. The denoising performance of the DUDE, however, is poor on grayscale images of practical size. The difficulty lies in the fact that one of the DUDE's key components is the determination of conditional empirical probability distributions of image samples, given the sample values in their neighborhood.When the alphabet is moderately large (as is the case with grayscale images), even for a small-sized neighborhood, the required distributions would be estimated from a large collection of sparse statistics, resulting in poor estimates that would cause the algorithm to fall significantly short of the asymptotically optimal performance. The present work enhances the basic DUDE scheme by incorporating statistical modeling tools that have proven successful in addressing similar issues in lossless image compression. The enhanced framework is tested on additive and non-additive noise, and shown to yield powerful denoisers that significantly su...

show abstract

Section: Introductionmentioning

confidence: 99%

The iDUDE Framework for Grayscale Image Denoising

Motta

Ordentlich

Ramírez

et al. 2011

IEEE Trans. on Image Process.

View full text Add to dashboard Cite

show abstract

“…Wavelets can represent data in very sparse form and therefore can be used in denoising by thresholding [20][21]. Finally, replacing x in (9) with the border value estimated using the method described in [18] and [19] and inserting the value of b found using (10), we obtain…”

Section:   mentioning

confidence: 99%

“…In this paper, we propose a method to determine the parameters of the bell-shaped function for optimal restoration. According to Hwang and Haddad [18] and Ko and Lee [19], the outlier border is the point beyond which sample points are considered outliers. The goal is to reduce the contribution of samples outside the outlier border gradually.…”

Section:   mentioning

confidence: 99%

Optimized Parameters for Bell-Shaped Error Function in Image Denoising

Özkan¹,

Seke²

2017

ANADOLU UNIVERSITY JOURNAL OF SCIENCE AND TECHNOLOGY a - Applied Sciences and Engineering

View full text Add to dashboard Cite

Adaptive image denoising algorithms rely on an error function that measure the distance between an estimated result and expectations. Selection of the error function and its parameters are crucial for a successful denoising implementation. In this paper, a method for determining close-to-optimal parameters for a bell-shaped error function is evaluated. The function with calculated parameters is employed within a gradient optimization algorithm and tested using test images with varying noise types and levels. The restoration results of the denoising test runs that use the proposed parameters are compared against the results of algorithms that employ well-known least squares and sum of absolute differences methods along with a method that combines both. The clear superiority of the bell-shaped error function for the proposed parameters is shown by the test results.

show abstract

“…Its purpose is mainly for the removing impulse noise, smoothing of other noise and reducing distortion, like excessive thinning or thickening of object boundary. The detailed algorithm is given in [12,13].…”

Section: Preprocessing and Contrast Enhancementmentioning

confidence: 99%

Segmentation and texture analysis with multimodel inference for the automatic detection of exudates in early diabetic retinopathy

Lee¹,

Zee²,

Li³

2013

JBiSE

View full text Add to dashboard Cite

Diabetic retinopathy (DR) is an eye disease caused by the increase of insulin in blood and may cause blindness if not treated at an early stage. Exudates are the primary sign of DR. Currently there is no fully automated method to detect exudates in the literature and it would be useful in large scale screening if fully automatic method is available. In this paper we developed a novel method to detect exudates that based on interactions between texture analysis and segmentation with mathematical morphological technique by using multimodel inference. The texture analysis involves three components: they are statistical texture analysis, high order spectra analysis, and fractal analysis. The performance of the proposed method is assessed by the sensitivity, specificity and accuracy using the public data DIARETDB1. Our results show that the sensitivity, specificity and accuracy are 95.7%, 97.6% and 98.7% (SE = 0.01), respectively. It is shown that the proposed method can be run automatically and also improve the accuracy of exudates detection significantly over most of the previous methods.

show abstract

Adaptive median filters: new algorithms and results

Cited by 1,060 publications

References 4 publications

The iDUDE Framework for Grayscale Image Denoising

The iDUDE Framework for Grayscale Image Denoising

Optimized Parameters for Bell-Shaped Error Function in Image Denoising

Segmentation and texture analysis with multimodel inference for the automatic detection of exudates in early diabetic retinopathy

Contact Info

Product

Resources

About