Design of Fuzzy Relation-Based Image Sharpeners

Russo, Fabrizio

doi:10.1007/978-3-642-11739-8_6

Cited by 6 publications

(4 citation statements)

References 16 publications

(4 reference statements)

Supporting

Mentioning

Contrasting

Order By: Relevance

“…The major drawback of such evaluation methods, however, is the fact that they have limited accuracy in estimating the different filtering features. As already observed for grayscale images [17,18], MSE and MAE cannot yield accurate measures of noise cancellation and detail preservation, because they cannot totally separate these effects. Although the MSE is more sensitive to residual noise than the MAE, it takes into account the amount of distortion produced by a filter too.…”

Section: Introductionmentioning

confidence: 86%

Accurate Tools for Analyzing the Behavior of Impulse Noise Reduction Filters in Color Images

Russo¹

2013

JSIP

Self Cite

View full text Add to dashboard Buy / Rent full text

Effective cancellation of noise and preservation of color/structural information are features of paramount importance for any filter devoted to impulse noise removal in color images. In this paper novel full-reference tools for analyzing the behavior of this family of filters are presented. The proposed approach is based on the classification of color errors into two main classes that separately take into account the inaccuracy in removing noise pulses and the filtering distortion. The distortion errors are then classified into two subclasses for a deeper analysis of the filtering behavior. Computer simulations show that the proposed method gives more accurate results than using other measures of filtering performance in the literature. Furthermore, the method can easily yield the spatial location of the different filtering features in the image.

show abstract

Section: Introductionmentioning

confidence: 86%

Accurate Tools for Analyzing the Behavior of Impulse Noise Reduction Filters in Color Images

Russo¹

2013

JSIP

Self Cite

View full text Add to dashboard Buy / Rent full text

show abstract

“…Few images of the DIARETDB1 dataset have good brightness levels and contrast, while the majority of them are dark with low contrast. The quality of fundus images is enhanced using contrast limited adaptive histogram equalization (CLAHE) [ 17 ], gradient-based adaptive brightness adjustment (GAGC) [ 18 ], and nonlinear unsharp masking [ 19 ]. CLAHE enhances contrast and reduces the effects of over-saturation by clipping intensity peaks.…”

Section: Methodsmentioning

confidence: 99%

Comparing Conventional and Deep Feature Models for Classifying Fundus Photography of Hemorrhages

Tamoor¹,

Chalie²,

Mahapakulchai³

2022

Journal of Healthcare Engineering

View full text Add to dashboard Buy / Rent full text

Diabetic retinopathy is an eye-related pathology creating abnormalities and causing visual impairment, proper treatment of which requires identifying irregularities. This research uses a hemorrhage detection method and compares the classification of conventional and deep features. Especially, the method identifies hemorrhage connected with blood vessels or residing at the retinal border and was reported challenging. Initially, adaptive brightness adjustment and contrast enhancement rectify degraded images. Prospective locations of hemorrhages are estimated by a Gaussian matched filter, entropy thresholding, and morphological operation. Hemorrhages are segmented by a novel technique based on the regional variance of intensities. Features are then extracted by conventional methods and deep models for training support vector machines and the results are evaluated. Evaluation metrics for each model are promising, but findings suggest that comparatively, deep models are more effective than conventional features.

show abstract

“…It is expected that a fuzzy approach can represent a more powerful resource. Indeed, fuzzy techniques are well suited to model the uncertainty that occurs when conflicting tasks are performed, for example, noise cancellation and detail preservation [13][14][15].…”

Section: Introductionmentioning

confidence: 99%

“…where ρ LT (u,v) is the membership function that describes the fuzzy relation "u is larger than v": (14) The procedure described by (13)(14) aims at determining the degree of residual noise μ(i,j) (0≤μ≤1) affecting the pixel at location [i,j] in the filtered picture. This is achieved by comparing the quantities Δ YB (i,j) and Δ YR (i,j).…”

Section: Introducing the Fuzzy Maementioning

confidence: 99%

A fuzzy approach to performance measurement of grayscale image denoising algorithms

Russo

2015

2015 IEEE 9th International Symposium on Intelligent Signal Processing (WISP) Proceedings

Self Cite

View full text Add to dashboard Buy / Rent full text

The most advanced metrics for performance evaluation of image denoising algorithms are based on the classification of filtered pixels in two crisp classes: pixels where residual noise is still present (due to insufficient filtering) and pixels where excessive filtering has produced distortion. However, the intrinsic nature of image denoising is very likely to be fuzzy: a pixel can be affected by different degrees of unfiltered noise and filtering distortion as well. According to this idea, a new method for performance measurement of grayscale image denoising filter is presented. The method adopts a fuzzy modelbased procedure that estimates, for each filtered pixel, the different components of the filtering error, i.e., the amounts of unfiltered noise and filtering distortion produced by the denoising process. Computer simulations dealing with different test images corrupted by various amounts of noise show that the new approach performs significantly better than state-of-the art metrics in the field. Furthermore, the results yielded by the proposed method are in perfect agreement with the true values of residual noise and image blur that can be theoretically evaluated for an important class of denoising filters.

show abstract

Design of Fuzzy Relation-Based Image Sharpeners

Cited by 6 publications

References 16 publications

Accurate Tools for Analyzing the Behavior of Impulse Noise Reduction Filters in Color Images

Accurate Tools for Analyzing the Behavior of Impulse Noise Reduction Filters in Color Images

Comparing Conventional and Deep Feature Models for Classifying Fundus Photography of Hemorrhages

A fuzzy approach to performance measurement of grayscale image denoising algorithms

Contact Info

Product

Resources

About