Extraction of Retinal Blood Vessel Using Curvelet Transform and Fuzzy C-Means

Kar, Sudeshna Sil; Maity, Santi P.

doi:10.1109/icpr.2014.584

Cited by 7 publications

(5 citation statements)

References 15 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…The signal energy values ( E total ) stored in FC are classified into four different classes, ie, PU signal presence in absence of PUEA, PU signal presence in presence of PUEA, PUEA signal presence in absence of PU, and noise only. The classes, as mentioned earlier, are shown in Figure using four different membership functions, namely, Z(x, α , β )‐function,

\prod false(x, α, β false)

‐function,

\prod false(x, α, β false)

‐function, and S(x, α , β )‐function, respectively. Based on the energy values of PU and PUEA signals in radio mobile environment, such distinctive regions are less likely to obtain.…”

Section: Problem Formulation and Proposed Solutionmentioning

confidence: 99%

“…The membership functions μ n , μ m , μ p , μ pm , shown in Figure , represent the different states, namely, noise only, PUEA (in absence of PU), PU (in absence of PUEA), and PU (in presence of PUEA), respectively, and are same as used in the work of Kar et al The functions are expressed mathematically as follows:

μ_{n} false(x false) = ({, \begin{matrix} array \\ array 1 & array x \leq α_{1} \\ array \frac{x - β_{1}}{α_{1} - β_{1}} & array α_{1} \leq x \leq β_{1} \\ array 0 & array x > β_{1} \end{matrix})

μ_{s} false(x false) = ({, \begin{matrix} array \\ array 0 & array x \leq α_{n - 1} \\ array \frac{x - α_{n - 1}}{β_{n - 1} - α_{n - 1}} & array α_{n - 1} < x \leq β_{n - 1} \\ array 1 & array β_{n - 1} < x \leq α_{n} \\ array \frac{x - β_{n}}{α_{n} - β_{n}} & array α_{n} < x \leq β_{n} \\ array 0 & array x > β_{n .} \end{matrix})

Here, μ s ( x ) = μ m ( x ) for n = 2 and μ s ( x ) = μ p ( x ) for n = 3,

μ_{p m} false(x false) = ({, \begin{matrix} array \\ array 0 & array x \leq α_{3} \\ array x - \end{matrix})

…”

Section: Problem Formulation and Proposed Solutionmentioning

confidence: 99%

“…The membership functions n , m , p , pm , shown in Figure 4, represent the different states, namely, noise only, PUEA (in absence of PU), PU (in absence of PUEA), and PU (in presence of PUEA), respectively, and are same as used in the FIGURE 4 Membership functions for multiple thresholds. PU, primary user; PUEA, primary user emulation attack work of Kar et al 43 The functions are expressed mathematically as follows:…”

Section: Formulation Of Membership Function In Presence Of Pueamentioning

confidence: 99%

See 2 more Smart Citations

Joint cooperative spectrum sensing and primary user emulation attack detection in cognitive radio networks using fuzzy conditional entropy maximization

Banerjee

Maity

2019

Trans Emerging Tel Tech

Self Cite

View full text Add to dashboard Cite

Cooperative spectrum sensing (CSS) in cognitive radio system shows improved performance on spectrum sensing but, at the same time, faces a common threat called primary user emulation attack (PUEA) that impersonates the primary user (PU). This work explores joint PU and PUEA detection on CSS as a multiclass hypothesis using fuzzy conditional entropy maximization. To meet the goal, a multithreshold approach is suggested using a constrained differential evolution algorithm search to determine an optimal set of fuzzy function parameters, which maximizes the conditional entropy on the energy values. The proposed work also investigates the performance of CSS in presence of a group of malicious users (as PUEA), which generates signals and directly sends the same to the fusion center. Numerical results through simulation illustrate the efficacy of the proposed scheme in terms of both reliable PU detection in presence or absence of PUEA/malicious user and separate detection of falsifying PU and energy consumption in CSS. Simulation results show that the proposed scheme offers ∼17.54% and ∼39.39% higher detection probability of PU over the existing works in presence of PUEA.

show abstract

\prod false(x, α, β false)

‐function,

\prod false(x, α, β false)

‐function, and S(x, α , β )‐function, respectively. Based on the energy values of PU and PUEA signals in radio mobile environment, such distinctive regions are less likely to obtain.…”

Section: Problem Formulation and Proposed Solutionmentioning

confidence: 99%

μ_{n} false(x false) = ({, \begin{matrix} array \\ array 1 & array x \leq α_{1} \\ array \frac{x - β_{1}}{α_{1} - β_{1}} & array α_{1} \leq x \leq β_{1} \\ array 0 & array x > β_{1} \end{matrix})

μ_{s} false(x false) = ({, \begin{matrix} array \\ array 0 & array x \leq α_{n - 1} \\ array \frac{x - α_{n - 1}}{β_{n - 1} - α_{n - 1}} & array α_{n - 1} < x \leq β_{n - 1} \\ array 1 & array β_{n - 1} < x \leq α_{n} \\ array \frac{x - β_{n}}{α_{n} - β_{n}} & array α_{n} < x \leq β_{n} \\ array 0 & array x > β_{n .} \end{matrix})

Here, μ s ( x ) = μ m ( x ) for n = 2 and μ s ( x ) = μ p ( x ) for n = 3,

μ_{p m} false(x false) = ({, \begin{matrix} array \\ array 0 & array x \leq α_{3} \\ array x - \end{matrix})

…”

Section: Problem Formulation and Proposed Solutionmentioning

confidence: 99%

Section: Formulation Of Membership Function In Presence Of Pueamentioning

confidence: 99%

See 1 more Smart Citation

Joint cooperative spectrum sensing and primary user emulation attack detection in cognitive radio networks using fuzzy conditional entropy maximization

Banerjee

Maity

2019

Trans Emerging Tel Tech

Self Cite

View full text Add to dashboard Cite

show abstract

“…In 2014, Kar et al combined curvelet transform with matched filter and conditional fuzzy entropy for extraction of blood vessels [12]. In 2016, the same authors suggested another method for extraction of blood vessels by combining curvelet transform with matched filter and kernel fuzzy c-means [13]. Some of the significance associated with supervised and unsupervised works for retinal vessel segmentation that are available are discussed below.…”

Section: Introductionmentioning

confidence: 99%

A Hybrid Method to Enhance Thick and Thin Vessels for Blood Vessel Segmentation

Dash¹,

Verma

Kavita

et al. 2021

Diagnostics

View full text Add to dashboard Cite

Retinal blood vessels have been presented to contribute confirmation with regard to tortuosity, branching angles, or change in diameter as a result of ophthalmic disease. Although many enhancement filters are extensively utilized, the Jerman filter responds quite effectively at vessels, edges, and bifurcations and improves the visualization of structures. In contrast, curvelet transform is specifically designed to associate scale with orientation and can be used to recover from noisy data by curvelet shrinkage. This paper describes a method to improve the performance of curvelet transform further. A distinctive fusion of curvelet transform and the Jerman filter is presented for retinal blood vessel segmentation. Mean-C thresholding is employed for the segmentation purpose. The suggested method achieves average accuracies of 0.9600 and 0.9559 for DRIVE and CHASE_DB1, respectively. Simulation results establish a better performance and faster implementation of the suggested scheme in comparison with similar approaches seen in the literature.

show abstract

“…The study was able to provide good performance with AUC 87%, unfortunately, the research produced too low sensitivity below 80%. The same AUC value was also generated in the study of Kar and Maity [7]. In addition to the two studies, a combination of FCM with entropy information was developed by Mapayi et al [8] and weighted FCM by Kande et al [9].…”

Section: Introductionmentioning

confidence: 99%

The Hybrid Method of SOM Artificial Neural Network and Median Thresholding for Segmentation of Blood Vessels in the Retina Image Fundus

Wiharto

2019

IJFIS

View full text Add to dashboard Cite

Blood vessels in the retina of the eye are one important sign when making a diagnosis of hypertensive retinopathy. On the retina can be known several signs including tortuosity and arteriovenous ratio. Blood vessels mixed with a number of objects in the retina, the segmentation of blood vessels becomes a very interesting challenge because they have to separate blood vessels from a number of objects. This study aims to segmentation blood vessels using the main method of self-organizing maps artificial neural networks (SOM-ANN). The proposed segmentation method is divided into three stages, namely preprocessing, segmentation, and performance analysis. The preprocessing step is to improve image quality using the contrast-limited adaptive histogram equalization (CLAHE), median filter, and morphology. The segmentation stage uses the SOM-ANN algorithm combined with the mean or median thresholding. The performance parameters which are measured consist of sensitivity, specificity, and area under the curve (AUC). The test results using the dataset STARE and DRIVE show that the median thresholding is able to provide the best AUC performance compared to the mean thresholding. The proposed segmentation model is able to provide performance in the excellent category, with AUC values of 90.55% for the STARE dataset and 90.35% for the DRIVE.

show abstract

Extraction of Retinal Blood Vessel Using Curvelet Transform and Fuzzy C-Means

Cited by 7 publications

References 15 publications

Joint cooperative spectrum sensing and primary user emulation attack detection in cognitive radio networks using fuzzy conditional entropy maximization

Joint cooperative spectrum sensing and primary user emulation attack detection in cognitive radio networks using fuzzy conditional entropy maximization

A Hybrid Method to Enhance Thick and Thin Vessels for Blood Vessel Segmentation

The Hybrid Method of SOM Artificial Neural Network and Median Thresholding for Segmentation of Blood Vessels in the Retina Image Fundus

Contact Info

Product

Resources

About