Fuzzy c-means clustering with spatial information for color image segmentation

In this paper, a novel method for lumen boundary identification is proposed using Neutrosophic c_means. This method clusters pixels of the intravascular optical coherence tomography image into several clusters using indeterminacy and Neutrosophic theory, which aims to detect the boundaries. Intravascular optical coherence tomography images are crosssectional and high-resolution images which are taken from the coronary arterial wall. Coronary Artery Disease cause a lot of death each year. The first step for diagnosing this kind of diseases is to detect lumen boundary. Employing this approach, we obtained 0.972, 0.019, 0.076 mm 2 , 0.32 mm, and 0.985 as mean value for Jaccard measure (JACC), the percentage of area difference (PAD), average distance (AD), Hausdorff distance (HD), and dice index (DI), respectively. Based on our results, this method enjoys high accuracy performance.

show abstract

“…∊ . ∊ (19) In equation (19), a and b are curve points of and , respectively, and d(a, b)is the Euclidean distance.…”

Section: B Evaluation Metricsmentioning

confidence: 99%

Lumen boundary detection using neutrosophic c-means in IVOCT images

Habibi

Ayatollahi

Dallalazar

et al. 2019

2019 5th Conference on Knowledge Based Engineering and Innovation (KBEI)

View full text Add to dashboard Cite

show abstract

“…In [3], automated method of the initial seed selection for k-means clustering is presented and the selection of k value is designed in [4] for k-means clustering. Similarly, FCM algorithm is also modified including spatial information [5] and kernel [6].…”

Section: Introductionmentioning

confidence: 99%

KF-PSO: Hybridization of particle swarm optimization and kernel-based fuzzy C means algorithm

Binu

George

2013

2013 International Conference on Advances in Computing, Communications and Informatics (ICACCI)

View full text Add to dashboard Cite

In recent times, clustering has been well known for various researchers due to various applications in most of the fields like, telecommunication, networking, biomedical domain and so on. So, various attempts have been already made by the researchers to develop a better algorithm for clustering. One of the procedures well known among the researchers is optimization that has been effectively utilized for clustering. In most of the clustering, the objective function is to minimize the intra cluster distance among the data points. Here, we have made significant trial in developing optimization based clustering algorithm utilizing kernel-based FCM and PSO algorithm. The objective function for minimization is taken from kernel-based FCM and the same objective is solved using PSO algorithm. The algorithm developed based on these scenarios are named as, KF-PSO. At first, the input data is given to PSO algorithm and the final best cluster centers are chosen from PSO algorithm useful for grouping based on the objective of the kernel clustering. Finally, the experimentation have been performed in various datasets and from the results, we have showed that the proposed hybrid algorithm achieved 98% and 90.5 % accuracy in iris and wine dataset.

show abstract

“…Using discrete wavelet transform, a digital image can be decomposed into an approximation component and detailed components (horizontal, vertical, diagonal). (Ye et al , 2006Jaffar et al 2009). Information loss between two successive decomposition levels of approximations is represented in detail coefficients (Gonzalez and Woods 2007;Duda et al 2000;Haykin 1999;Ye et al 2007aYe et al , 2008.…”

Section: Introductionmentioning

confidence: 99%

“…The approximation component is further decomposed. Nonlinear K-means clustering is used in this case for image segmentation (Ye et al , 2006(Ye et al , 2007bJaffar et al 2009;Ye 2005). The essence of fractal-based denoising in the wavelet domain has been used to predict the fractal code of a noiseless image.…”

Section: Introductionmentioning

confidence: 99%