A Bayesian Mumford–Shah Model for Radiography Image Segmentation

Ramou, N.; Chetih, Nabil; Halimi, M.

doi:10.1007/s13369-017-3031-z

Cited by 7 publications

(4 citation statements)

References 8 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…The first dataset comprises MR brain images, which include both real and simulated images [4,34]. The second dataset consists of real x-ray images that include defects occurring during the welding process, used in nondestructive testing [8,35,36]. Specifically, this dataset is subdivided into:…”

Section: Resultsmentioning

confidence: 99%

“…• Radiographic images of welding that include defects that could happen during the welding operation (Lacks of penetration) obtained from images data used in [8,35].…”

Section: Resultsmentioning

confidence: 99%

“…Figures 11 and 12 show the comparative behaviour of the FCMC, KFCMC, NBWTFCM, FCMC-NBA and the proposed EIFCMNB method in terms of VPE, VPC for a number of iterations (15, 30, 50, 80 and 100) with an image corrupted by the Gaussian noise (σ = 20). The test images used are simulated and MR brain images [4,32] and x-ray welding images [8,35,36].…”

Section: Resultsmentioning

confidence: 99%

“…It facilitates the delineation, characterization, and extraction of the region of interest [1][2][3][4]. There are several image segmentation techniques, each one with its advantages and limitations [5][6][7][8]. Among these techniques, fuzzy clustering techniques such as K-means, Fuzzy c-means clustering (FCMC), and Kernel fuzzy c-means clustering (KFCMC) can be mentioned [4,5,9].…”

Section: Introductionmentioning

confidence: 99%

See 3 more Smart Citations

Enhanced independent component analysis and fuzzy C-mean clustering based on novel bat algorithm for noisy image segmentation

Chetih,

Thelaidjia,

Boudani

2023

Eng. Res. Express

View full text Add to dashboard Cite

Fuzzy c-means clustering is widely recognized as one of the most effective methods for image segmentation and achieving accurate classification. However, this method has two significant drawbacks: its sensitivity to noise and its convergence to local minimum clusters’ centroids. In this paper, we proposed a novel model called EIFCMNB, which incorporates enhanced independent component analysis (EICA), fuzzy c-means clustering (FCMC) and novel bat algorithm (NBA) for noise image segmentation. The suggested model consists of two main phases: image denoising and extraction of the regions of interest (ROIs). In the first phase, the enhanced independent component analysis (EICA) algorithm is used for recovering a good quality image, from a noisy image of poor quality. Several noisy images, with noise variances ranging from 5 to 20, were filtered. The resulting images were then evaluated based on several criteria viz: Peak Signal to Noise Ratio (PSNR), Relative Norm Error (RE), Normalized Cross-Correlation (NCC), and Structural Similarity index measure (SSIM).In the second phase, the fuzzy c-means clustering based on a novel bat algorithm is adopted to calculate optimal clusters’ centroids and extract the ROIs. By incorporating the new bat algorithm, we aim to overcome the problem of converging to local minimums and achieve improved segmentation accuracy. Promising experimental results have been obtained by applying the proposed model to MRI brain images and X-ray welding images. Two criteria viz: VPE end VPC have been employed to evaluate the suggested approach. The experiments clearly demonstrate that our suggested model effectively addresses the sensitivity to noise problem and provides optimal clusters' centroids. Moreover, it outperforms several FCMC-based algorithms, exhibiting superior performance in terms of image segmentation and classification

show abstract

Section: Resultsmentioning

confidence: 99%

“…• Radiographic images of welding that include defects that could happen during the welding operation (Lacks of penetration) obtained from images data used in [8,35].…”

Section: Resultsmentioning

confidence: 99%