Image-selective segmentation model for multi-regions within the object of interest with application to medical disease

Selective image segmentation is one of the most important topics in medical imaging and real applications. In this paper, we propose a robust selective segmentation model using a dual-level set variational formulation based on local spatial distance. Our model aims to segment all objects with one level set function (global) and the selected object with another level set function (local). Our model is the combination of marker distance function, edge detection, local spatial distance, and active contour without edges. The new model is robust to noise and gives better performance for images having intensity in-homogeneity (background and foreground). Moreover, we observed that the proposed model captures objects which do not have uniform features. The experimental results show that our model is robust to noise and works better than the other existing models.

show abstract

“…Ali et al [39] proposed a selective segmentation model based on generalized averages, the minimization functional is given by:…”

Section: Selective Segmentation Model For Multi-regions Within the Ob...mentioning

confidence: 99%

“…Sφrensen-Dice similarity for Liu et al[33], Mabood et al[32], Rada et al[31], Ali et al[39] and the proposed model on 10 different images.…”

mentioning

confidence: 99%

A Selective Segmentation Model Using Dual-Level Set Functions and Local Spatial Distance

et al. 2022

Self Cite

View full text Add to dashboard Cite

show abstract

“…The model in (19) keeps the merits for the smoothing features of the tested digital image. On the other hand, the noisy image will be stationary and kept unchanged when the number of iterations reaches to a specific value [19]. As a consequence, study in [20] Y,You and other researchers proposed high order partial differential equations and [21] came up with regularization P-M method [20] in order to deal with the over smoothing results in the denoised images.…”

Section: P-m Model Optimizationmentioning

confidence: 99%

Natural Digital image Mixed Noise Removal Using Regularization Perona-Malik Model and Pulse Coupled Neural Networks

Khmag

2022

Preprint

View full text Add to dashboard Cite

In the arena of digital image processing, mixed noise is normally shown. Nevertheless, the main limitation of the existing noise removal methods is the exploitation of the statistics of the original contaminated image only. This paper proposes a rapid and high accurate mixed noise removal method by combining Pulse Coupled Neural Networks (PCNN) and regularization of Perona-Malik equation (P-M equation) in order to remove unwanted contamination. In this regard, the locations of impulse noise are positioned by using PCNN, the second-generation wavelet filter is used in order to suppress the mixed noise into small local neighborhood, and then the full noisy image is denoised by exploiting the regularization of P-M equation. The fine details and sharp edges are well preserved in the proposed method. In addition, subjective and objective analyses are showed that the visual quality of the denoised technique outperformed state of the art noise removal methods. The experimental evaluation is conducted on well-known benchmark database images with mixed noise type. Furthermore, the results show that our proposed method can obtain more accurate and more reliable noise removal images than other approaches. Experimental results show that the proposed method provides accurate denoising performance with a low computational cost compared to nonlocal processing like NL-mean method.

show abstract

“…The model retains the advantages for image feature reservations of nonlinear smoothing; the image does not change when the iterations reaches a certain number, each area gray values in the image are the same, resulting in the iterative derivation to zero [15]. In response to this phenomenon, Y.-L.You and other researchers have proposed high order partial differential equations [16] and Catte F have proposed regularization P-M method [17].…”

Section: ( (mentioning

confidence: 99%

Mixed Image Noise Removal by PCNN Combined with Regularization P-M Equation

Liu,

ZHAO,

ZHAO

et al. 2022

Preprint

View full text Add to dashboard Cite

In order to effectively remove the mixed noise, a novel algorithm for image reducing noise combined Pulse Coupled Neural Networks (PCNN) and regularization of Perona-Malik equation (P-M equation) is put forward. Firstly, the positions of impulse noise pollution are located by using PCNN, and the first stage adaptive noise filtering is applied according to the result of noise detection. Secondly, the multi-direction information median filtering is applied according to the local neighborhood noisy information. And then the Gaussian noise in the image is denoised by utilizing the regularization P-M diffusion equation. The theoretical analysis and experimental results show that the proposed algorithm needs no detection threshold, which has higher accuracy in the noise detection, is effectively able to remove the mixed noise, and can preserve the image details and the edges as well. The proposed algorithm has better subjective vision effect and objective quality than the wiener filter, median filter and other related algorithms. This algorithm put up better filter performance, high signal-to-noise ratio, denoising ability and strong adaptability.

show abstract

Image-selective segmentation model for multi-regions within the object of interest with application to medical disease

Cited by 14 publications

References 53 publications

A Selective Segmentation Model Using Dual-Level Set Functions and Local Spatial Distance

A Selective Segmentation Model Using Dual-Level Set Functions and Local Spatial Distance

Natural Digital image Mixed Noise Removal Using Regularization Perona-Malik Model and Pulse Coupled Neural Networks

Mixed Image Noise Removal by PCNN Combined with Regularization P-M Equation

Contact Info

Product

Resources

About