Gauhar Arefin - Academia.edu (original) (raw)
Uploads
Papers by Gauhar Arefin
We propose a new measure for denoising image by calculating mean distance of all pixels in an ima... more We propose a new measure for denoising image by calculating mean distance of all pixels in an image in non-local means (NL-means) algorithm. We compute and analyze the original NL-means algorithm which total all the distance of the patches but, our proposed algorithm calculates the mean value of all distance of all the patches and then than get the sum of all distance. Our proposed algorithm exhibit better result with comparison of the existing NL-means algorithm. Keywords: NL-means, Patches, Mean Value, Measurement Matrix.
International Journal of Computer Applications, 2013
Segmentation on Computed Tomography (CT) image of heart and brain can be optimally posed as Bayes... more Segmentation on Computed Tomography (CT) image of heart and brain can be optimally posed as Bayesian labeling in which the segment of a image is defined as the maximum a posteriori (MAP) probability estimate of the true labeling. The Simulated Annealing (SA) algorithm is used to minimize the energy function associated with MRF posterior distribution function. The goal of this thesis paper is to minimize the energy function using Gaussian distribution and get accurate segmentation by slowly minimize the energy and simultaneously reduce the pixels which have no impact on the image at rapid rate to get the segmentation quickly without degrade the image. The propose algorithm able to get more precise segmentation.
Medical image segmentation is a fundamental task in the medical imaging field. Optimal segmentati... more Medical image segmentation is a fundamental task in the medical imaging field. Optimal segmentation is required for the accurate judgment or appropriate clinical diagnosis. In this paper, we proposed automatically gradient threshold estimator of anisotropic diffusion for Meyer's Watershed algorithm based optimal segmentation. The Meyer's Watershed algorithm is the most significant for a large number of regions separations but the over segmentation is the major drawback of the Meyer's Watershed algorithm. We are able to remove over segmentation after using anisotropic diffusion as a preprocessing step of segmentation in the Meyer's Watershed algorithm. We used a fixed window size for dynamically gradient threshold estimation. The gradient threshold is the most important parameter of the anisotropic diffusion for image smoothing. The proposed method is able to segment medical image accurately because of obtaining the enhancement image. The introducing method demonstrates better performance without loss of any clinical information while preserving edges. Our investigated method is more efficient and effective in order to segment the region of interests in the medical images indeed.
In image processing noise is possibly the most annoying problem. Ultrasound image has been used f... more In image processing noise is possibly the most annoying problem. Ultrasound image has been used for effective diagnosis for its non-invasive, harmless, accurate and cost effectiveness. Unfortunately, ultrasound images are degraded by an intrinsic artefact called speckle. Eliminating such speckle noise is an important preprocessing task. For acquiring a better performance for denoising, an adaptive anisotropic diffusion technique for ultrasound images is presented in this paper. It is a new efficient method for denoising the image without blurring the frontiers between different regions. The proposed noise detection-oriented method is based on the differentiation of the diffusion in the direction of the gradient and the adjacent pixels of entire image. The performance of different metrics shows the proposed method exhibit better result to existing Perona-Malik anisotropic diffusion method.
2012 15th International Conference on Computer and Information Technology (ICCIT), 2012
In this paper we present and evaluate a novel method for an efficient speckle denoising by using ... more In this paper we present and evaluate a novel method for an efficient speckle denoising by using principal component analysis (PCA) with bit plane slicing and nonlinear diffusion. We use PCA transformation for generating de-correlated dataset from a noisy image. Then we apply bit plane slicing on the de-correlated dataset and nonlinear diffusion is applied on each bit plane. For nonlinear diffusion in each bit plane level, a gradient threshold is automatically estimated. Add up all bit plane slice after nonlinear diffusion execution and then we implement inverse principal component analysis for making denoised images. The proposed speckle reduction method could improve image quality and the visibility of small structures and fine details in medical ultrasound imaging compared with state-of-the-art speckle denoising algorithms.
We propose a new measure for denoising image by calculating mean distance of all pixels in an ima... more We propose a new measure for denoising image by calculating mean distance of all pixels in an image in non-local means (NL-means) algorithm. We compute and analyze the original NL-means algorithm which total all the distance of the patches but, our proposed algorithm calculates the mean value of all distance of all the patches and then than get the sum of all distance. Our proposed algorithm exhibit better result with comparison of the existing NL-means algorithm. Keywords: NL-means, Patches, Mean Value, Measurement Matrix.
International Journal of Computer Applications, 2013
Segmentation on Computed Tomography (CT) image of heart and brain can be optimally posed as Bayes... more Segmentation on Computed Tomography (CT) image of heart and brain can be optimally posed as Bayesian labeling in which the segment of a image is defined as the maximum a posteriori (MAP) probability estimate of the true labeling. The Simulated Annealing (SA) algorithm is used to minimize the energy function associated with MRF posterior distribution function. The goal of this thesis paper is to minimize the energy function using Gaussian distribution and get accurate segmentation by slowly minimize the energy and simultaneously reduce the pixels which have no impact on the image at rapid rate to get the segmentation quickly without degrade the image. The propose algorithm able to get more precise segmentation.
Medical image segmentation is a fundamental task in the medical imaging field. Optimal segmentati... more Medical image segmentation is a fundamental task in the medical imaging field. Optimal segmentation is required for the accurate judgment or appropriate clinical diagnosis. In this paper, we proposed automatically gradient threshold estimator of anisotropic diffusion for Meyer's Watershed algorithm based optimal segmentation. The Meyer's Watershed algorithm is the most significant for a large number of regions separations but the over segmentation is the major drawback of the Meyer's Watershed algorithm. We are able to remove over segmentation after using anisotropic diffusion as a preprocessing step of segmentation in the Meyer's Watershed algorithm. We used a fixed window size for dynamically gradient threshold estimation. The gradient threshold is the most important parameter of the anisotropic diffusion for image smoothing. The proposed method is able to segment medical image accurately because of obtaining the enhancement image. The introducing method demonstrates better performance without loss of any clinical information while preserving edges. Our investigated method is more efficient and effective in order to segment the region of interests in the medical images indeed.
In image processing noise is possibly the most annoying problem. Ultrasound image has been used f... more In image processing noise is possibly the most annoying problem. Ultrasound image has been used for effective diagnosis for its non-invasive, harmless, accurate and cost effectiveness. Unfortunately, ultrasound images are degraded by an intrinsic artefact called speckle. Eliminating such speckle noise is an important preprocessing task. For acquiring a better performance for denoising, an adaptive anisotropic diffusion technique for ultrasound images is presented in this paper. It is a new efficient method for denoising the image without blurring the frontiers between different regions. The proposed noise detection-oriented method is based on the differentiation of the diffusion in the direction of the gradient and the adjacent pixels of entire image. The performance of different metrics shows the proposed method exhibit better result to existing Perona-Malik anisotropic diffusion method.
2012 15th International Conference on Computer and Information Technology (ICCIT), 2012
In this paper we present and evaluate a novel method for an efficient speckle denoising by using ... more In this paper we present and evaluate a novel method for an efficient speckle denoising by using principal component analysis (PCA) with bit plane slicing and nonlinear diffusion. We use PCA transformation for generating de-correlated dataset from a noisy image. Then we apply bit plane slicing on the de-correlated dataset and nonlinear diffusion is applied on each bit plane. For nonlinear diffusion in each bit plane level, a gradient threshold is automatically estimated. Add up all bit plane slice after nonlinear diffusion execution and then we implement inverse principal component analysis for making denoised images. The proposed speckle reduction method could improve image quality and the visibility of small structures and fine details in medical ultrasound imaging compared with state-of-the-art speckle denoising algorithms.