FAST MEDICAL IMAGE DENOISING USING LATEST GPGPU TECHNOLOGY

Abstract

 Obtaining high quality images MR is desirable not only for accurate visual assessment but also faurautomic processing to extract clinically revelent parameters If real-time image processing is required, power and size requirements go up as large data processing computers are required to keep pace with the data. In this paper ,we propose using desktop Graphics Processing Units (GPUs) to shrink the Size, Weight and Power (SWaP) pyramid. Image filtering is one of the most important parts in the image-processing. It takes much more time to performance the convolution in image filtering on CPU since the computation demanding of image filtering is massive. Contrast to CPU, GPU may be a good way to accelerate the image filtering. CUDA(Compute Unified Device Architecture) is a parallel computing architecture developed by NVIDIA. This paper implements the Bilateral filter, using CUDA enhanced parallel computations. The Bilateral filter allows smoothing images, while preserving edges, in contrast to e.g. the Gaussian filter, which smoothes across edges. While delivering visually stunning results, Bilateral filtering is a costly operation. Using NVidia's CUDA technology the filter can be parallelized to run on the GPU, which allows for fast execution, even for high definition images. In this paper the limitations of bilateral filter is avoided by using NLM filter. Also KLM filter is introduced with NLM filter which increases the frame rate of the filtered image.

Authors and Affiliations

Madhuri K. Ninawe*

Keywords

Related Articles

 To Enhance the Effort Estimation Accuracy of Cocomo Model Using Function Point

 Effort estimation means to estimate the efforts according to the expectations of stakeholders before implementation of the project. There are many top-down and bottom-up approaches that are recommended by stakeho...

 Process Re-Engineering of Automobile Truck Frame Assembly on Conveyor Line

 Assembly lines are traditional and still attractive means of mass and large high capital requirements when installing or redesigning a line, configuration planning is a great relevance for practitioners. The evid...

 Retrieving Best Web Pages Using Genetic Algorithm

 This paper is concerned with extraction of top web pages from the search engine. We use an effective algorithm for extracting the target file from the search engine. The majority of search engines like Google prov...

L-SASAKIAN MANIFOLDS WITH SEMI-SYMMETRIC CONNECTION

The purpose of this paper is to study Lorentzian Sasakian manifolds [1] and generalized Lorentzian Co-symplectic manifolds [2] with semi-symmetric connection [3] [4].

 ARM 11 Based Advance Safety System in Vehicle

 Now a days, Most of the accidents on the roads are caused by driver faults, inattention and low performance. The proposed system aims at developing Safety system for accidental monitoring of vehicle based on ARM...

Download PDF file
  • EP ID EP142994
  • DOI -
  • Views 58
  • Downloads 0

How To Cite

Madhuri K. Ninawe* (30).  FAST MEDICAL IMAGE DENOISING USING LATEST GPGPU TECHNOLOGY. International Journal of Engineering Sciences & Research Technology, 4(7), 1103-1112. https://europub.co.uk/articles/-A-142994