ISSN (Print) : 2319-5940 ISSN (Online) : 2278-1021 International Journal of Advanced Research in Computer and Communication Engineering Vol. 2, Issue 4, April 2013 Copyright to IJARCCE www.ijarcce.com 1896 Image Processing Tasks using Parallel Computing in Multi core Architecture and its Applications in Medical Imaging Sanjay Saxena¹, Neeraj Sharma², Shiru Sharma³ Research Scholar, School of Biomedical Engineering, IIT (BHU), Varanasi, UP, India¹ Associate Professor, School of Biomedical Engineering, IIT (BHU), Varanasi, UP, India² Assistant Professor, School of Biomedical Engineering, IIT (BHU), Varanasi, UP, India³ Abstract: To find accurate & reliable result in image analysis, it is important that image is processed and analyzed using image processing suitable AI technique further at the same time it is highly desired that processing time must be minimum. Preprocessing of the image makes it more clear and visible, while parallelizing of the algorithm optimizes the speed at which the image is processed. This paper explores current multi-core architectures available in commercial processors in order to speed up the image processing tasks. Parallel Implementation of Many sequential algorithms of Image processing was examined and analyzed in test and achieved good result if all the recourses are efficiently used. Main objective of this paper is to design some parallel image processing algorithms like segmentation, noise reduction, features calculation, histogram equalization etc by using Multi Core architecture and comparative study with some sequential image processing algorithm. These parallel algorithms are able to work with different number of thread, so as to take all the benefits of the upcoming processors having any number of cores. As medical imaging refers to view the human body in order to diagnose, monitor and treatment planning. This paper also describes the application of parallel computing applied in different Medical Imaging techniques like CT, PET scans etc. Keywords: Parallel Computing, Image Processing, Histogram, Multi Core, CPU, Latency, CT, PET. I. INTRODUCTION Image is the 2 dimensional distributions of small image points called as pixels. It can be considered as a function of two real variables, for example, f(x,y) with f as the amplitude (e.g. brightness) of the image at position (x,y). Image Processing is the process of enhancing the image and extraction of meaningful information from an image. Image processing is gaining larger importance in a variety of application areas. Active vision, e.g. for autonomous requires substantial computational power, in order to be able to operate in real time[1]. According to Jain [3], digital image processing consists of the application of functions that transform a two dimensional image using a computer. Others authors as Crane [4] define this task as a science that manipulates digital images that covers an extend set of techniques to enhance or distort them. Medical imaging is the technique and process used to create images of the human body (or parts and function thereof) for clinical purposes or medical purpose [5]. There are so many different medical image modality are present like CT, PET, MRI etc. These Modalities are having different characteristics and used as per requirements. Because size of these images are very large so for analysing these modalities take so much time to process sequentially and give result after some time. So if we divide this sequentially processing to efficient parallel processing than we can find good result in very reasonable time or if we are able to process basic steps like Image Enhancement, Morphological operation, feature calculation quickly than it will be beneficial for the medical practitioner. So by the parallel computing we can save time and/or money, we can solve larger problems in very short time periods. Parallel computing provides concurrency and by this we can use non – local recourses very efficiently. It also removes the limit of serial computing. Matlab 2010a onwards finally enables the „Parallel Computation Toolbox‟ for student use. It‟s not part of the core Matlab student package, but it is now available as