COMPARATIVE STUDY OF ITERATIVE BACK PROJECTION AND DISCRETE ALGEBRAIC RECONSTRUCTION TECHNIQUE FOR RECONSTRUCTION OF LOW RESOLUTION IMAGES

Abstract

This paper presents a comparison between Iterative Back Discrete Algebraic Reconstruction Technique (DART). In this experiment, images were acquired using a digital camera of 5Mega Pixel (MP). A total of 50 images were used. The Images were degraded by introducing noise, blur and shift in a images which were converted to grey scale. The techniques were evaluated using Peak Signal to Noise Ratio and Mean Square Error. The average Peak Signal to Noise Ratio (PSNR) gotten for IBP is 82.425 Square Error (MSE) gotten for IBP is 0.00077 while the average PSNR obtained for DART is 71.7025 and the MSE obtained is 0.00479. The experimental results suggest that IBP performs better than DART in reconstructing low resolution ima FJPAS Vol 2(1) ISSN: 2616 60 STUDY OF ITERATIVE BACK PROJECTION AND DISCRETE ALGEBRAIC RECONSTRUCTION TECHNIQUE FOR RECONSTRUCTION OF LOW RESOLUTION IMAGES Olabiyisi Stephen O., 1 Omidiora Elijah O., 2 Fagbola Temitayo M., 1 Adeyemo Temitope T. science and Engineering, Ladoke Akintola University of Technology, Ogbomoso, Nigeria Dept. of Computer Science, Federal University Oye Ekiti, Ekiti State, Nigeria. Image processing is a method employed to convert an image into digital form and perform some operations on it, in order to get an enhanced image or to extract some useful information from gnal dispensation in which input is image, like video frame or photograph and output may be image or characteristics associated with that image. Usually image processing system includes treating images as two dimensional signals while applying already set signal processing methods to them. processing can be done using analog or digital methods. Analog methods can be used for hard copies like printouts or photographs while digital processing technique helps in the manipulation of digital images by using computers [1]. Digital image processing is used to extract useful information from a given image of low quality. High resolution (HR) means that the pixel density within an image is high, and therefore an HR image can offer more details that may be criti Journal of Pure and Applied Sciences Available online at www.fuoye.edu.ng This paper presents a comparison between Iterative Back Discrete Algebraic Reconstruction Technique (DART). In this experiment, images were acquired using a digital camera of 5Mega Pixel (MP). A total of 50 images were used. The Images were degraded by introducing noise, blur and shift in angle. DART and IBP were used to reconstruct the degraded images which were converted to grey scale. The techniques were evaluated using Peak Signal to Noise Ratio and Mean Square Error. The average Peak Signal to Noise Ratio (PSNR) gotten for IBP is 82.425 Square Error (MSE) gotten for IBP is 0.00077 while the average PSNR obtained for DART is 71.7025 and the MSE obtained is 0.00479. The experimental results suggest that IBP performs better than DART in reconstructing low resolution images.