International Journal of Engineering and Techniques - Volume 4 Issue 1, Jan – Feb 2018 ISSN: 2395-1303 http://www.ijetjournal.org Page 575 A Study on Image Registration Schemes Dr. R. Kokila Department of Computer Science, JyotiNivascollege, Bangalore I. INTRODUCTION Registration of two dimensional images acquired from the same scene taken at different times, from different geometric viewpoint, or by a different image sensor is a fundamental problem in the image processing. Image registration is the preprocessing step for analysis and fusion of the images. It geometrically aligns two images the reference and sensed images. Image registration is a crucial step in all image analysis tasks in which the final information is gained from the combination of various data sources like in image fusion, change detection, and multichannel image restoration. It is widely used in different fields such as remote sensing for multispectral classification, environmental monitoring, change detection, creating super-resolution images and integrating information into geographic information systems (GIS) [51]. In medical applications it is used for combining computer tomography (CT) and nuclear magnetic resonance (NMR) data to obtain more complete information about the patient, monitoring tumor growth, treatment verification, comparison of the patients data with anatomical atlases. Image registration is also used in cartography for map updating and in computer vision for target localization and automatic control. Image registration can be defined as a mapping between two images both spatially and with respect to intensity. If we define images as two two- dimensional arrays of a given size denoted by I 1 and I 2 where I 1 (x,y) and I 2 (x,y) each map to their respective intensity values, then the mapping between these two images can be expressed as: I 2 (x,y) = g(I 1 (f(x, y))) where f is a two dimensional spatial coordinate transformation, i.e., (x ' ,y ' ) = f(x,y) and g is one dimensional intensity or radiometric transformation. To find the relationship between two images we rely on the estimation of the parameters of the transformation model. Number of parameters depends on the chosen transformation model. A common assumption is that the coordinate transformations between two images are rigid planar models. Rigid planar transformation is composed of scaling, rotation, and translation changes, which map the pixel (x 1 ,y 1 ) of image f 1 to the pixel (x 2, y 2 ) of another image f 2 : RESEARCH ARTICLE OPEN ACCESS Abstract: Computer vision is a field of computer science that includes methods for acquiring, processing, and analysing images. Image registration is one of the methods used in computer vision to transform different sets of data into one coordinate system to align images. Registration is important in order to be able to compare or integrate the data obtained from multiple measurements. In this paper, the related pieces of work done in the field of image registration that are studied in the literature are presented. Keywords —Image Registration, Feature Detection, Fast Fourier Transform.