An Efficient Approach with Contourlet and Curvelet Transformation for Image Fusion Rohit Dubey Student (Department of Information security), Chandigarh Engineering College, Landran,India Manish Mahajan Associate Professor(Department of IT) Chandigarh Engineering College, Landran , India Abstract : Image fusion is the process in which we combine two or more images or some features of images to form a single image which is free from distortion and does not loses its information. Images which are taken from different angles sometimes needs to be fused together to form a single image which has all the detail information to create accurate description of the image. Its application lie for medical imaging, satellite images, general photography etc. Nowadays, medical image fusion plays a vital role for diagnosis. There are number of issues related to image fusion that needs to resolved. None of single method can work as generalized for image fusion. In the current paper we are going to hybrid two methods: contourlet transformation and curvelet transformation for better fused images. KEYWORDS : Image Fusion, contourlet transformation, curvelet transformation I. INTRODUCTION Image fusion is a technique in which different images are fused together to form a single image which contains the detailed information of the images. The primary requirement of a good image fusion technique is that the fused image should be free from distortion and there should not be any lose of information [1]. The image formed after fusion should describe the image more accurately than the source image and is more easily understandable to human visual [7]. The resultant image has characteristics of spatial and spectral resolution. In medical images, images of same part can be taken from different sources like MRI, X-rays or CT scans etc and with the help of image fusion we can provide a single image of these images which has all the vital information from the source images and removing irrelevant data. A. General Image fusion process Feature Extraction: During image fusion feature extraction is the first step; in this step features or objects are detected either manually or automatically. The process can be accomplished using different frequency domains. Feature matching: The next step is feature matching, in this step features are matched and reference image is established. The matching algorithm used should be robust and efficient. Transform model estimation: This is the third step in which, estimation is made about the mapping functions that are used to align the sensed image with the reference image. Image re-sampling and transformation: Finally, the choice of the appropriate type of resembling technique depends upon the trade- off between the demanded accuracy of the interpolation and the computational complexity. International Journal of Latest Trends in Engineering and Technology (IJLTET) Vol. 4 Issue 2 July 2014 137 ISSN: 2278-621X