2014 International Conference on Computer Communication and Informatics (ICCCI -2014), Jan. 03 – 05, 2014, Coimbatore, INDIA [978-1-4799-2352-6/14/$31.00 ©2014 IEEE] Image Fusion with Biorthogonal Wavelet Transform Based On Maximum Selection and Region Energy Maruturi Haribabu Asst.professor, ECE Department, QIS College of Engineering & Technology, Ongole, India. haribabu.maruturi@gmail.com CH.Hima Bindu Assoc. Professor, ECE department, QIS College of Engineering & Technology, Ongole, India. hb.muvvala@gmail.com Dr.K.Satya Prasad Professor in ECE Department, JNTUK, Kakinada, AndhraPradesh, India. prasad_kodati@yahoo.co.in Abstract— Image Fusion plays major research role in the fields of image processing. Image Fusion is a method of combining the relevant information from a set of images, into a single image, where in the resultant fused image will be more informative and complete than any of the input images. Specifically it serves best in medical diagnosis i.e. Computed Tomography (CT), Magnetic Resonance Image (MRI) scans provide different types of information, by fusion can get accurate information for better clinical diagnosis. The Biorthogonal Wavelet Transform (BWT) is one of the most widely used transform method for fusion. Here this paper discusses the Biorthogonal wavelet transform based image fusion with absolute maximum selection rule and energy based fusion rule. The proposed method analysed both qualitatively and quantitatively among various fusion methods. Keywords- Multimodal & Multifocus images, Image fusion, Biorthogonal wavelet transform. I. INTRODUCTION Any piece of information makes sense only when it is able to convey the content across. The c1arity of information is important. Image Fusion is a method to improve the visual quality of information by the process of fusion of the given images to form a resultant image whose quality is superior to any of the input images [1, 2]. Hence the Image fusion is the process of integrating all relevant and complementary information from different source images into a single composite image without introducing any artifact or noise [4]. For Instance, doctors can annually combine the CT and MRI medical images of a patient with a tumour to make a more accurate diagnosis. Thus, it is necessary to develop the efficiently automatic image fusion system to decrease doctor’s work and improve the consistence of diagnosis [1, 2, 3]. Image fusion can be performed at three levels – pixel level [5, 8], feature level [6, 8] and decision level [7, 8]. Pixel level fusion deals with information associated with each pixel and fused image can be obtained from the corresponding pixel values of source images. In feature level fusion, source images are segmented into regions and features like pixel intensities, edges or texture, are used for fusion. Decision level fusion is a high level fusion which is based on statistics, voting, fuzzy logic, prediction and heuristics, etc. Pixel level fusion is advantageous over the other fusion schemes as it uses original (pixel values) information of images and can be performed both in spatial and transform domains. Spatial domain fusion directly operates on the pixels of the source images. Averaging, principal component analysis (PCA) [9], Brovey transform and IHS (Intensity hue saturation) [10] based fusion methods fall under this category. One of the major disadvantages of spatial domain fusion methods is that it introduces spatial distortions in the resultant fused image and does not provide any spectral information. These disadvantages were overcome with the use of transform domain image fusion methods. Rest of the paper is organized as follows: Constructions and properties of BWT are described in Section II. Section III explains the proposed fusion method. Experimental results and performance evaluations are given in Sections IV and V respectively. Finally, conclusions of the work are given in Section VI. II. BIORTHOGONAL WAVELET TRANSFORM The orthogonal filter of wavelet transform does not have the characteristics of linear phase. Therefore, the phase distortion causes to the distortion of the image edge. To nullify this, the biorthogonal wavelet with linear phase characteristic is introduced. In many filtering applications we need filters with symmetrical coefficient to obtain linear phase. None of the orthogonal wavelet systems, except Haar, have symmetrical coefficients. Biorthogonal wavelet system can be designed to achieve symmetry property and exact reconstruction by using two wavelet filters and two scaling filters instead of one [11, 12, 3]. Biorthogonal family contains biorthogonal compactly supported spline wavelets. With these wavelets symmetry and perfect reconstruction is possible using FIR (Finite Impulse Response) filters, not with orthogonal filters (except for the Haar filters). The biorthogonal family uses separate wavelet and scaling functions for the analysis and synthesis of image. The reverse biorthogonal family uses the synthesis functions for the analysis and vice versa [3].