Image Fusion Based on Wavelet Transforms

Abstract

The image fusion is the process of combining relevant information from two or more images into a single image. The resulting image will be more informative than any of the input images. A new approach for object extraction from high-resolution images is presented in this report. In this paper, we have presented image fusion based on wavelet transform. Medical Image Fusion is a sort of data fusion and developed from that into a new data fusion technology. As an advanced method of image processing technology to integrate multi-source image data, image fusion is to integrate two or more images into a new fusion image. The aim of fusion is the combination of images to integrate the information of each individual technique and reduce the uncertainty of the image information. Computed tomography (CT), and positron emission tomography (PET) provide data conditioned by the different technical, anatomical and functional properties of the organ or tissue being studied, with values of sensitivity, specificity and diagnostic accuracy variations between them. Their fusion enables the unification of the various technique-dependent data, thus summing the diagnostic potential of each individual technique. Because of the image fusion technology which can effectively integrate the image information, the fusion images are more intelligible and readable and have more information than the images that are got through single channel, and this technology has been concentrated very much, and has had a great development. Truly the image fusion is the process of combining relevant information from two or more images into a single image. The resulting image will be more informative than any of the input images. A new approach for object extraction from high-resolution images is presented in this report. In this we present a new approach to better extract information from CT (Computed Tomography) /PET (positron emission tomography) which will be helpful to diagnose diseases. Since there are various methods and algorithms for fusion of these images and as there are special advantages for each algorithm along with ever growing need to use of this technique, as a result research about this field of study becomes more sophisticated. Many methods exist to perform image fusion. The very basic ones are the Probabilistic Approximation model. The wavelet approach gives better accuracy and increased information compared to the previous techniques.