A Comparative Study of Traditional Image Fusion Techniques with a Novel Hybrid Method

摘要

With an expansion in the progress of sensing devices and technology, additional data is getting accessible to the user which increases the human amount of work. It becomes strenuous for human operator to simultaneously analyze, operate, and depict information from different images, leading to image fusion techniques. Image fusion comprised fusing of source images in such a manner that lead to maximizing the relevant information and reducing the redundancy. Image fusion technique can be used in various fields but image processing is an emerging field. In image processing, various techniques like Intensity Hue Saturation (IHS), Weighted Average, Principal Component Analysis (PCA), and Discrete Wavelet transform (DWT) are used. In this paper, the hybrid fusion technique is proposed using DWT and PCA which are analyzed on CT and MR images of Brain. The results of different techniques used for image fusion are discussed and compared with the proposed algorithm. The techniques are evaluated using various evaluation metrics and the proposed technique results in maximum spectral detail.