9. Classification of various image fusion algorithms and their performance evaluation metrics

Abstract

Image fusion is the process of enhancing the perception of a vision by combining substantial information captured by different sensors, different exposure values, and at different focus points. Several images captured from different sensors like infrared region and visible region, positron emission tomography scan, and computed tomography, Multifocus images with different focal points, and images taken by static camera at different exposure values. Most promising area of image processing nowadays is image fusion. The picture fusion method seeks to incorporate two or more pictures into one picture that contains better data than each source picture without adding any artifacts. In distinct apps, it plays an essential role, namely medical diagnostics, pattern detection and identification, navigation, army, civilian surveillance, robotics, and remote sensing satellite images. Three elements are taken into consideration in this review document: spatial domain fusion methodology, different transformation domain techniques, and image fusion performance metrics like entropy, mean, standard deviation, average gradient, peak signal-to-noise ratio, and structural similarity index (SSIM). Many image fusion applications are explored in this chapter.