Abstract
Conference Title: 2018 IEEE International Conference on Electro/Information Technology (EIT) Conference Start Date: 2018, May 3 Conference End Date: 2018, May 5 Conference Location: Rochester, MI, USA Medical image fusion (MIF), an image viewing technique for diagnostic images, works by reducing uncertainty and redundancy associated with viewing two separate images. The resultant fused image is easier for physicians to interpret than the originals. Even so, current MIF techniques do not always adequately resolve complex textural features or edges in the fused images. In this paper, a novel method using the properties of Gabor filters in combination with fuzzy-based pixel selection methods is described. The proposed method improves the textural properties and edges visualization of the resulting fused image. The approach used takes input images, filter them by Gabor filter, then select based on pixels with higher intensities for fusion using a fuzzy logic algorithm. The resultant images have superior texture and edge resolution when compared with either the original images or fused images created by other algorithms.