A Novel Gray Image Enhancement Using the Regional Similarity Transformation Function and Dragonfly Algorithm

Abstract

Image enhancement is a necessary and indispensable technique for increasing the quality of digital images. The main task is to generate a new intensity value for each pixel in the image using a transformation function after the input image receives the intensity value of each pixel. The proposed transfer function in this study is called the Regional Similarity Transfer Function (RSTF) that considers the density distribution similarity between adjoining pixels. Dragonfly Algorithm (DA) intuitive optimization technique, which is preferred in engineering applications, has been used to optimize the parameter values of the proposed transfer function. Image quality evaluation is performed with six criteria between the improved and original images. Our experimental results show that the intensity distribution between adjoining pixels show an increase in contrast and brightness over the similarity degree. Excessive brightness, blur, and deterioration in the images is resolved with the proposed method.

An Approach for Enhancement of MR Images of Brain Tumor

“…The performance has been evaluated for direct visual inspection and quantitative analysis of glioma, meningioma, and pituitary tumors. The proposed method is compared with CLAHE with Median filter [46], CLAHE with Wiener filter [25], Decorrelation [47], Enhancement Gravitational Search Algorithm (EnhGSA) [48], Median Mean based Sub Image Clipped Histogram Equalization (MMSICHE) [49], Variational based Fusion model for Gray Scale image Enhancement (VFGLE) [50], and Bi-Histogram Equalization with Adaptive Sigmoid Function (BEASF) [40]. The visual comparison of the proposed method with other state-of-the-art methods by taking an image from three different type of tumors, shown in Figure 1.…”