Analysis and Comparison of Image Enhancement Techniques for Improving PSNR of Liver Image by Mask Filtering over Wiener Filtering

Abstract

Aim: The major purpose of this project is to improve picture enhancement for human viewers in order to improve interpretability or perception of information in images, as well as to give better input for other automated image processing approaches.The scientific images are corrupted by noise, and the images as a whole deteriorate. Edges are suppressed, structural features are blurred, and obstructions are blurred, among other things. Mask Filter and Wiener Filter are two filtering techniques. Materials and methods: Different sources of liver images from the kaggle website were used in this study. The total sample size was computed using clinical.com and the sample sizes were (N=20) for Mask filtering and (N=20) for the Wiener filtering technique. The total number of samples was calculated to be 40 as a consequence. The PSNR was calculated using SPSS Software and a standard data set. Through Matlab coding, both a mask filter and a wiener filter technique were used to enhance liver images, as well as retrieving PSNR values for each image. Then, using the SPSS software, a comparison and analysis were performed. Results: In an image enhancement of the image processing pathway, Wiener filters technique shows the best performance by removing noise to improve PSNR of liver images than mask filtering. PSNR values are compared using IBM-SPSS software and an independent sample test. Between the mask filter and wiener filtering, there is a statistical difference. In comparison to mask filtering, the wiener filtering technique produced greater PSNR (78.3780dB) with (p=0.004) (62.9695dB). Conclusion: Wiener Filtering image enhancement technique provides high PSNR values for different sources of liver images than mask filtering Technique.