Analysis Of Various Quality Metrics for Medical Image Processing

Abstract—This paper presents the comparative analysis of various quality metrics for medical image processing. Measurement of image quality is important for many image processing applications. Image quality assessment is closely related to image similarity assessment in which quality is based on the differences (or similarity) between a degraded image and the original, unmodified image. Objective methods have been used for expressing the image quality because these are automatic and mathematically well defined procedure unlike subjective methods which are expansive, time consuming and observer dependent. In this work images have been subjected to various degrees of blur, noise, compression and contrast levels and quality has been measured in terms of well known metrics such as Mean Squared Error (MSE), Structural Similarity Index Metrics (SSIM) Peak Signal-to-Noise Ratio (PSNR), Maximum difference (MD), etc.