COMPARISION OF PREPROCESS TECHNIQUES FOR BRAIN IMAGE USING MACHINE LEARNING

Abstract

A brain tumour is the second leading cause of death in young people.. Tumors of the brain come in a wide range of shapes and sizes. Noncancerous brain tumour exist alongside cancerous brain tumors. In medical image processing, detecting and segmenting brain tumors is extremely difficult. Four forms of preprocessing are used here: Adaptive Median Filter (AMF), Median Filter, Gaussian Filter and Wiener Filter. The performance metrics were then determined using the following

1.The Mean Square Error Rate (MSE) is a measurement of a system's accuracy.

2.Signal-to-Noise Ratio at Peak (PSNR)

1. Structure Similarity Index

 4.Number four is the Spearman rank correlation. The Adaptive median Filter produces the best results for both regular and abnormal images based on the above measurements.