Forgery Detection in Medical Image and Enhancement using Modified CLAHE Method

Abstract

Health care system is one of the country's most important and delicate sectors. Our key priorities are security and privacy as the healthcare sector expands. The method of Forgery detection in medical image needs more attention in order to gain patient's trust and reduce the likelihood of providing the wrong medicine. These advancements have the potential to render the healthcare system dependable, safe, and easy to utilize in real-time. The suggested process involves different algorithms like Weber Local Descriptor (WLD), Local Binary Pattern (LBP), Scale-Invariant Feature Transform (SIFT) key points and region information. Invariant features are extracted from a picture using SIFT, and subsequently blocks are extracted using Principal Component Analysis (PCA). The PCA algorithm creates a fresh collection of variables known as principal components. Output images are produced using SVM (Support Vector Machine) and ELM (Extreme Machine Learning). Additionally, segmentation techniques can be utilized to compare and find any forgeries. This approach is a part of smart healthcare framework which can determine whether outsiders or hackers have altered the medical data. If the data has been altered, it will indicate the locations where the data has been falsified and image will then be enhanced using the Contrast Limited Adaptive Histogram Equalization (CLAHE) approach.