This document summarizes a research paper that proposes a robust image alignment method for tampering detection using SVM clustering of bag of features. The method first extracts bag of features from an image and clusters them using SVM clustering for effective image alignment. An image hash based on the bag of features is attached to images before transmission. The hash is then analyzed at the destination to detect any geometric transformations applied to the received image and align it to the original for tampering detection. The proposed approach provides good performance compared to state-of-the-art methods in localizing tampered regions through robust image alignment.