Performance Analysis of SWT-SVD Based Robust Blur-Invariant Copy-Move Forgery Detection Technique

Abstract

The utilization of advanced pictures has expanded in the course of recent years to spread a message. This expands the need of picture authentication. But Preserving picture genuineness is exceptionally mind boggling on the grounds that effortlessly accessibility of picture altering programming. Majority of the existing copy-move forgery detection algorithms operate based on the principle of image block matching. However, such detection becomes complicated when an intelligent adversary blurs the edges of forged region(s). To solve this problem, the authors present a novel approach for detection of copy-move forgery using stationary wavelet transform (SWT) which, unlike most wavelet transforms (e.g. discrete wavelet transform), is shift invariant, and helps in finding the similarities, i.e. matches and dissimilarities, i.e. noise, between the blocks of an image, caused due to blurring. The blocks are represented by features extracted using singular value decomposition (SVD) of an image. We used blur images for detection of forgery part. Previous techniques are having drawbacks of shift variant. Performance analysis of proposed technique is compared with existing technique. Finally I got the performance  of proposed work is better compared with all other state of art block based  techniques and key point based techniques.