Detection Of Image Forgery Using Error Level Analysis

Image forging is the manipulation of digital images using methods like copy-move, splicing, image removal etc. This paper provides an overview of the system’s architecture, highlighting the integration of digital image processing, OpenCV, and machine learning algorithms Image forgery detection is the process of identifying a modified image from the original. In the realm of digital image processing, image forgery detection is a critical task. The amount of altered and faked photographs has increased as digital imaging has become more prevalent and is used in a variety of fields, including forensics, media, and scientific study. They must guard the veracity of photos and stop the dissemination of false information and fake news. The detection of picture forgeries, however, is fraught with technological difficulties, including the requirement for reliable and accurate image features, the capacity to differentiate between various types of image alteration, and effective algorithms that can analyze enormous quantities of digital images. To meet these problems, the error level analysis image processing technique and convolutional neural network are used to create a model that can predict the input images as forged ad unforged. The proposed model shows a better performance by giving an accuracy of 87%.