Images are often manipulated with the intent and purpose of benefiting one party. images are often seen as evidence of a fact or reality, therefore, fake news or any form of publication that uses images that have been manipulated in such a way has the greater capability and potential to mislead. The web permits clients to process any type of digital media within seconds all over the globe. With expanding utilization of digital multimedia contents like pictures and video, the techniques for detecting the digital image forgery have also increased parallelly. people tamper with images to make the image look more pleasant for appearance but it is susceptible if one changed someone’s face within the image and misuses it. Hence this demands automatic tools for identifying the difference between authentic and tampered images. To detect such image falsification, a large amount of image data is required, and a model can process each pixel in the image. In addition, efficiency and flexibility in data training are also needed to support its use in everyday life. The concept of big data and deep learning is the perfect solution to this problem. Therefore, with an Error Level Analysis (ELA), Convolutional Neural Network (CNN)