Due to the supply of deep networks, progress has been created among the sector of image recognition. Pictures area unit spreading really handily and with the supply of robust piece of writing tools the meddling of digital content become simple. To sight such scams, we’ve got an inclination to planned techniques. In our paper, we’ve got an inclination to planned two necessary aspects of exploitation deep convolutional neural networks to image forgery detection. we’ve got an inclination to initial explore and examine fully totally different pre-processing methodology on a aspect convolutional neural networks (CNN) design. Later we’ve got an inclination to evaluated the varied transfer learning for pre-trained Image Net(via-fine tuning) and implement it over our dataset CASIA V2.0. So, it covers the pre- processing techniques with basic CNN model and later see the powerful results of the transfer learning models.

image tampering, convolution neural network (CNN), error level analysis (ELA), sharpening filter.