Image Forgery Localization using Image Patches and Deep Learning

Due to the broad accessibility of camera systems, photographing has grown in popularity. Photos seem to be significant in our daily lives since they carry a plethora of data, and it is frequently necessary to improve photographs to acquire greater information. Although many technologies are available to enhance the images, these are also often utilized to fabricate photos, leading to the spreading of disinformation. Image forgeries are becoming a serious topic of concern. To locate image forgeries, several conventional frameworks have been developed in the past. Convolutional neural networks (CNNs) have garnered much popularity in recent years, and CNN's have influenced image forgery localization. One of the most difficult images forgery types is image splicing, in which a part of an image is copied into another image. Image forgery localization techniques that exist in the literature have some limitations. Hence, it is essential to develop a technique for effectively and accurately locating forgeries in the tampered images. We present a strong deep learning-based approach for detecting forgery in an image by using image patches. A patch is taken around it to classify a pixel in an image, which is passed to a CNN to predict whether the pixel belongs to the tampered region. The proposed method efficiently predicts the boundary pixels of the tampered region and the background image. The technique has been rigorously evaluated, and the experiment results obtained are extremely encouraging on CASIA 2.0 database.