Abstract

Nowadays, many false images are spreading in digital media. The detection of these false images is inevitable for the unveiling of image-based cybercrimes. Forging images and identifying such images are promising research areas in this digital era. Altered images are detected using a neural network that also recognizes the regions of the image that have been manipulated and reveals the segments of the image. This original can be implemented on the Android platform and therefore made available to ordinary users. The compression ratio of foreign content in a false image is different from that of the original image and is detected using an error level analysis. The another function used with compression ratio is image metadata. Although it is possible to modify the metadata content, which makes it unreliable, here it is used as a support parameter for an analysis of the decision error level.