Detection and Localization of Multiple Image Splicing Using MobileNet V1

In modern society, digital images have become a prominent source of information and medium communication. They can, however, be simply altered using freely available image editing software. Two or more are combined to generate new that can transmit across social media platforms influence the people in society. This may both positive negative consequences. Hence there is need develop technique will detect locates multiple splicing forgery an image. research work proposes detection Mask R-CNN, with backbone as MobileNet V1. It also calculates percentage score forged region spliced images. The comparative analysis proposed variants ResNet performed. model trained tested our MISD (Multiple Image Splicing Dataset), it observed outperforms models (ResNet 51,101 151).