With advancements in technology, it is attainable to form illustration of human faces in an exceedingly seamless manner for pretend media, leverage the large-scale accessibility of videos. These pretend faces may be wont to conduct personation attacks on the targeted subjects. Availableness of ASCII text file computer code and a spread of business applications provides a chance to get pretend videos of a selected target subject during a few ways in which. In this article, we have a tendency to judge the generalizability to benchmark the detection ways through a series of studies to benchmark the detection accuracy. To this extent, we have collected a new database of more than 50,000 images, from non-copy websites, originating from multiple sources of digitally generated fakes including computer graphics image generation and many tampering based approaches. In addition, we have also used video modified by apps that is commonly available on smart phones. Extensive experiments are carried out using both textures based handcrafted detection and using CNN method to find the suitability of detection methods. Through this we can detect the fake faces through CNN method. detect a fake face which looks like realistic. We take a huge dataset of images and normalize them. So, we have collected a huge number of celebrities photos from Internet and from that we would like to detect a fake face from the images. So that the fake face will detect from the faces. Keywords: Fake face, Dataset, Detection CNN.
• Hardware: Processor: i3 ,i5 RAM: 4GB Hard disk: 16 GB • Software: operating System : Windws2000/XP/7/8/10 Anaconda,jupyter,spyder,flask Frontend :-python Backend:- MYSQL
₹10000 (INR)
NON IEEE -2021