Publications by authors named "Suganthi St"
PeerJ Comput Sci
February 2022
Article Synopsis
- Deep Learning is widely used in areas like natural language processing and computer vision, and it plays a key role in creating deep fakes, which are manipulated images that can be hard for humans to detect.
- The main challenge with current detection methods is their inaccuracy and high processing time, making it crucial to improve these techniques.
- This study focuses on detecting deep fake images by implementing Fisherface combined with Local Binary Pattern Histogram (FF-LBPH) and using Deep Belief Networks (DBN) with Restricted Boltzmann Machines (RBM) as a classifier, utilizing public datasets like FFHQ and CASIA-WebFace.
