With technology at its forefront, it has become even easier in this day and age to generate extremely realistic-looking fake videos of people. Using advanced image journaling tools, one can now easily alter the semantic meaning of images by using manipulation techniques like copy clone, object splicing/removal, which can mislead the viewers. One of the gravest and notorious examples of this sort of tampering is Deepfakes. This has also become a growing concern in today’s society.
A team of Indian-origin researchers have created Artificial Intelligence based deep neural network system that can identify the manipulated images at the pixel level with higher accuracy. Dr. Amit Roy-Chowdhury, professor of electrical and computer engineering at the University of California (UCR), Riverside, has developed a high-confidence manipulation localisation architecture which utilises resampling features, LSTM cells, and an encoder-decoder network to segment out manipulated regions from non-manipulated ones. His group is involved in research projects related to camera networks, human behavior modeling, face recognition, and bioimage analysis.
According to Dr. Amit, “We trained the system to distinguish between manipulated and nonmanipulated images, and now if you give it a new image it is able to provide a probability that that image is manipulated or not, and to localise the region of the image where the manipulation occurred”.
A deep neural network is what AI researchers call computer systems that have been trained to do specific tasks, in this case, recognize altered images. These networks are organized in connected layers; "architecture" refers to the number of layers and structure of the connections between them. While this might fool the naked eye, when examined pixel by pixel, the boundaries of the inserted object are different.
Dr. Roy-Chowdhury leads the Video Computing Group at UCR, with research interests in computer vision, image processing, and statistical pattern recognition and signal processing. He is the first author of the book Camera Networks: The Acquisition and Analysis of Videos Over Wide Areas, the first monograph on the topic. His work on face recognition in art was featured widely in the news media, including a PBS/National Geographic documentary and in The Economist. He is on the editorial boards of major journals and program committees of the main conferences in his area. He is a Fellow of the IAPR.