- 31 min ago Xiaomi Smarter Living 2020 Event: Watch The Launch Of Mi Band 4, Mi TV 65-inch, & Mi Water Purifier
- 34 min ago Realme X2 With 64MP Quad Rear Cameras To Be Launched On September 24
- 4 hrs ago Smart Bulbs To Buy In India: Philips, Syska, Mi, Wipro And More
- 7 hrs ago Most Trending Smartphones Of Last Week: iPhone 11 Pro, Mi A3, Galaxy A50, Nokia 7.2 And More
- News Artificial Intelligence, Drones all set to digitally map India
- Finance Petrol, Diesel Prices Hiked In India After Crude Oil’s Record Surge
- Lifestyle Disha Patani Looks Ravishing In Green Eye Make-up Look; Here Is How You Can Get This Look
- Movies Angad Bedi Talks About Ex-GF Nora Fatehi: The Partner She Deserves Will Come Her Way Very Soon
- Sports PSG vs Real Madrid: Three key battles
- Automobiles KTM Duke 790 Launch Date Confirmed For India: Here’s Everything You Need To Know
- Education AP Grama Sachivalayam Result 2019 Likely To Be Declared Soon
- Travel Cycling for beginners: The basics any beginner cyclists should know
AI Cameras Might Help Curbing Fake Image Circulation
Picking a fake photo is a tough task and even after recognizing the details, some pictures manage to fool the experts. Wouldn't it be really convenient if the process of picking fake pictures started from the source, the camera? Well, that's what a new study from New York University Tandon School of Engineering suggests.
What's new this time
If the cameras become intelligent, it could help additional machine learning programs to identify if the image was morphed. The researchers also found out that the technique amplified a computer's accuracy at spotting fakes from 45% to 90%.
The new method involves reimaging the way a camera will process information to expose a picture. The camera creates unique artifacts in the image that software can later use to gauge whether or not the image was altered.
Unlike the conventional methods, the software won't be tricked if the image is downsized, the researchers said. When added to the photo itself, AI programs for detecting manipulated programs were able to be more precise over earlier used techniques.
What's the catch
It seems practical, however, the trade here is that the artifacts which serve as a digital watermark, degrade the image quality. While the camera and lens makers try to reduce artifacts, the researchers have built them again.
The team said that their future studies will look for ways to incorporate these digital watermarks without degrading the quality of the image. Also, to use this method, camera makers will have to agree on implementing the artifacts into their equipment.
With the manufacturers poised at producing great cameras with increased quality with every new model, adding artifacts on purpose seems like a dealbreaker for many.
Do we need such technology
Of course, we do. Identifying fake images using software instead of a human eye will curbing the fake images circulating over the web. Social media is the most affected place due to the circulation of fake images. The method can also be added to these platforms to reduce fake news.