INTRO: Since the development of Artificial intelligence there have been numerous experiments like, from traffic surveillance to analyzing human traits, Artificial Intelligence is everywhere now and used in the majority of places. but, this technology has been used the most for face recognition and image enhancement purposes for now. A team of researchers from the Duke University of North Carolina has created an AI algorithm that can create an HD image from a low-res, pixelated picture.
The Artificial Intelligence algorithm, PULSE is created by a group of researchers from Duke University and it is designed to create an HD (High Definition) image of a face from a 16 x 16 pixelated picture which is quite a low pixel. Don’t expect the AI to find the exact face underneath that pixelated input image. But this algorithm comes up with a new face each time it performs the extraction process. According to the research team, the output image is 60x sharper than the original image with clarity.
Now, the way PULSE the AI algorithm work is using an unusual method of backward image processing behind it. Difference by the others, image-enhancing AI models that begin with a low-resolution (LR) image and if guessed its way to create a high-res (HR) one, PULSE starts off with a High-Resolution image and matches it with the Lower Resolution input image. The research team also used another machine learning to trick called the generative adversarial network (GAN) that uses the two neural networks that are trained on the same dataset of photos, to create true-to-life results.
Although Artificial Intelligence is pretty efficient in creating high-resolution pictures from the unrecognizable images, it is not that useful as it does not reveal the actual face of the person in the input image. But, if this AI can be used for enhancing medical images or images from the satellites, it would be pretty useful for all of us in the way of technological advancement.