AI ‘Ghost Imaging’ can Make Up Images that You Haven’t Seen

AI ‘Ghost Imaging’ can Make Up Images that You Haven’t Seen
Published on

The AI technique known as ghost imaging can be combined with human vision to image an object.

Artificial intelligence can use your brainwaves to see around corners. The technique is called "Ghost Imaging (GI)". It is often called cloning, which is a software-driven data backup process that copies the contents of a computer hard disk in a single compressed file or set of files, referred to as an image. And it is the process of creating data images of the content and configuration of a computer, server, or similar device.

Researchers have shown that the computational imaging technique known as ghost imaging can be combined with the human vision to image an object that can't directly be seen by the person. Its AI system Imagen creates photorealistic images from input text. It can reconstruct the basic details of objects hidden from view by analyzing how the brain processes barely visible reflections on a wall.  Ghost imaging is also known as data imaging, disk imaging, or computer imaging.

A Ghost Imaging system that reads the brainwaves of a person:

Researchers at the University of Glasgow have demonstrated a "Ghost Imaging" system that reads the brainwaves of a person looking at light scattered off a wall to identify an object around a corner. The researchers performed a comparative study on the base of several challenging real-world scenarios including a flying drone, and demonstrate that the proposed method outperforms other widespread Ghost Imaging methods. This is an entirely new visual phenomenon and provides a new tool to study the visual system.

Ghost imaging has been used before to reveal objects hidden around corners. Although the researchers previously passively used human vision to perform ghost imaging, the new work uses the human visual system in an active role by having a person view the light patterns instead of a camera. The GI has little relevance for human perception since the human visual system must be incapable of processing this kind of data. This is one of the first times that computational imaging has been performed by using the human visual system in a neurofeedback loop that adjusts the imaging process in real-time.

The researchers showed that their technique could successfully reconstruct 16 x 16-pixel images of simple objects that could not be seen by the observer. The technique relies on clever algorithms to crunch the seemingly random data that a single pixel appears to gather. Repeating this process with different random patterns of light produces a sequence of data points about how the light intensity varies over time. GI requires no additional viewing screen or computational steps.

GI with the eye opens up several completely novel applications such as extending human vision into invisible wavelength regimes in real-time. Ghosting can save hours of setup time compared with loading programs from scratch, and it reduces errors in the process. It is much faster than installing each machine separately, especially if it involves installing many applications. Considering that Ghost Imaging is a promising method for long-distance imaging, the proposed method has great potential for high-resolution remote sensing.

More Trending Stories 

Join our WhatsApp Channel to get the latest news, exclusives and videos on WhatsApp

                                                                                                       _____________                                             

Disclaimer: Analytics Insight does not provide financial advice or guidance. Also note that the cryptocurrencies mentioned/listed on the website could potentially be scams, i.e. designed to induce you to invest financial resources that may be lost forever and not be recoverable once investments are made. You are responsible for conducting your own research (DYOR) before making any investments. Read more here.

Related Stories

No stories found.
logo
Analytics Insight
www.analyticsinsight.net