Smile detector developed by the MIT

<![CDATA[<img src=”data:image/svg+xml,%3Csvg%20xmlns=’http://www.w3.org/2000/svg’%20viewBox=’0%200%20450%20329’%3E%3C/svg%3E” alt=”” title=”smile” width=”450″ height=”329″ class=”aligncenter size-full wp-image-68996″ data-lazy-src=”https://www.coolest-gadgets.com/wp-content/uploads/2012/05/smile.jpg” />They say that it is far easier to lie over the telephone compared to a face-to-face meeting, as body language does convey far more hidden messages than you can possibly imagine. How about smiles – when do you know that one of them is genuine, while another smile is but delivered right before you are stabbed in the back? The good people over at the MIT have come up with a smile detector that runs on a computer system, and in the image above, the computer detected that the smile on the right is one that signals frustration hidden behind those forced curved lips.
Most folks think that they do not smile whenever they are frustrated, but the evidence points otherwise. Not only that, the team of researchers over at MIT have also discovered that computers which were specially programmed with the latest research information did outperform human observers when it came to telling the difference between a genuine smile and otherwise. Looks like even our smiles have been broken down into an algorithm – what next, a handshake?
 
This particular piece of research by the MIT team might be the start of something interesting – that is, to utilize computers in order to better assess the emotional states of their users while coming up with an appropriate response. Imagine this – you are at the office, hacking away at the keyboard in thorough frustration while giving that faux smile, and the webcam picks it up before freezing your screen with a pop-up window, asking you to take a 15 minute break while you sort out your emotions as they could collide with your overall work performance. How neat would that be?
Not only that, such a computer system can also be used to help train folks who do experience difficulty in interpreting expressions, including those with autism, in order to more accurately gauge the expressions that they see. Ehsan Hoque, a graduate student in the Affective Computing Group of MIT’s Media Lab, says, “The goal is to help people with face-to-face communication.”
Press Release]]>