Thursday December 12, 2019
Home Lead Story Computer Can ...

Computer Can Now Reveal Your Fake Facial Expressions

According to the researchers, in fake smiles it is often only the mouth muscles which move but, as humans, we often don’t spot the lack of movement around the eyes. The computer software can spot this much more reliably

0
//
Shanghai,
A U.S. Customs and Border Protection facial recognition device is ready to scan another passenger at a United Airlines gate (Representational image). VOA

Real and fake smiles can be tricky to distinguish, but researchers have now developed a computer software that can spot false facial expressions.

By analysing the movement of the smile across a person’s face, the software can determine whether or not the expression is genuine, said the study published in journal Advanced Engineering Informatics.

The most significant movements detected by the software were around the eyes, supporting popular theories that a spontaneous, genuine smile is one that can be seen in a person’s eyes.

“Techniques for analysing human facial expressions have advanced dramatically in recent years, but distinguishing between genuine and posed smiles remains a challenge because humans are not good at picking up the relevant cues,” said study lead author Hassan Ugail, Professor at University of Bradford in the UK.

The software works by first mapping a person’s face from within a video recording, and identifying the mouth, cheeks and eyes of the subject.

It then measures how these facial features move through the progress of the smile and calculates the differences in movement between the video clips showing real and fake smiles.

Shanghai,
Rana el Kaliouby, CEO of the Boston-based artificial intelligence firm Affectiva, demonstrates the company’s facial recognition technology, in Boston, April 23, 2018. (Representational image). VOA

Researchers tested the programme using two different datasets, one containing images of people expressing genuine smiles, and another in which the images portrayed posed smiles.

They found significant differences in the way the subjects’ mouths and cheeks moved when comparing the real and the fake expressions. The movements around the subjects’ eyes, however, showed the most striking variation, with genuine smiles generating at least 10 per cent more movement in these muscles.

“We use two main sets of muscles when we smile — the zygomaticus major, which is responsible for the curling upwards of the mouth, and the orbicularis oculi, which causes crinkling around our eyes,” Ugail said.

Also Read: Microsoft Acquires Data Privacy, Governance Service BlueTalon

According to the researchers, in fake smiles it is often only the mouth muscles which move but, as humans, we often don’t spot the lack of movement around the eyes. The computer software can spot this much more reliably.

“An objective way of analysing whether or not a smile is genuine could help us develop improved interactions between computers and humans — for example in biometric identification,” he added. (IANS)

Next Story

Internship at IIT Bombay: How an Online Training came to my Rescue

Arpit Jindal shares the importance of online training

0
C++ internship
Arpit Jindal joined the internshala training for C++ and this helped him with his internship at IIT Bombay. Pixabay

About the Author: Arpit Jindal is pursuing B.Tech in Civil Engineering from IIT Roorkee. He joined Internshala Trainings for Programming with C and C++ training and shares how it helped him complete his internship at IIT Bombay.

Having come from a socially, educationally, and technically backward city, I had no familiarity with coding during my school years. Thus, my initial exposure to coding after getting admission in IIT Roorkee fascinated me to the core. I developed a keen interest in C++ programming in my first semester.

I was seeking an internship at IIT Bombay under Prof. Subimal Ghosh, so I sent him an email expressing my interest to work with him. He reverted asking about my working knowledge of C++, the profile I was interested in, and the time period for which I was available. He shared some of his research papers with me and when I had gained an initial insight on them, he asked me to join him at IIT Bombay. My joy knew no bounds when I was selected for the internship but then began the journey of a training that was to change my internship experience.

Arpit Jindal internship
Arpit Jindal was seeking an internship at IIT Bombay under Prof. Subimal Ghosh.

The professor was working in the field of climatic changes, statistical downscaling of rainfall, the projection of rainfall, etc. using MATLAB software. My job was to convert the MATLAB codes, written to get the projection of rainfall, into C++ codes. Although I was acquainted with the concepts of C++, I needed to enhance my learning and skills for the internship. While digging into available training programs, I came across Internshala’s Young Achiever Scholarship which provides free training to economically challenged students. This was a golden opportunity for me to learn in the comfort of my room. I applied for the scholarship and got the chance to do free training.

The training commenced on June 15. The course was divided into four modules which were designed in an easy and detailed manner and the concepts were explained well. An interesting thing about these was that I could not skip any lesson or test. Normally, with some prior knowledge, we tend to go through only those lessons that we need to learn. However, I had to go through all the lessons and tests which helped strengthen the basics of the subject.This learning not only boosted my knowledge but also my confidence. Another thing that I appreciated about the training program was the support of the team – whenever I had any doubt, I just called them and got it sorted. This made the training program stand out from other courses available on the internet.

Also Read- Airtel Brings WiFi Calling Services in India

The training program guided me through all the roadblocks I faced during my internship. Everything I needed to work on during the internship became easier (and sometimes possible) with the detailed lessons and practice tests. Conversion of codes required the knowledge of pointers, functions, gamma distribution, inverse gamma distribution, inverse normal distribution, and nested loops which I had no understanding of until this training came to my rescue. I completed my project in time and submitted the project report to my professor. The training helped me like Akshay Kumar had helped Paresh Rawal in the movie ‘Oh My God’, guiding me at each step, and helping me understand the nitty-gritty of C++. Pursuing this training proved to be a great decision and excited me enough to take up another training on AutoCAD in the coming summer.

Courtesy: Internshala Trainings, a training platform (trainings.internshala.com)