The Future of Education: Facial Recognition in the Classroom

https://i1.wp.com/edudemic.com/wp-content/uploads/2012/07/intel-bridge-the-gap.pngFor some time now, classroom cameras have been used to see what teachers do in the course of their lessons, and evaluate their overall effectiveness as educators. But thanks to a recent advances in facial recognition software, a system has been devised that will assess teacher effectiveness by turning the cameras around and aiming at them at the class.

It’s what’s known as EngageSense, and was developed by SensorStar Labs in Queens, New York. It begins by filming student’s faces, then applying an algorithm to assess their level of interest. And while it might sound a bit Big Brother-y, the goal is actually quite progressive. Traditional logic has it that by filming the teacher, you will know what they are doing right and wrong.

https://i2.wp.com/f.fastcompany.net/multisite_files/fastcompany/imagecache/slideshow_large/slideshow/2013/10/3018861-slide-makerfaire1.jpgThis system reverses that thinking, measuring reactions to see how the students feel and react, measuring their level of interest over time to see what works for them and what doesn’t. As SensorStar Labs co-founder Sean Montgomery put it:

This idea of adding the cameras and being able to use that information to assist teachers to improve their lessons is already underway. Where this is trying to add a little value on top of that is to make it less work for the teachers.

Montgomery also emphasized that the technology is in the research and development research and development  phase. In its current form, it uses webcams to shoot students’ faces and computer vision algorithms to analyze their gaze – measuring eye movement, the direction they are facing, and facial expressions. That, coupled with audio, can be transformed into a rough, automated metric of student engagement throughout the day.

https://i1.wp.com/endthelie.com/wp-content/uploads/2012/08/facial-recognition-data-points.jpgAfter a lesson, a teacher could boot up EngageSense and see, with a glance at the dashboard, when students were paying rapt attention, and at what points they became confused or distracted. Beyond that, the concept is still being refined as SensorStar Labs looks both for funding and for schools to give EngageSense a real-world trial.

The ultimate goal here is to tailor lessons so that the learning styles of all students can be addressed. And given the importance of classroom accommodation and the amount of time dedicated to ensuring individual student success, a tool like this may prove very useful. Rather than relying on logs and spreadsheets, the EngageSense employs standard computer hardware that simplifies the evaluation process over the course of days, weeks, months, and even years.

https://i0.wp.com/image.slidesharecdn.com/technologyandeducation2-110922110134-phpapp01/95/slide-1-728.jpgAt the present time, the biggest obstacle would definitely be privacy concerns. While the software is designed for engaging student interest right now, it would not be difficult at all to imagine the same technology applied to police interrogations, security footage, or public surveillance.

One way to assuage these concerns in the classroomstudents, according to Montgomery, is to make the entire process voluntary. Much in the same way that smartphone apps ask permission to access your GPS or other personal data, parental consent would be needed before a child could be recorded or their data accessed and analyzed.

Sources: fastcoexist.com, labs.sensorstar.com

2 thoughts on “The Future of Education: Facial Recognition in the Classroom

Leave a Reply

Fill in your details below or click an icon to log in:

WordPress.com Logo

You are commenting using your WordPress.com account. Log Out / Change )

Twitter picture

You are commenting using your Twitter account. Log Out / Change )

Facebook photo

You are commenting using your Facebook account. Log Out / Change )

Google+ photo

You are commenting using your Google+ account. Log Out / Change )

Connecting to %s