Researchers in Barcelona have developed new technology which can detect who is wearing a mask and who isn’t in crowded spaces.
A NEW law will be passed in Spain today, Wednesday, June 10, which declares that until a vaccine is found to fight Covid-19, everyone (except those who have medical reasons) over a certain age will have to wear a face mask – even after State of Alarm.
It will be applied everywhere that you cannot keep a 1.5-metre distance from another person who you don’t live with. There are exceptions for those who have medical problems.
But in crowds, enforcing the new law could prove tricky.
To make the task easier, a team at Barcelona University has created LogMask, which identifies people with or without masks in crowds.
The team, formed by computer science and telecommunication engineers and mathematicians and professionals of digitalisation in public bodies and companies, claim the technology is 95 per cent accurate.
LogMask apparently works under different light conditions, as well as in open and closed spaces, regardless of the amount of people present.
In a statement, the university said: “LogMask is a project based on artificial intelligence techniques, deep learning and big data to conduct computational analysis in real time images.
“The aim is to identify people with and without masks, which are mandatory as announced in the current regulation, published in the Official Gazette of the Spanish Government (BOE), on May 20.”
Petia Radeva, professor at the Department of Mathematics and Computer Science of the University of Barcelona, and leader of the research group, added: “Deep learning technology enables a computer to learn and identify automatically about the features based on images, people with or without mask in this case, having being shown thousands of images.
“Thanks to this technology, LogMask can learn to identify the visual features of the images and look for the patterns that identify eyes and face features to find faces, and on the other hand, features based on shape and colour of masks, as well as of mouths, to identify whether the person is wearing a mask.
“The algorithm was launched thanks to a set of 25,000 images with more than 45,000 human faces with and without masks.”
The technology not only warns in real time who is and who isn’t wearing a mask, it also detects the amount of people in a certain space, and can be adapted in accordance with distancing measures in place during the lifting of lockdown.