Friday, April 23, 2021
Home Lead Story Development of Facial Recognition To Identify Masked Faces

Development of Facial Recognition To Identify Masked Faces

Face recognition developed following the arrival of the pandemic

Facial recognition technology created after the onset of the Covid-19 pandemic shows that some software developers have made demonstrable progress at recognizing masked faces, says a study.

The findings by the National Institute of Standards and Technology (NIST), measures the performance of face recognition algorithms developed following the arrival of the pandemic.

Follow NewsGram on Instagram to keep yourself updated.

A previous report from July explored the effect of masked faces on algorithms submitted before March 2020, indicating that software available before the pandemic often had more trouble with masked faces.

“Some newer algorithms from developers performed significantly better than their predecessors. In some cases, error rates decreased by as much as a factor of 10 between their pre and post-Covid algorithms,” said study author Mei Ngan from NIST.

Face Recognition
The algorithms detect the difference automatically, without being told. Unsplash

“In the best cases, software algorithms are making errors between 2.4 and five percent of the time on masked faces, comparable to where the technology was in 2017 on non-masked photos,” Ngan added.

Want to read more in Hindi? Checkout : मुंबई-अहमदाबाद बुलेट ट्रेन के लिए रेलवे को मिली पर्यावरणीय मंजूरी

The new study adds the performance of 65 newly submitted algorithms to those that were tested on masked faces in the previous round, offering cumulative results for 152 total algorithms.

Using the same set of 6.2 million images as it had previously, the team tested the algorithms’ ability to perform “one-to-one” matching, in which a photo is compared with a different photo of the same person – a function commonly used to unlock a smartphone.

ALSO READ: One In Two Urban Indians Are Early Adopters Of Technology

The researchers revealed that software can handle images regardless of whether or not the faces are masked. The algorithms detect the difference automatically, without being told. (IANS)



Most Popular

Amitabh Bachchan: An Inspiration

By- Khushi Bisht Amitabh Bachchan, also known as Big B, is without a doubt Bollywood's biggest star. The 78-year-old Bollywood megastar has been a hugely...

Does Congress Party Have A Future In Face Of Modi Onslaught?

It was India’s “Grand Old Party.” The Congress Party ruled the country for 55 out of 71 years since independence. But following the party’s...

WHO: An Initiative To Halt The Transmission Of Malaria By 2025

The World Health Organization (WHO) is launching a new initiative that aims to halt the transmission of malaria in 25 more countries by 2025....

Largest Flare Ever Recorded From The Sun’s Nearest Neighbor

Scientists have spotted the largest flare ever recorded from the sun's nearest neighbor, the star Proxima Centauri. Proxima Centauri is a small but mighty...

Understanding Obsessive Compulsive Disorder (OCD)

BY- JAYA CHOUDHARY Many of us have our own unique habits and practices that we follow on a regular basis, such as bringing a lucky...

“Bangladesh: The Price of Freedom”: Relive The Horrors Of Bangladesh Liberation

Ace photographer Raghu Rai was only five years into the profession when the Bangladesh liberation struggle erupted in March 1971. He was dispatched post-haste...

What Makes SARS-CoV-2 More Deadly?

Researchers have found that the cell types, which the SARS-CoV-2 -- the virus behind Covid-19 -- infects, make it more deadly. The study, led...

UI , Auto Zoom And More Will Be Introduced By Google In Meet App

Google has announced to introduce new innovations in its Meet app like a refreshed user interface (UI), autozoom, enhanced reliability features powered by the...

Recent Comments