Новини

Big  brother следи дали носим маски

 

Tryolabs' software has two main components: The "pose" algorithms decipher different parts of the body before the "classification" algorithms decide if the facial region includes a mask.

Video by Mark Thiessen and Rebecca Hale, National Geographic/Face-mask recognition technology courtesy Tryolabs

 

Публичното заклейямяване за неносенето на маски започна почти едновременно със самата пандемия от Covid-19.  През февруари

PUBLIC SHAMING OVER not wearing a face mask started almost as soon as the COVID-19 pandemic itself. In February, some provinces and municipalities in China made it mandatory to wear masks when in public. News reports soon followed of residents and police chastising the non-compliant, a trend that’s now seen globally.

When Akash Takyar heard those early stories trickle out of China, he was shocked at how things were being handled, and he wondered if his software company—LeewayHertz—could offer a more peaceful way. Takyar recognized how important it is to wear a mask to slow the spread of SARS-CoV-2, the virus that causes COVID-19. But rather than leave members of the public to monitor each other, he wanted to develop a computer program that could look at images and detect whether people are wearing masks.

His San Francisco-based company is one of many now pioneering mask recognition as a way to get people to comply for the public good. So far, masks have been confounding traditional facial recognition software—but these new machine learning tools could conceivably be used in private or public spaces to measure compliance and ostensibly take that out of the hands of individuals.

 

To date, 34 states and the District of Columbia have mask mandates for public spaces, both outdoors and indoors. But only a few reports show that law enforcement has stepped in to arrest people who were indoors in private businesses without a mask.

 

For businesses that have workers returning to indoor facilities, noncompliance could lead to others in the workplace getting infected. Ultimately, it could be a great loss for a business if there was an outbreak because someone was asymptomatic and failed to wear a mask, says Takyar.

 

Today’s facial recognition software studies the features around the eye, nose, mouth, and ears to identify an individual whose picture is already supplied, either by the individual or in a criminal database.  Wearing a mask obstructs this recognition—an issue that many systems have already encountered, and others have solved. For example, Apple’s FaceID, which uses facial recognition so users can unlock their iPhone, recently released a system update that can, in essence, detect when a person is wearing a mask. The update quickly recognizes a covered mouth and nose and prompts the user to enter their passcode instead of making them pull down their face covering.

 

Developers say that mask recognition software  bypasses privacy issues because the programs don’t actually identify the people. Currently, this recognition software is being used  in multiple settings in the United States and Europe. Restaurants and hotels are using it to make sure the staff is complying with wearing masks.  Department stores could use it to dole out face coverings to noncompliant patrons, for instance, or a company could fire an employee who refuses to comply with wearing masks in the workplace.