Face recognition may help preserve seals, scientists say

FREEPORT, Maine – Face recognition technology is mostly associated with applications like surveillance and authentication of human faces, but scientists think they’ve found a new use for it — storing seals.

A research team from Colgate University developed SealNet, a database of seal faces created by photographing dozens of harbor seals in Maine’s Casco Bay. The team found that the tool’s accuracy in identifying the marine mammals is close to 100%, no small feat in an ecosystem home to thousands of seals.

The researchers are working to expand their database to make it available to other scientists, said Krista Ingram, a biology professor at Colgate and a team member. Adding rare species like the Mediterranean monk seal and Hawaiian monk seal to the database could help inform conservation efforts to save these species, she said.

Cataloging seal faces and using machine learning to identify them can also help scientists get a better idea of ​​where seals are in the ocean, Ingram said.

“Understanding their spread, understanding their patterns, really helps inform any coastal conservation effort,” she said. “For mobile marine mammals, which move a lot and are difficult to photograph in the water, we need to be able to identify individuals.”

SealNet is designed to automatically detect the face in an image, crop it and recognize it based on facial patterns such as the shape of eyes and nose, just like a human.

A similar tool called PrimNet, intended for use in primates, had previously been used in seals, but SealNet outperformed it, the Colgate researchers said.

The Colgate team published their findings in the journal Ecology and Evolution in April.

They processed more than 1,700 images of more than 400 individual seals, according to the newspaper.

The paper states that “the ease and richness of imagery that can be processed with the SealNet software provides an important tool for ecological and behavioral studies of marine mammals in the evolving field of conservation technology.”

Seals are a conservation success story in the US The animals were once subject to premiums in New England, where they were widely regarded as pests by fishermen in the 19th and early 20th centuries.

But the Marine Mammal Protection Act, which turned 50 in October, added new protections – and populations began to recover.

Seals and other marine mammals have long been studied using satellite trackers. Using artificial intelligence to study them is one way to bring conservation into the 21st century, said Jason Holmberg, CEO of Wild Me, an Oregon-based company working to bring machine learning to biologists. Wild Me is developing a potential partnership with SealNet.

“This is a ‘Big Brother’ style shift and upgrade of technology to a very benevolent conservation goal,” said Holmberg.

Harbor seals are now plentiful in New England waters, where they frolic on rocks and delight seal-watching cruises and beachgoers. However, other seal species remain at risk.

The Mediterranean monk seal is considered the most endangered seal in the world with just a few hundred animals left.

Using facial recognition could yield more valuable data, said Michelle Berger, an associate scientist at the Shaw Institute in Maine who wasn’t involved with the SealNet research.

“Once the system is perfected, I can envision many interesting ecological uses for it,” said Berger. “If they could identify seals, year by year, that would give us a lot of information about the movement, how much they move from place to place.”

The Colgate researchers are also working with FruitPunch, a Dutch artificial intelligence company, to improve some aspects of SealNet to encourage wider use.

FruitPunch is bringing a few dozen scientists around the world to work on a challenge to streamline SealNet’s workflow, said Tjomme Dooper, FruitPunch’s director of partnerships and growth.

Improved automation of facial recognition technology could make SealNet more useful to more scientists, Dooper said. That would open up new opportunities to study and protect the animals, he said.

“This helps biologists study seal behavior and also population dynamics,” Dooper said. “Seals are an important indicator species for the ecosystem around them.”