Scientists believe facial recognition technology is helpful in the quest to save the seals

0
6

Facial recognition technology is usually associated with applications such as human face surveillance and authentication, but scientists think they’ve found a new use for it: saving seals.

A research team at Colgate University has developed SealNet, a database of seal faces created by taking photos of 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%, which is no small feat in an ecosystem with thousands of seals.

The researchers are working on expanding their database to make it available to other scientists, said Krista Ingram, a biology professor at Colgate and a team member. Broadening the database to include rare species such as the Mediterranean monk seal and Hawaiian monk seal could help support conservation efforts to save those species, she said.

MAINE COAST SEEING ALARMING DEAD SEAL INCREASE, BLAME OF AVIAN INFLUENZA

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

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

ALSO READ  Trump announces 2024 presidential bid, experts explain how Dems avoided 'red wave' and more headlines

SealNet is designed to automatically detect, crop and recognize the face in a photo based on facial patterns such as eyes and nose shape, just like a human. A similar tool called PrimNet, which is for use on primates, had been used on seals before, but SealNet outperformed it, the Colgate researchers said.

The Colgate team published its findings in April in the scientific journal Ecology and Evolution. They processed more than 1,700 images of more than 400 individual seals, the paper said.

A harbor seal looks around Casco Bay on July 30, 2020 in Portland, Maine. A research team developed SealNet, a facial recognition database of seal faces created by taking photos of dozens of harbor seals in Maine.
(TBEN Photo/Robert F. Bukaty, Files)

The paper stated that the “ease and wealth of image data that can be processed using SealNet software is an essential tool for ecological and behavioral studies of marine mammals in the developing field of conservation technology.”

Harbor seals are a conservation success story in the US. The animals were once rewarded in New England, where they were widely considered pests by fishermen in the 19th and early 20th centuries. But the Marine Mammal Protection Act, which turned 50 in October, extended new protections to them — and populations began to recover.

ALSO READ  G20 Summit Shines Spotlight on Bali's Tourism Revival

RARE ELEPHANT SEAL SPOTTED SLEEPING NEAR THE CALIFORNIA COAST

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, executive director of Wild Me, an Oregon-based company dedicated to bringing machine learning to biologists. Wild Me is developing a possible partnership with SealNet.

“This is a shift and an elevator from ‘big brother’ style technology to a very benevolent conservation style goal,” Holmberg said.

Harbor seals are now quite numerous in New England waters, where they prowl on rocks and delight seal watching cruises and beachgoers. However, other seal species remain endangered. The Mediterranean monk seal is considered the most endangered seal in the world and there are only 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 was not involved in the SealNet study.

ALSO READ  Tallahassee Police Department: Mass shooting outside FAMU recreation center kills 1, injures 4 others

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

CLICK HERE TO GET THE TBEN NEWS APP

The Colgate researchers are also working with FruitPunch, a Dutch artificial intelligence company, to improve some aspects of SealNet to encourage wider use. FruitPunch has several dozen scientists around the world working on a challenge to streamline SealNet’s workflow, said Tjomme Dooper, head of partnerships and growth at FruitPunch.

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

“What this does is help the biologists study seal behavior, and also population dynamics,” Dooper said. “Common seals are an important indicator species for the ecosystem around them.”

LEAVE A REPLY

Please enter your comment!
Please enter your name here