January 29, 2023
Scientists consider facial recognition know-how is beneficial within the quest to avoid wasting the seals

Facial recognition know-how is generally related to makes use of corresponding to surveillance and the authentication of human faces, however scientists consider they’ve discovered a brand new use for it — saving seals.

A analysis workforce at Colgate College has developed SealNet, a database of seal faces created by taking photos of dozens of harbor seals in Maine’s Casco Bay. The workforce discovered the device’s accuracy in figuring out the marine mammals is near 100%, which isn’t any small accomplishment in an ecosystem house to hundreds of seals.

The researchers are engaged on increasing their database to make it out there to different scientists, mentioned Krista Ingram, a biology professor at Colgate and a workforce member. Broadening the database to incorporate uncommon species such because the Mediterranean monk seal and Hawaiian monk seal might assist inform conservation efforts to avoid wasting these species, she mentioned.


Cataloguing seal faces and utilizing machine studying to establish them also can assist scientists get a greater thought of the place within the ocean seals are situated, Ingram mentioned.

“Understanding their dispersal, understanding their patterns actually helps inform any conservation efforts for the coast,” she mentioned. “For cell marine mammals that transfer round lots and are laborious to {photograph} within the water, we want to have the ability to establish people.”

SealNet is designed to robotically detect the face in an image, crop it and acknowledge it primarily based on facial patterns corresponding to eyes and nostril form, as it might a human. An analogous device referred to as PrimNet that’s to be used on primates had been used on seals beforehand, however SealNet outperformed it, the Colgate researchers mentioned.

The Colgate workforce printed its findings in April within the scientific journal Ecology and Evolution. They processed greater than 1,700 pictures of greater than 400 particular person seals, the paper mentioned.

Scientists consider facial recognition know-how is beneficial within the quest to avoid wasting the seals

A harbor seal seems round in Casco Bay on July 30, 2020, in Portland, Maine. A analysis workforce developed SealNet, a facial recognition database of seal faces created by taking photos of dozens of harbor seals in Maine. 
(AP Picture/Robert F. Bukaty, Information)

The paper said that the “ease and wealth of picture information that may be processed utilizing SealNet software program contributes an important device for ecological and behavioral research of marine mammals within the creating subject of conservation know-how.”

Harbor seals are a conservation success story within the U.S. The animals had been as soon as topic to bounties in New England, the place they had been broadly considered by fishermen as pests within the nineteenth and early twentieth centuries. However the Marine Mammal Safety Act, which turned 50 in October, prolonged them new protections — and populations started to rebound.


Seals and different marine mammals have lengthy been studied utilizing satellite tv for pc trackers. Utilizing synthetic intelligence to review them is a approach to carry conservation into the twenty first century, mentioned Jason Holmberg, government director of Wild Me, an Oregon-based firm that works to carry machine studying to biologists. Wild Me is creating a possible partnership with SealNet.

“It is a shift and a elevate of ‘massive brother’ type know-how to a really benevolent conservation-style purpose,” Holmberg mentioned.

Harbor seals at the moment are pretty ample in New England waters, the place they haul out on rocks and delight seal watch cruises and beachgoers. Different seal species, nevertheless, stay in jeopardy. The Mediterranean monk seal is considered the world’s most endangered seal with only some hundred animals remaining.

The usage of facial recognition might present extra useful information, mentioned Michelle Berger, an affiliate scientist on the Shaw Institute in Maine, who was not concerned within the SealNet analysis.

“As soon as the system is perfected I can image a lot of attention-grabbing ecological purposes for it,” Berger mentioned. “If they might acknowledge seals, and acknowledge them from 12 months to 12 months, that will give us a lot of details about motion, how a lot they transfer from web site to web site.”


The Colgate researchers are additionally working with FruitPunch, a Dutch synthetic intelligence firm, to enhance some elements of SealNet to encourage wider use. FruitPunch is getting just a few dozen scientists all over the world to work on a problem to streamline SealNet’s workflow, mentioned Tjomme Dooper, FruitPunch’s head of partnerships and progress.

Improved automation of the facial recognition know-how might make SealNet extra helpful to extra scientists, Dooper mentioned. That will open new alternatives to review the animals and assist defend them, he mentioned.

“What this does is assist the biologists examine the habits of seals, and likewise inhabitants dynamics,” Dooper mentioned. “Harbor seals are an necessary indicator species for the ecosystem round them.”


Leave a Reply

Your email address will not be published. Required fields are marked *