2022年12月05日 VOA慢速英語(yǔ)：科學(xué)家使用面部識(shí)別技術(shù)研究海豹

 

Scientists believe they have found a new use for facial recognition technology: saving large ocean animals known as seals.
科學(xué)家們相信他們發(fā)現(xiàn)了面部識(shí)別技術(shù)的新用途：拯救被稱為海豹的大型海洋動(dòng)物。
 
Researchers at Colgate University in the U.S. state of New York have developed SealNet. The system is a database of seal faces created by taking pictures of many harbor seals in Maine's Casco Bay.
科爾蓋特大學(xué)的研究人員美國(guó)紐約州開(kāi)發(fā)了SealNet。該系統(tǒng)是一個(gè)海豹面孔數(shù)據(jù)庫(kù)，通過(guò)拍攝緬因州卡斯科灣的許多斑海豹照片創(chuàng)建。
 
The research team found the tool's accuracy in identifying the mammals was close to 100 percent.
研究團(tuán)隊(duì)發(fā)現(xiàn)該工具識(shí)別哺乳動(dòng)物的準(zhǔn)確率接近 100%。
 
The researchers are working on increasing the size of their database to make it available to other scientists, said Krista Ingram. She is a biology professor at Colgate and a team member.
研究人員正在努力擴(kuò)大數(shù)據(jù)庫(kù)的規(guī)模，以便其他科學(xué)家可以使用它，Krista Ingram 說(shuō)。她是高露潔大學(xué)的生物學(xué)教授和團(tuán)隊(duì)成員。
 
Increasing the database to include rare species such as the Mediterranean monk seal and Hawaiian monk seal could help efforts to save those species, she said.
增加數(shù)據(jù)庫(kù)以包括地中海僧海豹和夏威夷僧海豹等稀有物種可以幫助拯救這些物種，她說(shuō)。
 
Creating a list of seal faces and using machine learning to identify them can also help scientists know where in the ocean seals are, Ingram said.
英格拉姆說(shuō)，創(chuàng)建海豹面孔列表并使用機(jī)器學(xué)習(xí)來(lái)識(shí)別它們也可以幫助科學(xué)家了解海豹在海洋中的位置。
 
She said, "For...marine mammals that move around a lot and are hard to photograph in the water, we need to be able to identify individuals."
她說(shuō)，“對(duì)于......在海域周圍移動(dòng)的海洋哺乳動(dòng)物很多并且很難在水中拍攝，我們需要能夠識(shí)別個(gè)體。”
 
SealNet is designed to identify the face in a picture. It recognizes the seal's face based on information related to the eyes and nose shape, as it would a human. A similar tool called PrimNet, that is for use on primates, had been used on seals earlier, but SealNet performed better, the Colgate researchers said.
SealNet 旨在識(shí)別照片中的人臉。它根據(jù)與眼睛和鼻子形狀相關(guān)的信息識(shí)別海豹的面部，就像識(shí)別人類一樣。高露潔研究人員表示，一種名為 PrimNet 的類似工具用于靈長(zhǎng)類動(dòng)物，之前曾用于海豹，但 SealNet 表現(xiàn)更好。
 
 
The Colgate team published its findings last spring in Ecology and Evolution. They processed more than 1,700 images of more than 400 individual seals, the paper said.
高露潔團(tuán)隊(duì)去年春天在生態(tài)學(xué)和進(jìn)化論上發(fā)表了他們的發(fā)現(xiàn)。該論文稱，他們處理了 400 多只海豹的 1,700 多張圖像。
 
The paper stated that the SealNet software could be a valuable tool in the developing field of "conservation technology" - technology aimed at saving and protecting wild animals.
該論文稱，SealNet 軟件可能成為“保護(hù)技術(shù)”發(fā)展領(lǐng)域的寶貴工具 - 旨在保護(hù)動(dòng)物的技術(shù)拯救和保護(hù)野生動(dòng)物。
 
Harbor seals are a conservation success story in the U.S. More than 100 years ago, the animals were once widely killed. But the Marine Mammal Protection Act, which turned 50 in October, gave them new protections — and populations began to come back.
海豹在美國(guó)是一個(gè)成功的保護(hù)故事。100 多年前，這些動(dòng)物曾被廣泛捕殺。但 10 月滿 50 周年的《海洋哺乳動(dòng)物保護(hù)法》為它們提供了新的保護(hù)——數(shù)量開(kāi)始回升。
 
Seals and other ocean mammals have long been studied using satellite technology. Using artificial intelligence to study them is a way to bring conservation into the 21st century, said Jason Holmberg of Wild Me. The Oregon-based company works to bring machine learning to biologists. Wild Me is developing a possible partnership with SealNet.
長(zhǎng)期以來(lái)，人們一直在使用衛(wèi)星技術(shù)研究海豹和其他海洋哺乳動(dòng)物。 Wild Me 的 Jason Holmberg 說(shuō)，使用人工智能研究它們是將保護(hù)帶入 21 世紀(jì)的一種方式。這家位于俄勒岡州的公司致力于將機(jī)器學(xué)習(xí)帶給生物學(xué)家。 Wild Me 正在與 SealNet 建立可能的合作伙伴關(guān)系。
 
Harbor seals are now common in the waters off the coast of the Northeastern United States. Other seal species, however, remain at risk. The Mediterranean monk seal is thought to be the world's most at-risk seal with only a few hundred animals remaining.
斑海豹現(xiàn)在在美國(guó)東北部沿海水域很常見(jiàn)。然而，其他海豹物種仍處于危險(xiǎn)之中。地中海僧海豹被認(rèn)為是世界上最危險(xiǎn)的海豹，僅存數(shù)百只。
 
Facial recognition technology could provide valuable data, said Michelle Berger, an associate scientist at the Shaw Institute in Maine. Berger was not involved in the SealNet research.
緬因州逸夫研究所的副科學(xué)家 Michelle Berger 說(shuō)，面部識(shí)別技術(shù)可以提供有價(jià)值的數(shù)據(jù)。 Berger 沒(méi)有參與 SealNet 研究。
 
"Once the system is perfected I can picture lots of interesting" environmental uses for it, Berger said. "If they could recognize seals, and recognize them from year to year, that would give us lots of information about movement, how much they move from site to site."
“一旦系統(tǒng)完善，我就可以想象出很多有趣的”環(huán)境用途，Berger 說(shuō)。 “如果他們能認(rèn)出海豹，并且年復(fù)一年地認(rèn)出它們，那將為我們提供大量關(guān)于運(yùn)動(dòng)的信息，包括它們從一個(gè)地方到另一個(gè)地方的移動(dòng)量。”
 
The Colgate researchers are also working with FruitPunch, a Dutch artificial intelligence company, to improve some parts of SealNet to help more scientists use it, said Tjomme Dooper, FruitPunch's head of partnerships and growth.
FruitPunch 合作伙伴關(guān)系和發(fā)展主管 Tjomme Dooper 表示，高露潔研究人員還與荷蘭人工智能公司 FruitPunch 合作，改進(jìn) SealNet 的某些部分，以幫助更多科學(xué)家使用它。
 
That would open new opportunities to study the animals and help protect them, he said.
這將打開(kāi)他說(shuō)，這是研究這些動(dòng)物并幫助保護(hù)它們的新機(jī)會(huì)。
 
"What this does is help the biologists study the behavior of seals, and also population dynamics," Dooper said. He added that harbor seals give important information about the environment around them.
“這有助于生物學(xué)家研究海豹的行為以及種群動(dòng)態(tài)，”Dooper 說(shuō)。他補(bǔ)充說(shuō)，斑海豹提供有關(guān)它們周圍環(huán)境的重要信息。