Called SEE Shell, the application uses machine learning (or machine learning) to analyze a photograph of an object with a tortoiseshell pattern to determine with 94% accuracy whether it is real or fake. It is the first mobile application to use computer vision to combat the illegal wildlife trade, according to Alexander Robillard, a doctoral student at the Smithsonian’s Data Science Lab and who built the computer model that runs the application. It will help inform conservation-minded buyers as well as law enforcement. (App can be downloaded from the Apple App Store and on Google Play.)
According to Nahill, black market sales of tortoiseshell persist in at least forty countries, mostly in Central America and Southeast Asia. The vast majority of these illicit sales are due to tourists buying tortoiseshell trinkets from gift shops and souvenir stalls.
The app is also very useful for the wealth of information it can provide access to. All images are uploaded to a private, centralized database, along with GPS coordinates for each, allowing SEE Turtles to identify where the major illicit sales locations are.
“If we encourage a few hundred travelers to actively use it, collect data, and avoid buying real tortoiseshell, that’s good enough,” Nahill says. SEE Turtles plans to promote the free app through social media campaigns and partnerships with other conservation organizations.
Marine ecologist Emily Miller, who was not involved in developing the app but authored a 2019 article about the global scale of the hawksbill trade, explains that, although many groups around the world collect data on the trade in these animals, “one of the main obstacles that makes it difficult to answer the research questions is the step of consolidating, formatting and organization of all data. Having a larger, centralized database “will be incredibly helpful in understanding trading patterns globally,” she adds.
TRAIN A COMPUTER TO PROTECT TURTLES
Robillard worked with Nahill’s team to collect 4,000 images of real and fake tortoiseshell products. The researcher fed these images into his computer model, which analyzed the pixels of each of them in order to determine the differences in shape and coloration between a real and a false scale.
According to Nahill, one of the main differences is that the patterns of real tortoiseshell are random. Fake products, on the other hand, tend to have spots with uniform edges, or the same pattern on different items sold together. The orange tint of the false scale also tends to be uniformly translucent.
Nahill and Robillard know how to tell right from wrong, but without the application it might take years of practice for a non-expert to develop this skill. “I like to tell people they have Brad [Nahill] in their pocket! Robillard says of the app. Machine learning and computer vision “can do any visual task that a human can do, but more efficiently and faster,” he adds. (For my part, I tested SEE Shell on two pairs of tortoiseshell-patterned glasses and she immediately identified both as fakes.)
COCKTAIL STICKS AND MORE
Thanks to the app, scientists have already discovered tortoiseshell products they never knew existed: for example, sticks for mixing cocktails or even ergots for cockfighting.
The app will be very useful for local conservation groups. Before its launch, the Fundacion Tortugas del Mar, a turtle protection group in Cartagena, Colombia, had previously successfully lobbied local law enforcement to crack down on the trade, reducing it by nearly 80% in the region. But, according to Nahill, the authorities only go on patrol if a member of the group accompanies them in order to help them identify illegal products. Tortugas del Mar plans to train law enforcement to use the app, which would allow them to work faster and more independently.
David Godfrey, Executive Director of the Sea Turtle Conservancywhich is working to protect hawksbill turtles in Panama, a major point of trade, believes that if tourists use SEE Shell, it will amount to equipping “an army of conservationists to make life difficult for people who sell [l’écaille de tortue] on the black market. Now that people can immediately identify the real scale, sellers may think twice before offering it, he adds.
With help from the World Wide Fund for Nature (WWF), SEE Turtles also aims to apply this technology to online platforms, which have seen a sharp increase in illegal wildlife trade these last years. Among others, Facebook and eBay filter out illegal products by detecting ads that include banned keywords, but the filters are easily circumvented. “To our knowledge, no one has implemented any sort of visual system,” says Nahill.
This visual learning technology could be adapted to other materials from wildlife, for example to distinguish real bones from fakes. According to Robillard, the ability to identify real elephant ivory in an instant would be particularly useful, but it would be trickier than for tortoiseshell: a key indicator is to observe internal cross-hatched lines to determine whether the ivory is authentic or not, which is not possible using a simple photograph.
Nevertheless, according to him, “there is a whole range of possibilities for applying machine learning to questions of preservation”.
We want to say thanks to the writer of this article for this awesome web content
This application offers to save sea turtles threatened with extinction
Take a look at our social media profiles and also other related pageshttps://www.ai-magazine.com/related-pages/