IE 11 is not supported. For an optimal experience visit our site on another browser.

Tiger stripes used to ID poached pelts

Tigers' enchanting stripe patterns and gorgeous fur are their downfall — poachers and illegal traders have pushed many tiger species to the brink of extinction, slaughtering them for their coveted pelts.
iStockPhoto | 
 
Telling Tigers by Their Stripes
Each tiger's markings are unique, like a fingerprint, and a new computer-driven technique can match images of live animals with illegally traded skins, identifying when and where poachers made their kills.
Each tiger's markings are unique, like a fingerprint, and a new computer-driven technique can match images of live animals with illegally traded skins, identifying when and where poachers made their kills. iStockPhoto |
/ Source: Discovery Channel

Tigers' enchanting stripe patterns and gorgeous fur are their downfall — poachers and illegal traders have pushed many tiger species to the brink of extinction, slaughtering them for their coveted pelts.

But conservation researchers have found a new weapon against trade, a code hidden in tigers' stripes. Each tiger's markings are unique, like a fingerprint, and a new computer-driven technique can match images of live animals with illegally traded skins, identifying when and where poachers made their kills.

Photographs of live, wild tigers are hard to come by — like most big cats, they're notoriously reclusive. With a new system developed by Lex Hiby of Conservation Research Limited, automated camera traps do most of the image collecting. Then computer software melds several pictures into a three-dimensional map of an animal's markings on both sides, from the neck to the base of the tail.

The map is digitally flattened until it resembles a tiger skin, which can be compared to pictures of skins being traded on the black market.

Out of a collection of between 264 and 298 tigers with known stripe patterns in the Nagarhole and Bandipur tiger reserves in India, the program correctly matched 95 percent of images that belonged to the same animal.

In a study of six images taken from three skins between 2006 and 2008, the program matched five to pictures of live tigers. In the sixth image the right flank of the skin was folded, preventing a strong match.

"If copies of camera trap images were accumulated in a central database, an image of a skin that had been taken from one of the tigers in that database could be traced within a few minutes to where and when the living animal was last recorded," the authors wrote in a paper published this week in the journal Biology Letters.

Pattern recognition software of this kind has been around for some time, and has been used to identify gray seals, cheetahs and whale sharks, among other animals.

"We develop population models to determine if a group of animals is healthy or declining," said Jason Holmberg of ECOCEAN, a research organization that tracks whale sharks by matching their spot patterns in pictures taken by researchers and tourists.

Through the analysis of thousands of photographs of whale sharks, Holmberg and his colleagues have shown that the mysterious creatures living near the Ningaloo Reef off the coast of Australia have grown in number by about 1.7 percent over the last 12 years.