Kansas State researchers develop cattle facial recognition technology

Kansas State University researchers are developing facial recognition technology for the cattle industry. According to the university, this could help officials as they try to develop a national animal disease traceability system.

The technology builds on concepts used for human facial recognition, which is becoming more common in secure locations like airports. Just like humans, individual cows have unique facial features that can be scanned and used to track the animal throughout its life.

“Our thinking is, ‘why can’t we have something like that for beef cattle, which could then be used to create a national animal disease traceability system?'” said KC Olson, a beef cattle scientist at the university who’s helping develop the new concept. “The need for such a system has never been greater. We need this extra layer of protection for our industry against a foreign animal disease or…possible malfeasance by somebody who’s an enemy of this nation.”

Olson and other university experts in computer engineering, veterinary medicine and animal science have been discussing the idea since last year. They initially made short videos of 1,000 feeder cattle, taking a panoramic view of each calf’s head.

Engineers then uploaded images from those videos to a neural network that uses artificial intelligence. With those pictures, Olson said, the system “teaches itself which of the biometric measurements are critical.”

The research team recently tested the network’s reliability, resulting in 94% accuracy, Olson said.