Article: AI Can Help in Finding Stolen Dogs

Photo Source: Unsplash

Thanks to the unique nose print of every dog, artificial intelligence stands poised to add a new layer to safeguarding our dogs. People adore their dogs; some even refer to them as fur babies. In the US, dog parents, the newer term for dog owners, spent over $136.8 billion on their dogs in 2022, up 10.7% from the year before. According to Forbes, that comes out to around $750 per dog per year. (forbes.com) The cost of dog ownership continues to rise as more sophisticated and expensive dog healthcare becomes widely available. In parallel with growing dog healthcare costs, dog health insurance has emerged from obscurity to nearly standard financial protection for dog owners in the face of an unexpected accident or illness. Many corporations now offer pet health insurance as part of their employee benefits. Adopting a dog from a shelter in the Boston area can cost anywhere from $350-595, depending on the dog's age. (northeastanimalshelter.org) Moreover, purebred puppies cost, on average, $1,000 to $5,000 or more, depending on the breed. (marketwatch.com)

Given the rising popularity of dog ownership and the value of a healthy dog, it may come as no surprise that dognapping has jumped 40% since 2021 in the US, according to the American Kennel Club, with over 2,000,000 dogs stolen every year. (akcreunite.org) Some of the most targeted breeds include Labrador Retrievers, French Bulldogs, Chihuahuas, and Pitbulls. Famously, in February 2021, dognappers shot Lady Gaga's dog walker and stole two of her French Bulldogs named Koji and Gustov. (latimes.com) Gaga's dogs were eventually recovered after the singer offered a $500,000 reward for their safe return.

People steal dogs for ransom or resale, among other reasons, which is why microchipping comes so highly suggested for dog security. Vets will routinely scan dogs for a microchip when brought in for checkups or emergency care. The microchip can help locate the true owners of the dog. However, a surgical procedure can remove a microchip. So, the microchip does not represent a foolproof safeguard. However, research first conducted in 1926 by J.G. Horning and others and published in Veterinary Medicine determined that the pattern of beads and ribbons on a dog's nose is unique to every dog. In other words, instead of a unique fingerprint like people have, dogs have unique nose prints. More recent research showed that a dog's nose print does not change with age and remains consistent across different dog breeds. (nih.gov)

Building on the uniqueness of the nose print, a company in South Korea called iSciLab uses an AI technology called deep learning to recognize a dog's unique nose pattern. Deep learning uses thousands of photo images to train itself to recognize patterns such as dog noses. The computer model then can compare a new dog nose picture to other dog noses in its database of registered dogs. The company provides a smartphone app called Anipuppy that a dog parent can use to register their dog's nose print. (euronews.com) Using the smartphone camera, a dog owner only needs to take a picture of their dog's nose and provide key information such as the name and address of the dog and owner to complete the registration. iSciLab hopes to use this technology to register dogs in South Korea and based on their filed patents in the US, Japan, and several other countries in the future. 

Dognapping has moved into a growth phase in the US due to the rapidly increasing value of and demand for healthy dogs. Indeed, a recent poll found that among pet owners, 97% considered the pet as part of the family, and 51% considered their pet as much a part of the family as any human. (pewresearch.org) Such devotion to their pets and the growing desire for people to acquire a fur baby has driven up the benefit of dognapping for ransom or resale. Microchipping can help recover lost dogs, but many dogs do not have a microchip. Even worse, a dognapper can surgically remove a microchip. Fortunately, dogs have a unique and visible nose print that AI tools can identify and match.   The nose print of a dog combined with AI makes it possible to find missing dogs not just at the vet but on social media or anywhere else you can find a good photo of a dog's nose.

Dr. Smith’s career in scientific and information research spans the areas of bioinformatics, artificial intelligence, toxicology, and chemistry. He has published a number of peer-reviewed scientific papers. He has worked over the past seventeen years developing advanced analytics, machine learning, and knowledge management tools to enable research and support high-level decision making. Tim completed his Ph.D. in Toxicology at Cornell University and a Bachelor of Science in chemistry from the University of Washington.

You can buy his book on Amazon in paperback and in kindle format here.