Where Is My Puppy? Retrieving Lost Dogs by Facial Features

TL;DR

This paper explores automated facial recognition for dogs to help locate lost pets, comparing traditional and neural network methods, and demonstrating the superior performance of CNN-based solutions.

Contribution

It introduces CNN-based dog facial recognition methods, BARK and WOOF, and evaluates their effectiveness against traditional human facial recognition algorithms.

Findings

CNN methods outperform traditional algorithms significantly.

WOOF achieves up to 89.4% accuracy in dog face recognition.

Dog facial recognition is a challenging extension of human facial recognition.

Abstract

A pet that goes missing is among many people's worst fears: a moment of distraction is enough for a dog or a cat wandering off from home. Some measures help matching lost animals to their owners; but automated visual recognition is one that - although convenient, highly available, and low-cost - is surprisingly overlooked. In this paper, we inaugurate that promising avenue by pursuing face recognition for dogs. We contrast four ready-to-use human facial recognizers (EigenFaces, FisherFaces, LBPH, and a Sparse method) to two original solutions based upon convolutional neural networks: BARK (inspired in architecture-optimized networks employed for human facial recognition) and WOOF (based upon off-the-shelf OverFeat features). Human facial recognizers perform poorly for dogs (up to 60.5% accuracy), showing that dog facial recognition is not a trivial extension of human facial recognition. The convolutional network solutions work much better, with BARK attaining up to 81.1% accuracy, and WOOF, 89.4%. The tests were conducted in two datasets: Flickr-dog, with 42 dogs of two breeds (pugs and huskies); and Snoopybook, with 18 mongrel dogs.