DogFLW: Dog Facial Landmarks in the Wild Dataset

TL;DR

This paper introduces DogFLW, a new dataset with 3,274 annotated dog facial images featuring 46 landmarks, aiming to advance automated analysis of dog facial expressions for affective computing.

Contribution

The paper presents a novel, large-scale dataset of dog facial landmarks, filling a critical gap for research in animal affective computing and facial expression analysis.

Findings

Dataset contains 3,274 annotated dog images

Includes 46 facial landmarks based on anatomy

Enables future research in dog emotion recognition

Abstract

Affective computing for animals is a rapidly expanding research area that is going deeper than automated movement tracking to address animal internal states, like pain and emotions. Facial expressions can serve to communicate information about these states in mammals. However, unlike human-related studies, there is a significant shortage of datasets that would enable the automated analysis of animal facial expressions. Inspired by the recently introduced Cat Facial Landmarks in the Wild dataset, presenting cat faces annotated with 48 facial anatomy-based landmarks, in this paper, we develop an analogous dataset containing 3,274 annotated images of dogs. Our dataset is based on a scheme of 46 facial anatomy-based landmarks. The DogFLW dataset is available from the corresponding author upon a reasonable request.