Martvel George ; Shimshoni Ilan ; Zamansky Anna

Abstract

The field of animal affective computing is rapidly emerging, and analysis offacial expressions is a crucial aspect. One of the most significant challengesthat researchers in the field currently face is the scarcity of high-quality,comprehensive datasets that allow the development of models for facialexpressions analysis. One of the possible approaches is the utilisation offacial landmarks, which has been shown for humans and animals. In this paper wepresent a novel dataset of cat facial images annotated with bounding boxes and48 facial landmarks grounded in cat facial anatomy. We also introduce alandmark detection convolution neural network-based model which uses amagnifying ensembe method. Our model shows excellent performance on cat facesand is generalizable to human facial landmark detection.