Domestic Cats Facial Expression Recognition Based on Convolutional Neural Networks

Despite extensive research on Facial Expression Recognition (FER) in humans using deep learning technology, significantly less focus has been placed on applying these advancements to recognize facial expressions in domestic animals. Recognizing this gap, our research aims to extend FER techniques specifically to domestic cats, one of the most popular domestic pets. In this paper, we present a real-time system model that employs deep learning to identify and classify cat facial expressions into four categories: Pleased, Angry, Alarmed, and Calm. This innovative model not only helps cat owners understand their pets' behavior more accurately but also holds substantial potential for applications in domestic animal health services. By identifying and interpreting the emotional states of cats, we can address a critical need for improved communication between humans and their pets, fostering better care and well-being for these animals. To develop this system, we conducted extensive experiments and training using a diverse dataset of cat images annotated with corresponding facial expressions. Our approach involved using convolutional neural networks (CNNs) to analyze and learn from the subtleties in feline facial features by investigating the models' robustness considering metrics such as accuracy, precision, recall, confusion matrix, and f1-score. The experimental results demonstrate the high recognition accuracy and practicality of our model, underscoring its effectiveness. This research aims to empower pet owners, veterinarians, and researchers with advanced tools and insights, ensuring the well-being and happiness of domestic cats. Ultimately, our work highlights the potential of FER technology to significantly enhance the quality of life for cats by enabling better understanding and more responsive care from their human companions