A Comparative Analysis of Dog Emotion Classification Based on Four CNN Architectures
DOI:
https://doi.org/10.54097/jf7fm038Keywords:
Emotion Classification in Dogs, Transfer Learning, Efficientnet, Mobilenet, Comparative Experiments.Abstract
This study was research on the validation accuracy of different convolutional neural network (CNN) architectures in identifying the dog’s emotions based on their facial images. The goal is to recognize which model can best verify an animal's emotion. The four CNN models are: a custom-designed Original CNN (OCNN), MobileNetV2, EfficientNetB3, and EfficientNetB7. The experiment used a labeled dataset from Kaggle, which contains 4,000 dog facial images with four emotional states: happy, angry, sad, and relaxed, to train and preprocess the model. The research is using accuracy, precision, recall, and F1-score to evaluate the performance of the model. It was shown that EfficientNetB3 had the highest F1-score of 0.72, showcasing better model complexity and performance. In contrast, OCNN was underfitting, while EfficientNetB7 showed overfitting. This experiment highlights the importance of model choice in emotion classification tasks and provides some new views for the development of emotional computing systems in animal welfare.
References
[1] Wani, A., Pawar, U., Gatagat, Y., & Thalor, M.: ' Handwritten character recognition using CNN, KNN and SVM', International Journal of Technology Engineering Arts Mathematics Science, 2021, 1(2), 19–26
[2] Applebaum, J. W., Peek, C. W., & Zsembik, B. A.: ' Examining U.S. pet ownership using the General Social Survey', The Social Science Journal, 2020, 60(1), 110–119
[3] Wells, D. L.: 'Horse-training techniques that may defy the principles of learning theory and compromise welfare', Journal of Veterinary Behavior, 2010, 5(5), 226–234
[4] Pickersgill, O., Mills, D. S., & Guo, K.: 'Owners’ beliefs regarding the emotional capabilities of their dogs and cats', Animals,2023, 13(5), 820
[5] Albuquerque, N., Mills, D. S., Guo, K., et al.: 'Dogs can infer implicit information from human emotional expressions', Animal Cognition, 202225, 231–240
[6] Correia-Caeiro, C., Guo, K., & Mills, D. S.: 'Bodily emotional expressions are a primary source of information for dogs, but not for humans', Animal Cognition, 2021, 24, 267–279.
[7] Xie, Y.: 'Dogs emotion recognition and parameter analysis based on EfficientNet with transfer learning', Science and technology publictions. 2024.
[8] American Pet Products Association. State of the Industry Report, 2025.
[9] Begum, M., et al.: 'LCNN: Lightweight CNN architecture for software defect feature identification using explainable AI', IEEE Access, 2024, 12, 55748.
[10] Dataset Training. https://www.kaggle.com/datase ts/danielshanbalico/dog-emotion. 2025.
[11] Dataset Testing. https://www.kaggle.com/datasets /devzohaib/dog-emotions-prediction. 2025.
[12] Ng, A. Y.: 'Feature selection, L1 vs. L2 regularization, and rotational invariance. In Proceedings of the Twenty-First International Conference on Machine Learning (ICML '04), 78', 2004, Association for Computing Machinery, New York, NY
Downloads
Published
Issue
Section
License
This work is licensed under a Creative Commons Attribution-NonCommercial 4.0 International License.
How to Cite
