A development of cat face recognition model using deep learning
Article Sidebar
Main Article Content
Abstract
Currently, the number of pets in Thailand is increasing every year. Unfortunately, these pets may get lost or lost. Cats are one of the most popular pets. The rate of cats getting lost and returning is only 64 percent. In addition, the death rate of lost cats is twice as high as that of dogs. Cat identification can help to locate them or provide information about lost cats. Traditional cat identification methods, such as ear tattooing and microchipping, have many limitations. Among them are violence against animals, the risk of infection, or the possibility of the device being lost. This article introduces the development of cat face recognition to identify lost cats by their faces. This is a non-violent and low-cost method. It is an application of a method based on human facial identification. The method for recognizing cat faces consists of 3 steps: 1) A step for detecting cat faces in images, which can detect the face and the position of the ears, eyes, and nose. 2) A step to learn features from facial images of identical pairs of the same cat and different pairs of different cats. 3) An identification step is a process in which features extracted from cat faces are used to sort or compare other data sets using the K-NN method to find the number of similar faces and identify which cat is in the database. The experimental results found that the developed model for face detection has a mAP value of 0.995 by the top-5 identification process. The Identification has been shown to be 89% accurate.
Article Details
References
ณัฐโชติ พรหมฤทธิ์, & สัจจาภรณ์ ไวจรรยา. (2564). Fundamental of deep learning in practice. Hytexts Interactive Limited.
ปริญญา สงวนสัตย์. (2562). Artificial intelligence with machine learning, AI สร้างได้ด้วยแมชชีนเลิร์นนิ่ง. Infopress.
Chen, Y. C., Hidayati, S. C., Cheng, W. H., Hu, M. C., & Hua, K. L. (2016). Locality constrained sparse representation for cat recognition. In MultiMedia Modeling (pp. 140-151).
Ethem, A. (2010). Introduction to machine learning second edition. The MIT Press Cambridge.
He, K., Zhang, X., Ren, S., & Sun, J. (2016). Deep residual learning for image recognition. In Proceedings of the IEEE conference on computer vision and pattern recognition (pp. 770-778).
Hermans, A., Beyer, L., & Leibe, B. (2017). In defense of the triplet loss for person re-identification. arXiv preprint arXiv:1703.07737.
Kantar Worldpanel. (2022, December 5). Thailand pet food market trends. https://www.kantarworldpanel.com/th/news/2022-Thailand-Pet-Food-Market-Trends
Klein, A. (2019). Pet cat face verification and identification. Stanford University, CS230 Fall 2019.
Kumar, S., & Singh, S. K. (2018). Monitoring of pet animal in smart cities using animal biometrics. Indian Institute of Technology.
Kumar, S., & Singh, S. (2014). Biometric recognition for pet animal. Journal of Software Engineering and Applications, 7, 470-482.
Lai, K., Tu, X., & Yanushkevich, S. (2019). Dog identification using soft biometrics and neural networks. In International Joint Conference on Neural Networks (IJCNN) (pp. 1-8).
Lin, T. Y., & Kuo, Y. F. (2018). Cat face recognition using deep learning. ASABE Annual International Meeting.
Liu, J., Kanazawa, A., Jacobs, D., & Belhumeur, P. (2012). Dog breed classification using part localization. In Computer Vision – ECCV 2012 (pp. 172-185).
Montenegro, L., Abreu, M., Fred, A., & Machado, J. M. (2022). Human-assisted vs. deep learning feature extraction: An evaluation of ECG features extraction methods for arrhythmia classification using machine learning. Applied Sciences.
Moreira, T. P., Perea, M. L., Werneck, R. O., & Valle, E. (2017). Where is my puppy? Retrieving lost dogs by facial features. Multimedia Tools and Applications, 76, 15325-15340.
Mougeot, G., Li, D., & Jia, S. (2019). A deep learning approach for dog face verification and recognition. In PRICAI 2019: Trends in Artificial Intelligence (pp. 418-430).
Qi, D., Tan, W., Yao, Q., & Liu, J. (2022). YOLO5Face: Why reinventing a face detector. arXiv preprint arXiv:2105.12931. Retrieved from https://arxiv.org/abs/2105.12931
Redmon, J., Divvala, S. K., Girshick, R. B., & Farhadi, A. (2016). You only look once: Unified, real-time object detection. arXiv preprint arXiv:1506.02640. Retrieved from https://arxiv.org/abs/1506.02640
Ren, S., He, K., Girshick, R., & Sun, J. (2015). Faster R-CNN: Towards real-time object detection with region proposal networks. IEEE Transactions on Pattern Analysis and Machine Intelligence, 39, 1137-1149. https://doi.org/10.1109/TPAMI.2016.2577031
Ruan, Z., Wang, G., Xue, J., Lin, X., & Jiang, Y. (2014). Detection of user-registered dog faces. Neurocomputing, 142, 256-266.
Yoon, B., So, H., & Rhee, J. (2021). A methodology for utilizing vector space to improve the performance of a dog face identification model. Applied Sciences, 11, 2074.
Zhang, X., Yu, F. X., Kumar, S., & Chang, S. F. (2017). Learning spread-out local feature descriptors. In IEEE International Conference on Computer Vision (ICCV) (pp. 4605-4613).
