Enhanced Dog Breed Classification Using Transfer Learning and Convolutional Neural Networks

This paper presented an Enhanced Dog Breed Classification system leveraging transfer learning with the pre-trained ResNet50 Convolutional Neural Network architecture, specifically targeting the representational and scalability limitations that constrain conventional machine learning approaches — most notably SVM-based pipelines employing hand-crafted feature descriptors — when applied to fine-grained breed identification at scale. The proposed system integrates deep feature extraction, ImageNet-standard preprocessing, probabilistic softmax classification, and interactive result delivery within a unified, Flask-served web application, producing an end-to-end breed identification platform accessible through standard browser interfaces without requiring specialized client-side hardware or software installation. The system’s modular four-layer architecture — comprising Input, Processing, Intelligence, and Output and Presentation layers — enforces a principled separation of concerns that isolates preprocessing logic, inference computation, and result rendering into independently maintainable components. Experimental evaluation confirmed consistent functional correctness across diverse input image formats, resolutions, and color spaces, with strong top-k classification performance on unambiguous single-subject breed images drawn from the Stanford Dogs dataset. Inference latency of 1–3 seconds per image on CPU hardware establishes the system’s viability for interactive web-based deployment. By demonstrating that a high-capability deep learning inference pipeline can be constructed, deployed, and operated on standard academic laboratory hardware using exclusively open-source components, the project establishes a replicable template for AI-powered web application development accessible to institutions without dedicated research computing infrastructure. The system’s applicability to veterinary diagnostics support, pet adoption platform enhancement, animal shelter management, and lost pet recovery services further underscores the practical societal value of advancing fine-grained breed classification capability toward robust, scalable deployment.

[1] N. H. Pratama, E. Rachmawati, and G. Kosala, “Classification of dog breeds from sporting groups using convolutional neural network,” JIPI (Jurnal Ilmiah Penelitian Dan Pembelajaran Informatika), vol. 7, no. 4, pp. 1080–1087, Nov. 2022. [2] P. Borwarnginn, W. Kusakunniran, S. Karnjanapreechakorn, and K. Thongkanchorn, “Knowing your dog breed: Identifying a dog breed with deep learning,” International Journal of Automation and Computing, vol. 18, no. 1, pp. 45–54, Feb. 2021, doi: 10.1007/s11633-020-1261-0. [3] D. Kamdar, “Implementation of pre-trained deep learning model for dog breed classification,” Turkish Journal of Computer and Mathematics Education, vol. 120, no. 7, pp. 555–558, 2021. [4] D. M. Sundaram and A. Loganathan, “A new supervised clustering framework using multi discriminative parts and expectation–maximization approach for a fine-grained animal breed classification (SC-MPEM),” Neural Processing Letters, vol. 52, no. 1, pp. 727–766, Aug. 2020. [5] S. Ramaneswaran, K. Srinivasan, P. M. D. R. Vincent, and C.-Y. Chang, “Hybrid inception v3 XGBoost model for acute lymphoblastic leukemia classification,” Computational and Mathematical Methods in Medicine, vol. 2021, pp. 1–10, Jul. 2021, doi: 10.1155/2021/2577375. [6] C. Wang, J. Wang, Q. Du, and X. Yang, “Dog breed classification based on deep learning,” in Proc. 13th Int. Symp. Comput. Intell. Design (ISCID), Dec. 2020, pp. 209–212, doi: 10.1109/ISCID51228.2020.00053. [7] X. Tu, K. Lai, and S. Yanushkevich, “Transfer learning on convolutional neural networks for dog identification,” in Proc. IEEE 9th Int. Conf. Softw. Eng. Service Sci. (ICSESS), Nov. 2018, pp. 357–360, doi: 10.1109/ICSESS.2018.8663718. [8] A. Varshney, A. Katiyar, A. K. Singh, and S. S. Chauhan, “Dog breed classification using deep learning,” in Proc. Int. Conf. Intell. Technol. (CONIT), Jun. 2021, pp. 1–5, doi: 10.1109/conit51480.2021.9498338. [9] R. O. Sinnott, F. Wu, and W. Chen, “A mobile application for dog breed detection and recognition based on deep learning,” in Proc. IEEE/ACM 5th Int. Conf. Big Data Comput. Appl. Technol. (BDCAT), Dec. 2018, pp. 87–96, doi: 10.1109/BDCAT.2018.00019. [10] Z. Ráduly, C. Sulyok, Z. Vadászi, and A. Zölde, “Dog breed identification using deep learning,” in Proc. IEEE 16th Int. Symp. Intell. Syst. Informat. (SISY), Sep. 2018, pp. 271–276, doi: 10.1109/sisy.2018.8524715.