How to Cite: Sitepu, A. C., Liu, C.-M., Sigiro, M., Panjaitan, J., & Copa, V. (2022). A convolutional neural network bird’s classification using north American bird images. International Journal of Health Sciences, 6(S2), 15067–15080. https://doi.org/10.53730/ijhs.v6nS2.8988 International Journal of Health Sciences ISSN 2550-6978 E-ISSN 2550-696X © 2022. Manuscript submitted: 27 March 2022, Manuscript revised: 18 May 2022, Accepted for publication: 9 June 2022 15067 A convolutional neural network bird’s classification using north American bird images Ade Clinton Sitepu International Electrical Engineering and Computer Science National Taipei University of Technology Corresponding author email: t110999406@ntut.org.tw Chuan-Ming Liu Department of Computer Science and Information Engineering National Taipei University of Technology Email: cmliu@ntut.edu.tw Mula Sigiro Department of Physics Education University of HKBP Nommensen Email: mulasigiro@gmail.com Joel Panjaitan Department of Electrical Engineering Academy of Deli Serdang Engineering Email: joel.pandjaitan@gmail.com Venkatesh Copa International Electrical Engineering and Computer Science National Taipei University of Technology Email: t110998406@ntut.org.tw Abstract---In general, image classification is more like to classify objects with large categories, where these objects have a low level of similarity that is relatively rare. Birds image classification is a tough image dataset annotated with many bird species. It may be a challenging issue as numerous of the species of birds have degree of visual closeness. Bird species recognition can be challenging for people, let alone computer vision calculations. To analyze the image, this paper resizes the image into 224 224 pixels. We use the Convolutional Neural network (CNN) approach and add the structure of MobileNetV2, EfficientNetB0, EfficientNetB3 and the weight of the network that has previously trained using ImageNet. This paper attempts to analyze the comparative results from using MobileNetV2, EfficientNetB0 and EfficientNetB3 architecture. The F1 weighted average score MobileNetV2 is 75%, EfficientNet B0 is 81% and