Chen, Szu YuSzu YuChenYAN-FU KUOLin, Hong YeHong YeLinHong-Ye LinSzu-Yu ChenChia-Lin ChungCHIA-LIN CHUNG2019-11-042019-11-042019-01-01https://scholars.lib.ntu.edu.tw/handle/123456789/430862© 2019 ASABE Annual International Meeting. All rights reserved. Culturing bacteria on agar plate is a common approach used for isolating bacterial colonies. The results of culturing is assessed by the number, size, and shape of the colonies on the agar plates. Conventionally, the assessing is performed by operators. Manual identification and counting of the colonies are time consuming. Also, misidentification occurs due to human fatigue. This study aimed to automatically count bacterial colonies on agar plates using deep learning. In the procedure, a convolutional neural network (CNN) model was trained to identify and count the colonies in the images of agar plates. Once developed, the CNN model was hosted as a cloud service. Hence, the counting of bacterial colonies can be achieved using mobile devices.Agar plate | Bacterial colony | Colony counting | Convolutional neural network | Deep learningconference paper10.13031/aim.2019004852-s2.0-85072941299https://api.elsevier.com/content/abstract/scopus_id/85072941299