Counting bacterial colony on agar plates using deep convolutional neural network
Journal
2019 ASABE Annual International Meeting
Date Issued
2019-01-01
Author(s)
Abstract
© 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.
Subjects
Agar plate | Bacterial colony | Colony counting | Convolutional neural network | Deep learning
Type
conference paper