LCU-Net: A novel low-cost U-Net for environmental microorganism image segmentation

• Published in: Pattern recognition Vol. 115; p. 107885
• Main Authors: Zhang, Jinghua, Li, Chen, Kosov, Sergey, Grzegorzek, Marcin, Shirahama, Kimiaki, Jiang, Tao, Sun, Changhao, Li, Zihan, Li, Hong
• Format: Journal Article
• Language: English
• Published: Elsevier Ltd 01-07-2021
• Subjects: Deep convolutional neural networks; Environmental miroorganisms; Image segmentation; Low-cost; Deep convolutional neural networks; Low-cost; Image segmentation; Environmental miroorganisms
• ISSN: 0031-3203; 1873-5142
• DOI: 10.1016/j.patcog.2021.107885

In this paper, we propose a novel Low-cost U-Net (LCU-Net) for the Environmental Microorganism (EM) image segmentation task to assist microbiologists in detecting and identifying EMs more effectively. The LCU-Net is an improved Convolutional Neural Network (CNN) based on U-Net, Inception, and concatenate operations. It addresses the limitation of single receptive field setting and the relatively high memory cost of U-Net. Experimental results show the effectiveness and potential of the proposed LCU-Net in the practical EM image segmentation field.