Colony-YOLO: A Lightweight Micro-Colony Detection Network Based on Improved YOLOv8n

Colony-YOLO: A Lightweight Micro-Colony Detection Network Based on Improved YOLOv8n

The detection of colony-forming units (CFUs) is a time-consuming but essential task in mulberry bacterial blight research. To overcome the problem of inaccurate small-target detection and high computational consumption in mulberry bacterial blight colony detection task, a mulberry bacterial blight c...

Full description

Saved in:
Bibliographic Details
Main Authors: Meihua Wang, Junhui Luo, Kai Lin, Yuankai Chen, Xinpeng Huang, Jiping Liu, Anbang Wang, Deqin Xiao
Format: Article
Language:English
Published: MDPI AG 2025-07-01
Series:Microorganisms
Subjects:
colony detection
mulberry bacterial blight
YOLOv8
StarNet
attention mechanism
loss function
Online Access:https://www.mdpi.com/2076-2607/13/7/1617
Tags: Add Tag
No Tags, Be the first to tag this record!
Description
Summary:The detection of colony-forming units (CFUs) is a time-consuming but essential task in mulberry bacterial blight research. To overcome the problem of inaccurate small-target detection and high computational consumption in mulberry bacterial blight colony detection task, a mulberry bacterial blight colony dataset (MBCD) consisting of 310 images and 23,524 colonies is presented. Based on the MBCD, a colony detection model named Colony-YOLO is proposed. Firstly, the lightweight backbone network StarNet is employed, aiming to enhance feature extraction capabilities while reducing computational complexity. Next, C2f-MLCA is designed by embedding MLCA (Mixed Local Channel Attention) into the C2f module of YOLOv8 to integrate local and global feature information, thereby enhancing feature representation capabilities. Furthermore, the Shape-IoU loss function is implemented to prioritize geometric consistency between predicted and ground truth bounding boxes. Experiment results show that the Colony-YOLO achieved an mAP of 96.1% on MBCDs, which is 4.8% higher than the baseline YOLOv8n, with FLOPs and Params reduced by 1.8 G and 0.8 M, respectively. Comprehensive evaluations demonstrate that our method excels in detection accuracy while maintaining lower complexity, making it effective for colony detection in practical applications.
ISSN:2076-2607

Similar Items