AUTHOR=Zhou Shizheng , Jiang Juntao , Hong Xiaohan , Fu Pengcheng , Yan Hong 

TITLE=Vision meets algae: A novel way for microalgae recognization and health monitor

JOURNAL=Frontiers in Marine Science

VOLUME=Volume 10 - 2023

YEAR=2023

URL=https://www.frontiersin.org/journals/marine-science/articles/10.3389/fmars.2023.1105545

DOI=10.3389/fmars.2023.1105545

ISSN=2296-7745

ABSTRACT=Marine microalgae are widespread in the ocean and play a crucial role in the ecosystem. The manual microscopic examination is laborious, error-prone and subject to human judgment, while benchtop automatic instruments are not suitable in field sampling. Automatic identification and location of marine microalgae in microscopy images would help establish marine ecological environment monitoring and water quality evaluation system. Therefore, a CV-based microfluidic algae detection method that combines microfluidic technology, microscopic image processing, and deep learning neural network was established for cell analysis. A new dataset for marine microalgae detection is proposed in this paper. Six classes of microalgae commonly found in the ocean (Bacillariophyta, Chlorella pyrenoidosa, Platymonas, Dunaliella salina, Chrysophyta, Symbiodiniaceae) are microscopically imaged in real-time. Images of Symbiodiniaceae in three physiological states known as normal, bleaching, and translating are also included. We annotated these images with bounding boxes using Labelme software and split them into the training and testing sets. The total number of images in the dataset is 937 and all the objects in these images were annotated. The total number of annotated objects is 4201. The training set contains 537 images and the testing set contains 430 images. Baselines of different object detection algorithms are trained, validated and tested on this dataset.