PlanktonLake-CEREEP- A Freshwater Plankton Image Dataset with Semi-Automated Label Cleaning
Plankton plays a fundamental role in aquatic ecosystems, influencing biogeochemical cycles and serving as a key food source for many organisms. Recent high-throughput imaging technologies enable the rapid acquisition of large volumes of microscopic images, creating new opportunities for monitoring planktonic ecosystems. However, the manual processing and annotation of the vast amounts of data…
Plankton, a crucial component of aquatic ecosystems, contributes to biogeochemical cycles and serves as a vital food source for numerous organisms. With the advent of high-throughput imaging technologies, vast quantities of microscopic plankton images are now easily captured, presenting novel possibilities for monitoring these ecosystems.
However, manually processing and annotating the immense data produced by such devices remains a labor-intensive challenge. In such circumstances, machine learning-based classification models emerge as a promising solution.
This data paper presents a new labeled freshwater plankton dataset, encompassing roughly 88,000 images across 43 distinct taxa. To aid in the annotation process, the authors devised a labeling assistance method, which significantly streamlines the task. To evaluate the effectiveness of their approach, they developed a baseline utilizing a convolutional neural network (CNN), which achieves a remarkable classification accuracy of 93% on their dataset.
Written by urgent.news from bioRxiv's reporting — not their text. Machine-written — may contain errors; check the original before relying on it.
