Summary of Recognition Of Harmful Phytoplankton From Microscopic Images Using Deep Learning, by Aymane Khaldi et al.
Recognition of Harmful Phytoplankton from Microscopic Images using Deep Learning
by Aymane Khaldi, Rohaifa Khaldi
First submitted to arxiv on: 19 Sep 2024
Categories
- Main: Computer Vision and Pattern Recognition (cs.CV)
- Secondary: Artificial Intelligence (cs.AI)
GrooveSquid.com Paper Summaries
GrooveSquid.com’s goal is to make artificial intelligence research accessible by summarizing AI papers in simpler terms. Each summary below covers the same AI paper, written at different levels of difficulty. The medium difficulty and low difficulty versions are original summaries written by GrooveSquid.com, while the high difficulty version is the paper’s original abstract. Feel free to learn from the version that suits you best!
| Summary difficulty | Written by | Summary |
|---|---|---|
| High | Paper authors | High Difficulty Summary Read the original abstract here |
| Medium | GrooveSquid.com (original content) | Medium Difficulty Summary A study evaluates several state-of-the-art CNN models, including ResNet, ResNeXt, DenseNet, and EfficientNet, using transfer learning approaches to classify eleven harmful phytoplankton genera from microscopic images. The best performance was achieved by ResNet-50 with an accuracy of 96.97%. The models struggled to differentiate between four harmful phytoplankton types with similar morphological features. |
| Low | GrooveSquid.com (original content) | Low Difficulty Summary A study helps us monitor plankton better. Right now, it’s hard and expensive to track which ones are bad for the environment. This study looks at how good some AI models are at recognizing bad plankton from tiny pictures. They tried different ways of using these models and found that one way worked best, getting 96% correct! The tricky part is telling apart four types of bad plankton that look similar. |
Keywords
» Artificial intelligence » Cnn » Resnet » Transfer learning
