Summary of Early Detection Of Coffee Leaf Rust Through Convolutional Neural Networks Trained on Low-resolution Images, by Angelly Cabrera et al.
Early Detection of Coffee Leaf Rust Through Convolutional Neural Networks Trained on Low-Resolution Images
by Angelly Cabrera, Kleanthis Avramidis, Shrikanth Narayanan
First submitted to arxiv on: 20 Jul 2024
Categories
- Main: Computer Vision and Pattern Recognition (cs.CV)
- Secondary: Machine Learning (cs.LG)
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 This paper addresses the pressing issue of coffee leaf rust, a fungal disease threatening Central American coffee production. Climate change exacerbates the problem by reducing the latency period between infection and symptom emergence, leading to more severe epidemics. To combat this, researchers explore deep learning models for early detection. However, these models require significant processing power and data, which can be scarce. To overcome these limitations, a preprocessing technique is proposed, utilizing high-pass filters to enhance lesion-contrast in training images. This method achieves over 90% performance across various evaluation metrics (precision, recall, F1-score, Dice coefficient), outperforming other methods and unaltered image usage. |
| Low | GrooveSquid.com (original content) | Low Difficulty Summary Coffee leaf rust is a big problem for coffee farmers. Climate change makes it worse by making the disease spread faster. To stop this from happening, scientists are trying to develop new ways to detect the disease early. One approach they’re exploring is using super-powerful computers and lots of data to teach machines to recognize signs of the disease. But these machines need a lot of power and data, which can be hard to find. So, researchers came up with an idea to make it easier by improving the quality of images used for training. This new method works really well, doing better than other methods in tests. |
Keywords
» Artificial intelligence » Deep learning » F1 score » Precision » Recall
