StoManager1: Automated, High-throughput Tool to Measure Leaf Stomata Using Convolutional Neural Networks
Authors/Creators
- 1. Mississippi State University - Mississippi State, MS
- 2. Nanjing Normal University
Description
The characteristics of stomata on leaves are crucial for the performance of plants and their impact on global water and carbon cycling. However, manually counting stomata can be time-consuming, prone to bias, and limited to small scales and sample sizes. We have created StoManager1, a high-throughput tool that automates detecting, counting, and measuring stomata to address this issue. StoManager1 uses convolutional neural networks to estimate parameters such as stomatal density, area, orientation, and variance. Our results show that StoManager1 is highly precise and has an excellent recall for the stomatal characterizing leaves from various species. This tool can automate measuring leaf stomata, making it easier to explore how leaf stomata control and regulate plant growth and adaptation to environmental stress and climate change. An online demonstration of StoManager1 is available on GitHub at https://github.com/JiaxinWang123/StoManager.git. We have also developed a standalone, user-friendly Windows application for StoManager1 that does not require any programming or coding experience.
Notes
- Substantially improved group analysis speed.
- Added Toy dataset for users to play around.
- Updated line-edit default text.
- Fine-tuned weights for Hardwoods.
- Enhanced detection capacity for blurred images.
- Enhanced version with more stomatal metrics measured with geometrical algorithms!!
- Note: to use gpu version, you must have your cuda11.7 installed.
- Bugs fixed.
- Enhanced weights for non-nail polish images.
- Added functions to convert the units of width and length from pixels to μm.
- Added Stomata arrangement pattern indices, such as stomata evenness index, stomatal divergence index, and stomatal aggregation index.
- Enhanced models trained with more species such as ginkgo, poplar, cuticle, and usnm images from: Fetter, Karl C. et al. (2019), Data from: StomataCounter: a neural network for automatic stomata identification and counting, Dryad, Dataset, https://doi.org/10.5061/dryad.kh2gv5f.
- Bugs fixed (calculate stomata/guard cell area for image size over 1280*760). ---Fixed issues in generating stomatal indices.
- Support more image formats such as .jpg, .png, .tif, .jpeg.
- Fixed bugs for not continuing measurement when no stoma detected.
- Integrated custom datatset model training module.
- Fine-tunned weights for more species (over 100 species that were not in training dataset were tested).
- Fixed Group analysis bugs
Files
StoManager1.0.0_Manual.pdf
Files
(5.7 GB)
| Name | Size | Download all |
|---|---|---|
|
md5:70748993c1a378d618afd19e421a9877
|
752.5 MB | Download |
|
md5:452ac1485b7646794cb29880ca2ff7cc
|
2.1 GB | Download |
|
md5:6fde5c69dbfb6ed4a9ae24ef8d1ba536
|
69.9 MB | Download |
|
md5:fd57c4a91dbfbeb3ecb9185d66ea6a36
|
1.9 MB | Preview Download |
|
md5:5c0663bfb6a40a5978fea7f6e3cf4a91
|
2.2 GB | Download |
|
md5:94325d0b90c28367c126e2842bdd5aff
|
294.1 MB | Download |
|
md5:3d9247c2c44264aea721f9441ae89f6e
|
5.0 MB | Download |
|
md5:1dccccd66e629b8d5dbbebd5d9878f06
|
109.9 MB | Download |
|
md5:830825e4676edd8c7da3304f7a04b435
|
142.6 MB | Download |
Additional details
Related works
- References
- Publication: arXiv:2304.10450 (arXiv)