LeafMachine2 Data: Urticaceae Leaf Outlines and ECT
Fuente:
Zenodo
Enregistré dans:
| Auteur principal: | |
|---|---|
| Format: | Recurso digital |
| Publié: |
Zenodo
2025
|
| Sujets: | |
| Accès en ligne: | |
| Tags: |
Ajouter un tag
Pas de tags, Soyez le premier à ajouter un tag!
|
| _version_ | 1866901965521289216 |
|---|---|
| author | Weaver, William |
| author_facet | Weaver, William |
| contents | <p><strong>Urticaceae - 224,532 leaves - 31.3 GB: </strong>This repository contains HDF5 (.h5) files with leaf morphological data for species in the Urticaceae family. Each file represents a single leaf specimen and contains leaf shape outlines, the 128x128 ECT matrix, and associated metadata.</p> <h3>File Contents</h3> <p>This dataset contains <strong>224,532 leaves</strong> from taxa in the family <strong>Urticaceae</strong>. Some leaves may be partial, predated, broken, or incomplete. </p> <p>Each .h5 file contains the following datasets:</p> <ul> <li><strong><code>ECT_matrices/</code></strong> - Euler Characteristic Transform (ECT) matrices capturing topological features of leaf shapes</li> <li><strong><code>shapes/shape_0</code></strong> - Coordinate array (x,y) defining the leaf outline boundary. </li> <li><strong><code>component_names</code></strong> - Original filename identifier (without extension)</li> <li><strong><code>group_labels</code></strong> - Taxonomic classification dictionary containing: <ul> <li><code>family</code>: Taxonomic family name</li> <li><code>genus</code>: Genus classification</li> <li><code>genus_species</code>: Binomial species name</li> <li><code>fullname</code>: Complete taxonomic identifier</li> </ul> </li> </ul> <h3>Data Format</h3> <p>Files are organized with standardized naming: <code>[Herbarium]_[ID]_[Family]_[Genus]_[Species]__[LeafID].h5</code></p> <p>Shape coordinates are normalized to a unit circle centered at the origin (-0.5 to 0.5 range), vertically oriented.</p> <h3>Uncompressed Size:</h3> <p>31.3 GB</p> <h3>Usage</h3> <p>Code for reading, processing, and analyzing these files is available at: <a href="https://github.com/Gene-Weaver/LM2-Data-Tools" target="_blank" rel="noopener">https://github.com/Gene-Weaver/LM2-Data-Tools</a></p> <p>The repository includes functions for extracting data and generating visualizations.</p> <p><strong>Citation</strong>: Please cite the LeafMachine2 paper and this dataset.</p> <div> <div>Weaver, W. N., & Smith, S. A. (2023). From leaves to labels: Building modular machine learning networks for rapid herbarium specimen analysis with LeafMachine2. <em>Applications in Plant Sciences</em>, <em>11</em>(5), e11548. <a href="https://doi.org/10.1002/aps3.11548" target="_blank" rel="noopener">https://doi.org/10.1002/aps3.11548</a></div> </div> |
| format | Recurso digital |
| id | zenodo_https___doi_org_10_5281_zenodo_15572008 |
| institution | Zenodo |
| language | |
| publishDate | 2025 |
| publisher | Zenodo |
| record_format | zenodo |
| spellingShingle | LeafMachine2 Data: Urticaceae Leaf Outlines and ECT Weaver, William LeafMachine2 leaf outlines <p><strong>Urticaceae - 224,532 leaves - 31.3 GB: </strong>This repository contains HDF5 (.h5) files with leaf morphological data for species in the Urticaceae family. Each file represents a single leaf specimen and contains leaf shape outlines, the 128x128 ECT matrix, and associated metadata.</p> <h3>File Contents</h3> <p>This dataset contains <strong>224,532 leaves</strong> from taxa in the family <strong>Urticaceae</strong>. Some leaves may be partial, predated, broken, or incomplete. </p> <p>Each .h5 file contains the following datasets:</p> <ul> <li><strong><code>ECT_matrices/</code></strong> - Euler Characteristic Transform (ECT) matrices capturing topological features of leaf shapes</li> <li><strong><code>shapes/shape_0</code></strong> - Coordinate array (x,y) defining the leaf outline boundary. </li> <li><strong><code>component_names</code></strong> - Original filename identifier (without extension)</li> <li><strong><code>group_labels</code></strong> - Taxonomic classification dictionary containing: <ul> <li><code>family</code>: Taxonomic family name</li> <li><code>genus</code>: Genus classification</li> <li><code>genus_species</code>: Binomial species name</li> <li><code>fullname</code>: Complete taxonomic identifier</li> </ul> </li> </ul> <h3>Data Format</h3> <p>Files are organized with standardized naming: <code>[Herbarium]_[ID]_[Family]_[Genus]_[Species]__[LeafID].h5</code></p> <p>Shape coordinates are normalized to a unit circle centered at the origin (-0.5 to 0.5 range), vertically oriented.</p> <h3>Uncompressed Size:</h3> <p>31.3 GB</p> <h3>Usage</h3> <p>Code for reading, processing, and analyzing these files is available at: <a href="https://github.com/Gene-Weaver/LM2-Data-Tools" target="_blank" rel="noopener">https://github.com/Gene-Weaver/LM2-Data-Tools</a></p> <p>The repository includes functions for extracting data and generating visualizations.</p> <p><strong>Citation</strong>: Please cite the LeafMachine2 paper and this dataset.</p> <div> <div>Weaver, W. N., & Smith, S. A. (2023). From leaves to labels: Building modular machine learning networks for rapid herbarium specimen analysis with LeafMachine2. <em>Applications in Plant Sciences</em>, <em>11</em>(5), e11548. <a href="https://doi.org/10.1002/aps3.11548" target="_blank" rel="noopener">https://doi.org/10.1002/aps3.11548</a></div> </div> |
| title | LeafMachine2 Data: Urticaceae Leaf Outlines and ECT |
| topic | LeafMachine2 leaf outlines |
| url | https://doi.org/10.5281/zenodo.15572008 |