Plant Region Detection in Digitised Herbarium Specimens

This dataset was created as part of the <i>e-col+</i> project (ANR‐21‐ESRE‐005) to support detection of plant regions in digitised herbarium sheets. It is intended for use in training and evaluating computer vision models for plant detection and segmentation tasks.<b>Content</b>The dataset consists of digitised herbarium specimen images annotated with bounding boxes identifying the vegetative regions (i.e., plant material). It consists of <b>19,078 image patches</b> annotated with bounding boxes. Images were collected from the <b>ReColNat</b> website (<b>https://recolnat.fr</b>) and split into:<b>14,307</b> training samples<b>3,815</b> validation samples<b>956</b> test samplesThe dataset includes two main directories: <code>images/</code> and <code>labels/</code>, each subdivided into <code>train/</code>, <code>val/</code>, and <code>test/</code>folders. The <code>images/</code> directory contains RGB <code>.jpg</code> files, while the <code>labels/</code> directory includes annotation <code>.txt</code> files in YOLO format (class_id, x_center, y_center, width, height), with each label file named identically to its corresponding image. <br>