Find research datasets worth reusing

Sainfoin Fruit Processing - Object Detection Dataset

<p>This dataset consists of 500 images of sainfoin (Onobrychis viciifolia) seed pods, seed, and split seeds. The images were taken as a part of an experiment to determine minimum sample size of seed pods needed to accurately estimate pod threshing trait heritability within sainfoin breeding lines.</p><p>The experiment was a complete factorial design with the following factors:</p><ul><li>Sainfoin named varieties: AAC Mountainview, Delaney, Eski , Rocky Mountain Remont, and Shoshone</li><li>Sample Size: 1, 2, 3, 4, and 5 grams of dried seed pods</li><li>Two different threshing types: Belt thresher processed 3X, Haldrup Impact Thresher (35sec @ Speed 9)</li></ul><p>This makes for a total factorial combination set of 5 varieties X 5 sample sizes X 2 threshing types = 50.</p><p>Each combination was comprised of 10 individual replicates where each replicate in a combination was a unique, random sample of seeds of the same mass (So, 10 random, 2g samples of Eski seed, processed by belt thresher; 10 random, 5g samples of Delaney seed processed by the Haldrup thresher, etc.). This makes for a total of 500 experimental units that comprise the sample set.</p><p>Once the seeds were sampled, weighed, and processed through the threshing equipment, they were weighed again and imaged.</p><p>The threshed seeds were scattered onto an imaging platform with a blue background, lit by 2 LED panels, and photographed with a Sony ILCE-7RM2 at the following settings:</p><ul><li>ISO: 100</li><li>Exposure: 1/40s</li><li>Focal Length: 55mm</li><li>Format: TIFF</li><li>Size: 7968x5320</li></ul><p>The raw images were converted from TIFF files to JPEG format and annotated in image labeling software. The seed objects were annotated with bounding boxes classified as the following classes</p><ol><li>pod: an enclosed seed pod</li><li>seed: a seed which was successfully threshed from the legume pod carpel</li><li>split: a seed threshed from the pod, but which split in two halves during the threshing process</li></ol><p>All image annotations were exported into the convenient <a href="https://docs.aws.amazon.com/rekognition/latest/customlabels-dg/md-coco-overview.html">COCO format</a>.</p><p>No further image processing was performed.</p><p>The image set was split into a 80/20 training and validation step using `scikit-learn` in Python 3.11 stratifying the datasets equally over the various experimental factor levels.</p><p>The zip file 'train_val_images.zip' contains a 'train' folder with 400 training images, 'val' containing 100 validation images, an image taken with a color correction card named 'color_test.jpg', and a json file with all the annotations.</p><p>Another file called 'seed_weights.csv' contains the image_name to global-key mapping in tabular format as well as the before and after threshing seed weights for each experimental sample.</p><p><strong>Labeling Metrics:</strong></p><ul><li>Pod (48.58%)<ul><li>36,599 objects</li></ul></li><li>Seed (33.83%)<ul><li>25,488 object</li></ul></li><li>Split (17.59%)<ul><li>13,255 objects</li></ul></li><li><strong>TOTAL (100%)</strong><ul><li><strong>75,342 objects</strong></li></ul></li></ul>