ARAN/Recent content on ARANHugo -- 0.147.0en-us<link>/download/</link><pubDate>Mon, 01 Jan 0001 00:00:00 +0000</pubDate><guid>/download/</guid><description><h2 id="license-information">License information</h2> <p>The ARAN dataset is released under the Creative Commons Attribution-NonCommercial 4.0 International license. By requesting to download this dataset, you agree to:</p> <ul> <li>Use the dataset only for research purposes</li> <li>Not redistribute the dataset for commercial purposes</li> <li>Cite our paper in any resulting publications</li> </ul> <div style="text-align: center; margin-top: 2em;"> <a href="https://dataverse.nl/dataset.xhtml?persistentId=doi:10.34894/FWYPYC" target="_blank" style="display: inline-block; padding: 0.75em 1.5em; background-color: #007BFF; color: white; border-radius: 8px; text-decoration: none; font-weight: bold;"> Request Dataset </a> </div></description></item><item><title/><link>/</link><pubDate>Mon, 01 Jan 0001 00:00:00 +0000</pubDate><guid>/</guid><description><h1 id="aran-age-restricted-anonymized-dataset-of-children-images-and-body-measurements">ARAN: Age-restricted Anonymized Dataset of Children Images and Body Measurements</h1> <p align="center">Hezha MohammedKhan, Cascha van Wanrooij, Eric Postma, Çiçek Güven, Marleen Balvert, Heersh Hmh Raof Saeed, Chenar Omer Ali</p> <img src="./images/main_image.webp" alt="Sample images" style="width: 100%; height: auto;" /> <h2 id="about">About</h2> <p>Precisely estimating a child’s body measurements and weight from a single image is useful in pediatrics for monitoring growth and detecting early signs of malnutrition. The development of estimation models for this task is hampered by the unavailability of a labeled image dataset to support supervised learning. This paper introduces the ‘‘Age-Restricted ANonymized’’ (ARAN) dataset, the first labeled and GDPR-approved image dataset of children with body measurements. The ARAN dataset consists of images of 512 children aged 16 to 98 months, each captured from four different viewpoints, i.e., 2048 images in total. The dataset includes each child’s height, weight, age, waist circumference, and head circumference measurements, which is GDPR-approved because we used masks to cover the faces of the children. The dataset is a solid foundation for developing prediction models for various tasks related to these measurements. To create a suitable reference, we trained state-of-the-art deep learning algorithms on the ARAN dataset to predict to predictrectly from the images. The best results are obtained by a DenseNet121 model achieving competitive estimates for the body measurements, outperforming state-of-the-art results on similar tasks. The ARAN dataset is developed as part of a collaboration to create a mobile App to measure children’s growth and detect early signs of malnutrition contributing to the United Nations Sustainable Development Goals.</p></description></item><item><title>Leaderboard/leaderboard/Mon, 01 Jan 0001 00:00:00 +0000/leaderboard/<table class="sortable"> <thead> <tr> <th>Rank</th> <th>Method</th> <th>Authors</th> <th>MAE Height (CM)</th> <th>MAE Weight (KG)</th> <th>MAE Waist (CM)</th> <th>MAE Head Circ (CM)</th> </tr> </thead> <tbody> <tr> <td>1</td> <td>DenseNet121</td> <td>Mohammedkhan et al.</td> <td>2.5</td> <td>1.5</td> <td>2.5</td> <td>1.5</td> </tr> </tbody> </table>