PS-Plant dataset
收藏资源简介:
自动叶子分割是计算机视觉中一个具有挑战性的领域。与传统的图像处理技术相比,机器学习方法的最新进展可以获得更好的结果; 但是,训练此类系统通常需要大量带注释的数据集。为了提供带注释的数据集并帮助克服植物表型研究中的这一瓶颈,在这里,我们提供了一种带有带注释的叶子掩模的新型光度立体 (PS) 数据集。该数据集构成了BBSRC工具和资源开发项目BB/N02334X/1中完成的工作的一部分。
Automatic leaf segmentation is a challenging field in computer vision. Compared with traditional image processing techniques, recent advances in machine learning methods can yield better results; however, training such systems typically requires large-scale annotated datasets. To address the need for annotated datasets and help overcome this bottleneck in plant phenotyping research, we herein present a novel photometric stereo (PS) dataset with annotated leaf masks. This dataset forms part of the work conducted under the BBSRC Tools and Resources Development Project grant BB/N02334X/1.




