CotLeaf-X: Cotton Leaf Surface Images dataset with eXpert labels

This dataset is a collection of 5,049 images of cotton leaf surfaces acquired with a hand-held microscope to develop deep learning models for leaf hairiness and assist Cotton breeders in their variety selection efforts. These images were collected from two populations (A: 3,276 images; B: 1,773 images) over the 2021-2022 season in a field located at Australian Cotton Research Institute, -30.21, 149.60, Narrabri, NSW, Australia. Populations and genotypes have been anonymized to protect germplasm Intellectual Property.\n\nThis dataset is being released together with our HairNet2 paper (Farazi et al 2024). See below for links to related Datasets and Publications.\n\n\nLineage: Plant genotypes and growth conditions:\nTwo cotton populations called A and B, were selected for their heterogeneous leaf hairiness, with population A being generally less hairy than population B. Both populations were planted in the summer growing season of 2021-22 at ACRI. Seeds of each genotype were planted in a field on the 23rd of October 2021 at a planting density of 10-12 plants/m2 in rows spaced at 1m. Each genotype was grown in a single 13m plot.\n\nLeaf selection and imaging\nLeaf samples from these plant populations were collected on the 2nd and 6th of March 2022 (at 19 weeks, first open boll stage). Leaf 3 was harvested from 10 plants per genotype, placed in a paper bag and imaged the same day using the same protocol and equipment as in Rolland, Farazi et al 2022, with the following distinctions:\n- for population A, two images were collected per leaf: one along the central midvein and one on the leaf blade.\n- for population B, one image was collected per leaf: along the central midvein.\nThe abaxial side of leaves were imaged at a magnification of about 31x with a portable AM73915 Dino-lite Edge 3.0 (AnMo Electronics Corporation, Taiwan) microscope equipped with a RK-04F folding manual stage (AnMo Electronics Corporation, Taiwan) and connected to a digital tablet running DinoCapture 2.0 (AnMo Electronics Corporation, Taiwan). The exact angle of the mid-vein in each image was not fixed. However, either end of the mid-vein was always cut by the left and right borders of the field of view, and never by the top and bottom ones. \n\nVisual scoring of images by human expert\nA human expert scored all CotLeaf-X images using arbitrary ordinal scales (0 − 5 for population A and 2 − 5.5 for population B), where higher numbers corresponded to images with more trichomes.

本数据集包含5049张棉花叶片表面图像，均通过手持显微镜（hand-held microscope）采集，旨在开发用于叶片茸毛性状（leaf hairiness）分析的深度学习模型（deep learning models），并助力棉花育种者开展品种选育工作。该数据集的图像采集于澳大利亚棉花研究所（Australian Cotton Research Institute）位于澳大利亚新南威尔士州纳拉布里（Narrabri）的试验田（坐标：-30.21, 149.60），采集时段为2021-2022生长季，共分为两个群体：群体A包含3276张图像，群体B包含1773张图像。为保护种质知识产权（germplasm Intellectual Property），所有群体及基因型均已做匿名化处理。

本数据集将与我们的HairNet2论文（Farazi等人，2024）同步发布，相关数据集与论文的链接见下文。

谱系：植物基因型与生长条件：
选取两个叶片茸毛性状存在异质性的棉花群体A与B，其中群体A的叶片茸毛密度普遍低于群体B。两个群体均于2021-2022夏季生长季种植于澳大利亚棉花研究所（Australian Cotton Research Institute，简称ACRI）试验田。每个基因型的种子于2021年10月23日播种于大田，种植密度为10-12株/平方米，行距为1米，每个基因型种植于13米长的试验小区（plot）中。

叶片选取与成像：
分别于2022年3月2日与3月6日采集上述植物群体的叶片样本，此时处于种植后第19周，为首次开铃期（open boll stage）。从每个基因型的10株植株上采集第3片叶，装入纸袋后于当日完成成像，成像流程与设备参考Rolland、Farazi等人2022年的研究，但存在以下区别：
- 群体A：每片叶采集两张图像，一张沿中央主脉（central midvein）拍摄，一张于叶片区域拍摄；
- 群体B：每片叶采集一张图像，沿中央主脉拍摄。
拍摄部位为叶片远轴面（abaxial side），放大倍率约31×，使用配备RK-04F折叠手动载物台的便携式AM73915 Dino-lite Edge 3.0显微镜，由中国台湾安磨电子股份有限公司（AnMo Electronics Corporation）生产，连接运行DinoCapture 2.0软件的数位平板（digital tablet）。每张图像中主脉的精确角度未作固定，但主脉的两端始终被视野的左右边界裁切，未被上下边界裁切。

人工专家视觉评分：
一名领域专家采用任意序数量表对所有CotLeaf-X图像进行评分：群体A的评分区间为0-5，群体B的评分区间为2-5.5，数值越高代表图像中表皮毛（trichomes）越多。