Image segmentation masks for curved arrows on molecular images from chemical reaction mechanism images

The dataset presented herein is designed as a ground truth for image segmentation tasks focused on noise extraction in Optical Chemical Structure Recognition (OCSR) processes. It comprises 73 manually extracted and annotated images from real reaction mechanism images, along with 5320 synthetic molecular images generated using RDKit, each featuring computer-drawn curved arrows on random locations on the molecular image pertinent to their respective tasks. Curved arrows are prevalent in chemical reaction mechanism images and significantly impact the accuracy of molecular identity recognition. This dataset aims to enhance OCSR tasks by enabling the pretreatment of molecular images to remove noise, thereby improving molecular recognition accuracy.本数据集被设计为光学化学结构识别（Optical Chemical Structure Recognition, OCSR）流程中面向噪声提取的图像分割任务的基准真值数据集。数据集包含73张从真实反应机理图像中手动提取并标注的图像，以及5320张通过RDKit生成的合成分子图像；每张合成图像均在与对应任务相关的分子图像随机位置处，添加了计算机绘制的弯曲箭头。弯曲箭头在化学反应机理图像中极为常见，且会显著影响分子身份识别的准确率。本数据集通过支持分子图像的去噪预处理操作，以提升分子识别精度，进而优化OCSR任务的整体性能。