ocr_drug

# ocr_drug ## 数据集描述 ocr_drug中的数据都是使用百度飞桨的OCR工具PPOCRLabel工具手工标准提取出来的药物、药品等外包装的文本字符数据集。 用来做ocr药品名称提取的实验使用。 ### 数据集简介 由333张药品外包装文字图片组成，用于药品名称识别测试。 ### Clone with HTTP ```bash git clone https://www.modelscope.cn/datasets/mitchell/ocr_drug.git ```# ocr_drug ## Dataset Description The ocr_drug dataset is a manually curated and standardly extracted text character dataset sourced from the packaging texts of medications and pharmaceutical products, utilizing Baidu PaddlePaddle's OCR tool PPOCRLabel. It is intended for experiments focused on OCR-based pharmaceutical name extraction. ### Dataset Overview This dataset consists of 333 images of text on pharmaceutical product packaging, designed for pharmaceutical name recognition testing. ### Clone with HTTP bash git clone https://www.modelscope.cn/datasets/mitchell/ocr_drug.git

搜集汇总

背景与挑战

背景概述

ocr_drug数据集包含333张药品外包装文字图片，用于OCR技术提取药品名称的实验，数据通过百度PaddlePaddle的PPOCRLabel工具标准化提取。