Gmgge / ImageAnalysisServiceLinks
轻量模型的图像分析web服务,包括倾斜矫正OCR,公章(印章)检测+识别,车牌识别。api方案使用FastAPI+Gunicorn,提供gradio展示。
☆101Updated last year
Alternatives and similar repositories for ImageAnalysisService
Users that are interested in ImageAnalysisService are comparing it to the libraries listed below
Sorting:
- 基于transformer的ocr识别,在公章(印章识别, seal recognition)拓展应用☆243Updated 3 weeks ago
- 卡证和文档检测和矫正☆66Updated 10 months ago
- 检测和提取各种场景图片中的表格区域,并纠正透视和旋转问题 Detect and extract table regions from images in various scenarios, and correct perspective and rotation i…☆103Updated 7 months ago
- 文档方向分类☆221Updated 8 months ago
- 修正文档扭曲/模糊/阴影等情况,使用onnx模型简单轻量部署,未来持续跟进最新最好的文档矫正方案和模型,Correct document distortion using a lightweight ONNX model for easy deployment. We wi…☆69Updated 7 months ago
- 中文版面检测(Chinese layout detection),yolov8 is used to detect the layout of Chinese document images。☆58Updated 2 years ago
- Style-Text data synthesis tool☆57Updated 7 months ago
- transformers ocr for chinese☆399Updated 2 years ago
- Recognition of Various Common Seal Scans in Complex Environments☆47Updated last year
- PPOCRLabelv2 is a semi-automatic graphic annotation tool suitable for OCR field, with built-in PP-OCR model to automatically detect and r…☆261Updated last month
- 通过浏览器渲染生成表格图像☆231Updated last year
- 印章检测和印章文字识别☆19Updated last year
- Convert the model in PaddleOCR to ONNX format☆92Updated 3 weeks ago
- 基于序列表格识别算法推理库,集成PP-Structure和modelscope等表格识别算法。☆340Updated 3 weeks ago
- Analysis of Chinese and English layouts 中英文版面分析☆234Updated 3 weeks ago
- 飞桨 智能标注,让标注快人一步☆289Updated 8 months ago
- ☆16Updated 10 months ago
- 从NLP出发对于OCR的深度实践集锦,重在实战☆89Updated 4 years ago
- 🔥Char detection base on crnn 字符(单字)检测基于CRNN☆83Updated 2 years ago
- 文档图像处理工具(Document image processing tool),包括漂白 / 文字方向矫正 / 清晰增强 / 笔记去噪美化 / 去阴影 / 扭曲矫正 / 切边增强(DocBleach / TextOrientationCorrection / DocSha…☆82Updated 11 months ago
- 印章目标检测以及印章内信息提取。☆18Updated last year
- A toolbox of ocr models and algorithms based on MindSpore☆278Updated last week
- 【间隙·树·排序算法】 对OCR结果或PDF提取的文本进行版面分析,按人类阅读顺序进行排序。☆146Updated last year
- ☆25Updated 3 years ago
- 该项目是为了使用layoutlmv3针对中文图片训练和推理。 其中主要解决三个问题: 1.数据标准化成可以的训练数据集格式 2.layoutlmv3-base-chinese 分词修改 2.超过512长度的文本切分和滑窗操作☆55Updated 11 months ago
- DocTr++ in PaddlePaddle☆52Updated last year
- 基于TrOCR + UniMER-1M数据集,训练一个小而美的公式识别模型☆25Updated last month
- ✅Deploy PaddleOCR with flask | 利用Flask对PaddleOCR进行部署,方便调用☆41Updated 3 years ago
- Based on RapidOCR, extract the PDF content☆179Updated 3 months ago
- table detect(yolo) , table line(unet)☆256Updated last year