Code Monkey home page Code Monkey logo

Comments (4)

hiroi-sora avatar hiroi-sora commented on June 17, 2024

开源通用模型库,可能一般不会训练斜杠0这种较少见的情景。

非通用领域的任务需求,需要用专门的训练集来训练和微调模型。目前可用于行驶证识别的开源引擎较少,效果没有保证;因此Umi-OCR暂时不会添加该功能。

如果你有大量需求,建议使用付费的商业服务。百度、阿里云等服务商,都提供了成熟的证件识别(包括行驶证)的接口。

请参考:
https://cloud.baidu.com/product/ocr_cars/vehicle_license
https://help.aliyun.com/document_detail/442298.html
https://developers.weixin.qq.com/miniprogram/dev/OpenApiDoc/img-ocr/ocr/vehicleLicenseOCR.html
https://support.huaweicloud.com/api-ocr/ocr_03_0034.html

from umi-ocr.

954224685 avatar 954224685 commented on June 17, 2024

通用领域的任务需求,需要用专门

感谢回复,是否有其他方式解决呢,我理解的目前的识别也是训练支持的,那是否可以单独加入这个0的训练,比如说我单独训练一下这个0,然后加资源库加到现在的系统里面?再次感谢

from umi-ocr.

hiroi-sora avatar hiroi-sora commented on June 17, 2024

PaddleOCR支持自己训练/微调模型库,然后将自己的模型库导入Umi-OCR。

训练模型的要求:

  • 拥有一些训练数据,比如一批行驶证图片及对应标签(人工识别结果)。
  • 较好的电脑,最好拥有支持CUDA的高配显卡
  • 有一定Python使用经验

训练步骤:

https://github.com/PaddlePaddle/PaddleOCR/blob/release/2.7/doc/doc_ch/recognition.md
https://github.com/PaddlePaddle/PaddleOCR/blob/release/2.7/doc/doc_ch/training.md

训练完成后,模型导入Umi的步骤:

可参考 #316 (comment)

另:单独训练一个0,可能效果不会太好。Paddle引擎是按行作为处理单位,而不是按单字。按照传统方式,一般是用整张图片(行驶证)做训练。

from umi-ocr.

954224685 avatar 954224685 commented on June 17, 2024

from umi-ocr.

Related Issues (20)

Recommend Projects

  • React photo React

    A declarative, efficient, and flexible JavaScript library for building user interfaces.

  • Vue.js photo Vue.js

    🖖 Vue.js is a progressive, incrementally-adoptable JavaScript framework for building UI on the web.

  • Typescript photo Typescript

    TypeScript is a superset of JavaScript that compiles to clean JavaScript output.

  • TensorFlow photo TensorFlow

    An Open Source Machine Learning Framework for Everyone

  • Django photo Django

    The Web framework for perfectionists with deadlines.

  • D3 photo D3

    Bring data to life with SVG, Canvas and HTML. 📊📈🎉

Recommend Topics

  • javascript

    JavaScript (JS) is a lightweight interpreted programming language with first-class functions.

  • web

    Some thing interesting about web. New door for the world.

  • server

    A server is a program made to process requests and deliver data to clients.

  • Machine learning

    Machine learning is a way of modeling and interpreting data that allows a piece of software to respond intelligently.

  • Game

    Some thing interesting about game, make everyone happy.

Recommend Org

  • Facebook photo Facebook

    We are working to build community through open source technology. NB: members must have two-factor auth.

  • Microsoft photo Microsoft

    Open source projects and samples from Microsoft.

  • Google photo Google

    Google ❤️ Open Source for everyone.

  • D3 photo D3

    Data-Driven Documents codes.