Skip to content
New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

SampleOCR希望越来越强大,不用裁剪! #155

Open
xinsuinizhuan opened this issue May 29, 2020 · 10 comments
Open

SampleOCR希望越来越强大,不用裁剪! #155

xinsuinizhuan opened this issue May 29, 2020 · 10 comments

Comments

@xinsuinizhuan
Copy link

No description provided.

@zuoqing1988
Copy link
Owner

前面加个检测器就行

@xinsuinizhuan
Copy link
Author

只能识别这种横着的吗,倾斜的和竖直的能识别不?

@zuoqing1988
Copy link
Owner

需要检测器先检测到,然后矫正

@xinsuinizhuan
Copy link
Author

支持中文识别不?还是只能识别数字和英文?

@zuoqing1988
Copy link
Owner

只要有模型,都可以。
这只是个框架,有啥模型转上去就行了

@xinsuinizhuan
Copy link
Author

只要有模型,都可以。
这只是个框架,有啥模型转上去就行了

https://github.com/ouyanghuiyu/chineseocr_lite,这个的模型能转不?

@zuoqing1988
Copy link
Owner

我能转,但是一般人转不了。因为我懂两种模型的细节,知道怎么把值填进去。

@xinsuinizhuan
Copy link
Author

我能转,但是一般人转不了。因为我懂两种模型的细节,知道怎么把值填进去。

膜拜。有时间了,给转一个!左大神!现在来看C++的ocr,貌似这个相对来说不错。

@zuoqing1988
Copy link
Owner

轻量级OCR的精度都不高,这个chineseocr_lite也就能演示一下而已,拿去卖钱还差得远。

@xinsuinizhuan
Copy link
Author

轻量级OCR的精度都不高,这个chineseocr_lite也就能演示一下而已,拿去卖钱还差得远。

对我们来说,这种级别的一般都够了,像屏幕中数字读数识别这种应用。票据识别的还,可能不够。

Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment
Labels
None yet
Projects
None yet
Development

No branches or pull requests

2 participants