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

请问未开源的部分有推荐的论文吗 #15

Open
dqksnow opened this issue Mar 31, 2020 · 3 comments
Open

请问未开源的部分有推荐的论文吗 #15

dqksnow opened this issue Mar 31, 2020 · 3 comments

Comments

@dqksnow
Copy link

dqksnow commented Mar 31, 2020

作者你好,我是一名非计算机专业的本科生,我已跑通你的代码,并把lenet换成了其他识别率更高的网络,。如果我想实现你未开源的部分,你有推荐的论文吗?我比较菜,一直没找到合适的论文。

@Roujack
Copy link
Owner

Roujack commented Mar 31, 2020

我这个项目采用的思路比较传统,现在有比较好的end-to-end的模型,其识别公式鲁棒性和精确度更好,你可以看看TAP(CNN+RNN+Attention)这个模型。如果你只是想学习,在我开源的基础上进行改进,参考两方面的文章,一个是对字符之间的关系进行分类。第二个是结构分析,这个可以参考编译原理的语法分析方法(算符优先法,或者递归下降法),或者二维文法。

@tengerye
Copy link

@Roujack 请问二维文法的英文术语叫什么?

@Roujack
Copy link
Owner

Roujack commented May 28, 2020

@Roujack 请问二维文法的英文术语叫什么?

不太清楚二维文法的术语,我的意思是那种考虑空间关系的文法。我觉的,现在基于规则的方法效果可能没有连接主义的方法好。目前跟CNN+RNN+Attention不同的做法,可能通过Graph convolution network去做,不清楚mathematical expression recognition有没有相关文献,在表格识别就有,参考Rethinking table recognition using graph neural networks

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

3 participants