search

DayBreak-u / chineseocr_lite

超轻量级中文ocr，支持竖排文字识别, 支持ncnn、mnn、tnn推理 ( dbnet(1.8M) + crnn(2.5M) + anglenet(378KB)) 总模型仅4.7M
GNU General Public License v2.0
11.73k stars 2.25k forks source link

how to recognize the blank between two English words #131

Open ghost opened 4 years ago

ghost commented 4 years ago

How to recognize blank between two English words? for my current model, if I input one English sentence then the output will concatenate all the English words together. for example: inputed image:

36

recognized result:

A------l-ll-t-h--e--r-e-c--o--g-n-i-tiio---n--a-c-cc--ur-a--c-i-e-s---o--n--t-h---e => Alltherecognitionaccuraciesonthe

So how to recognize the blank between two English words?

Zrufy commented 4 years ago

hi how do you solve the problem of the output model with error core dumped?

ghost commented 4 years ago

yes, please refer to https://github.com/Holmeyoung/crnn-pytorch/issues/48#issuecomment-620557523

Zrufy commented 4 years ago

I wanted to ask you if the model obtained with Holmeyoung / crnn-pytorch are you able to convert it to ncnn. Thanks for helping me.

ghost commented 4 years ago

I'm not sure. I have no experience in converting model to ncnn.