Show HN: Pytorch Text Recognition Tool

#1

Post by s3nh_ » Tue, Sep 03, 2019, 9:02 AM UTC

Show HN: Pytorch Text Recognition Tool
github.com

Re: Show HN: Pytorch Text Recognition Tool

#2

Post by abeppu » Tue, Sep 03, 2019, 3:05 PM UTC

In the example on the readme, why does it reverse the order of "casteli" (3) and "castle" (4)? It's a bit surprising that it understand the rest of the ordering (including the "and" in the center), but flips those two.

Also, if I were a developer trying to use this, I'd be constantly annoyed at receiving a dict with keys like "0", "1", "2" rather than just getting a list.

Re: Show HN: Pytorch Text Recognition Tool

#3

Post by s3nh_ » Tue, Sep 03, 2019, 4:19 PM UTC

abeppu wrote: post #2

In the example on the readme, why does it reverse the order of "casteli" (3) and "castle" (4)? It's a bit surprising that it understand the rest of the ordering (including the "and" in the center), but flips those two. Also, if I were a developer trying to use this, I'd be constantly annoyed at receiving a dict with keys like "0", "1", "2" rather than just getting a list.

In the example, text is not sorted by it's corrdinates but by appearence of boxes in first network. It is visible in more complex documents, that crnn network did not create boxes in descending order (word-by-word).

also, good point about the list. dictionary keys has no logical usage in this one.

Re: Show HN: Pytorch Text Recognition Tool

#4

Post by dpaluy » Tue, Sep 03, 2019, 4:25 PM UTC

How to train this model in other languages?

Re: Show HN: Pytorch Text Recognition Tool

#5

Post by s3nh_ » Tue, Sep 03, 2019, 5:08 PM UTC

dpaluy wrote: post #4

How to train this model in other languages?

the hardest part in training model in foreign languages is to get correctly labeled dataset. I worked with pretrain model on Polish language documents and based on this experience it is relatively good if you are using some text similarity measures. There are some examples/pretrain models with Korean/English/French language

Re: Show HN: Pytorch Text Recognition Tool

#6

Post by boromi » Tue, Sep 03, 2019, 8:13 PM UTC

And CRAFT stands for what?

Re: Show HN: Pytorch Text Recognition Tool

#7

Post by piceas » Wed, Sep 04, 2019, 8:27 AM UTC

boromi wrote: post #6

And CRAFT stands for what?

The topic list gives the answer https://github.com/topics/craft

Fist repo: Character Region Awareness for Text Detection (CRAFT)

https://github.com/clovaai/CRAFT-pytorch

Which has a nice video demo.

https://youtu.be/HI8MzpY8KMI

Re: Show HN: Pytorch Text Recognition Tool

#8

Post by jkaufmann_ » Thu, Sep 05, 2019, 1:38 PM UTC

This is awesome, definitely a ton of use cases for this. It would be interesting if you put some background into why you made this project in your README. Some inspiration always helps.

Also some examples of where else you've seen it applied could spark peoples imagination to help people get some more usage out of your work.

Re: Show HN: Pytorch Text Recognition Tool

#9

Post by s3nh_ » Mon, Sep 09, 2019, 7:03 AM UTC

jkaufmann_ wrote: post #8

This is awesome, definitely a ton of use cases for this. It would be interesting if you put some background into why you made this project in your README. Some inspiration always helps. Also some examples of where else you've seen it applied could spark peoples imagination to help people get some more usage out of your work.

Hi, thanks for feedback! I'll add more general information. In my opinion theres a lot to do in complex document classification, I'll try to add some demo to make things more intuitive. thanks!