How to segregate resume layouts into different types?


I'm looking for any suggestions on how to segregate resume layout into different types.

How do one proceed with such a task? I mean resumes are usually available as pdf or docx format and when we parse text from documents we lose a lof of information regarding layout or metadata.

So how one could build a system to segregate resumes based on layouts.

It'll be really helpful if you have any suggestions.

Sai Kumar

Posted 2020-05-07T12:20:23.207

Reputation: 591

Can you maybe add an example of what you mean by "segregating"? Two pictures of resumes that should be grouped together perhaps? I am guessing you mean clustering resumes based on their visual layout? – Valentin Calomme – 2020-05-07T13:35:58.133

@ValentinCalomme Yes. Clustering resumes based on their visual layout. I have multiple pdf or docx resume files and I want to group together them. How should I approach such problem. Should I just convert the pdfs to image and use a CNN (or) is there any approach that works better in these circumstances. – Sai Kumar – 2020-05-07T19:31:52.330

No answers