Hacker News Reader

Trun_walon Ask HN: ML – if training data are private documents

Hi. I am working on building an application using ML on confidential finance documents. Data I require in huge number are private information which I can never have legally without the permission of the owner.

Has anyone used ML on such private documents, if yes what approaches did you take to collect such data?

Trun_walon Ask HN: Customised dosages to individuals

Hi! Have you come across research on interaction between an individual's molecules and the medicines so that customizable dosages can be prescribed to the patients.

Trun_walon Annoying Car horns – Can technology ever replace vehicle horns?

Maybe be it is not a universal problem. It is a huge issue in Asian countries from what I know.

Even while travelling, if you are passing by larger than sedan vehicles, it becomes unbearable.

Trun_walon Ask HN: What are the best resources to learn computer vision?

"The general idea is to take a document a user has filled out and "fit" it to a blank template" - I agree point to point. However, I am struggling with templatization due to poor quality of the document images. To process those documents (denoise, super resolution, HE - etc. etc.), the OpenCV algorithms are not working good enough, requires a lot of tuning varying with each document.

So, I was wondering if those algorithms work better for natural images (buildings, people, things etc) than document images (text, graphics) and if so, there must exist algorithms to process such documents I am unaware of.

Trun_walon Ask HN: What are the best resources to learn computer vision?

Hey, amazing blogs. Currently working on degraded scanned documents. Are there algorithms distinguishable for documents and natural images?

I am using open cv to process the documents, curious if I am missing out chunk of cv algorithms specially for scanned administrative documents (financial,personal documents)?

Trun_walon Text Engineering: GATE by University of Sheffield

I intend to use this platform to build my own text parser (in a product). Some queries: 1. How robust it is? 2. I have written my code in C#, and to migrate it to GATE I have to write all code in GATE Developer from scratch using JAPE. Is there a way to speed up this migration? Thanks

Trun_walon NLP,DM – General Architecture for Text Engineering (University of Sheffield)

I intend to use this platform to build my own text parser (in a product). Some queries:

1. How robust it is? 2. I have written my code in C#, and to migrate it to GATE I have to write all code in GATE Developer from scratch using JAPE. Is there a way to speed up this migration?

Thanks