Text Recognition on physical documents

[Thor]

Just some ideas I have floating around, will php be up for this or is this in the realm of some other language.

I have a bunch of documents, I want to take a picture upload it to my website and perform some text manipulations on it.

For example Digitally, you can search for specific characters, words or phrases, by pressing Control F (or Command F for mac users).

I want to be able to do that on images of physical documents

 

[HavocXphere]

Just some ideas I have floating around, will php be up for this or is this in the realm of some other language.

Sure. All you need to do is write a OCR engine.

Good luck

 

[DJ...]

Google Cloud Vision API or Tesseract + Hadoop...

 

[Thor]

Sure. All you need to do is write a OCR engine.

Good luck

Turned out to be a lot easier than I thought. I should have googled first.

http://www.sitepoint.com/ocr-in-php-read-text-from-images-with-tesseract/

 

[Thor]

Google Cloud Vision API or Tesseract + Hadoop...

Not a big fan of paying money to google

 

[DJ...]

Not a big fan of paying money to google

Not sure why, their products are superb, and their OCR/image engine blows everyone else's out of the water. But their Vision API is free for the first 1000 units/month...

 

[TJ99]

Are you sure you want to add Thor187 to your ignore list?

[]Yes []No [X]GAWDYES

 

[rward]

I should have googled first.

Yup ..

 

[Thor]

View attachment 354446

Well fu too then

 

[Thor]

View attachment 354446

Also as a side note wondering what the fck I could have done to upset you?

 

[DA-LION-619]

Also as a side note wondering what the fck I could have done to upset you?

http://mybroadband.co.za/vb/showthread.php/810496-Text-Recognition-on-physical-documents
http://mybroadband.co.za/vb/showthread.php/810286-Remix-OS-within-Windows-10
http://mybroadband.co.za/vb/showthread.php/809184-Steve-Jobs-internal-demo-of-NeXT
http://mybroadband.co.za/vb/showthr...r-Web-Africa-folk-getting-constant-DNS-errors
http://mybroadband.co.za/vb/showthr...-Apple-as-FBI-has-now-unlocked-Farook’s-iPhon

That's only for April

 

[Thor]

http://mybroadband.co.za/vb/showthread.php/810496-Text-Recognition-on-physical-documents
http://mybroadband.co.za/vb/showthread.php/810286-Remix-OS-within-Windows-10
http://mybroadband.co.za/vb/showthread.php/809184-Steve-Jobs-internal-demo-of-NeXT
http://mybroadband.co.za/vb/showthr...r-Web-Africa-folk-getting-constant-DNS-errors
http://mybroadband.co.za/vb/showthr...-Apple-as-FBI-has-now-unlocked-Farook’s-iPhon

That's only for April

Your point is?

 

[DA-LION-619]

Your point is?

Most of your threads can be solved by doing the following,
http://mybroadband.co.za/vb/showthr...-documents?p=17396488&viewfull=1#post17396488

 

[Thor]

Most of your threads can be solved by doing the following,
http://mybroadband.co.za/vb/showthr...-documents?p=17396488&viewfull=1#post17396488

MyBB is my Google

#dealwithit

 

[dj_jyno]

Not a big fan of paying money to google

If you think that's expensive, don't look at Ephesoft pricing...

 

[Thor]

If you think that's expensive, don't look at Ephesoft pricing...

It's free actually, I used it just now

 

[Thor]

^community addition

 

[dj_jyno]

It's free actually, I used it just now

I know

 

[Thor]

I know

 

[[)roi(]]

Indexing scanned documents has been done over and over and over and over and .... (Yip you guessed it over and over...., ad nauseam)

Example: http://www.metrofile.com/metrofile-solutions/enterprise-solutions/image-processing/digital-services/