Jump to content

Need Scripting Help for Project (OCR)


JSBach
 Share

Recommended Posts

I've been using AutoIt for a few weeks now and have made a few projects, and I love the program so far.  My friends and I want to make a project to display simple artificial intelligence by making a script to allow the computer to match text from an image to select the right answer, but none of use currently have enough scripting/programming knowledge.  I know that this may sound fishy, and a friend of mine even warned that it sounded like I wanted a captcha solver, but I assure you that this is meant to be a fun project.

Here's an example of the type of problem I want the program to solve:

Instructions: Match the given sentence in the image with the identical statement.

Image: John's dog is large.

  • John's dog is long.
  • Josh's dog is large.
  • John's dog is large.
  • My sister was here.

                           Submit Answer Button

My idea on how to approach this is:

  1. Make an OCR to convert both the image and the text to text of the same font and font size.
  2. Create a script that will match the words of the sentence to one of the answers.
  3. Set conditions so that the computer will click on the correct answer. (Maybe some like "If ___  true, then Mouseclick coordinates)

However it should be noted that the images are of varying sizes so the mouse-click coordinates should be programmed to click in relation to something that doesn't move (ex: the "Submit" button)

I hope that you can help me with this.  Thanks in advance  :D  :ILA3:

Edited by JSBach
Link to comment
Share on other sites

  • Moderators

There is so MUCH work that has to go into an intelligent OCR.  More so than I'm sure any one/many person(s) on this forum would be willing to partake in without payment or first child contract.

Having said that, there have been many many many threads/example scripts/etc on this subject in the short (almost) 10 years I've been a part of this forum, one that pops to mind is tesseract (sp?), I believe even microsoft had a built in one at one time.

Food for thought:

The only thing I see the request most for anymore is what you've tried to emphasize it isn't for (captcha).  Assurances mean little when you present the possible doubt without probable and undeniable and detailed example/proof per say that you aren't.  Especially from someone that says they have been using the program for weeks and has only 2 posts.

On a personal note:

If all of you are novice programmers, it really makes me wonder what use novices would have for an ocr other than 1 of 2 options.

Wish you well, good luck.

Common sense plays a role in the basics of understanding AutoIt... If you're lacking in that, do us all a favor, and step away from the computer.

Link to comment
Share on other sites

Don't see why OCR, PixelChecksum would suffice.

 

Problem with pixelchecksum, you have to build one sum for each letter and pray the font and screen size stays exactly the same as when you built the checksums.

Lofting the cyberwinds on teknoleather wings, I am...The Blue Drache

Link to comment
Share on other sites

Create an account or sign in to comment

You need to be a member in order to leave a comment

Create an account

Sign up for a new account in our community. It's easy!

Register a new account

Sign in

Already have an account? Sign in here.

Sign In Now
 Share

  • Recently Browsing   0 members

    • No registered users viewing this page.
×
×
  • Create New...