SPONSORS:






User Tag List

Thanks Thanks:  0
Likes Likes:  0
Dislikes Dislikes:  0
Results 1 to 4 of 4
  1. #1
    Member
    Join Date
    May 2004
    Location
    Singapore
    Posts
    96
    Post Thanks / Like
    Mentioned
    0 Post(s)
    Tagged
    0 Thread(s)
    Total Downloaded
    0

    TC4 OCR on capture image

    Hi,

    Our company is reviewing the possibility of new feature on OCR to test the LCD display of hardware product. However OCR is not able to recognize the chars. Can anyone suggest how to fine tune the OCR parameters? [img]images/icons/rolleyes.gif[/img]

    Here is what we captured using TC4:

    And a sample code based on the TC4 help.
    </font><blockquote><font size="1" face="Verdana, Arial, Helvetica">code:</font><hr /><pre style="font-size:x-small; font-family: monospace;">Sub Main

    Set PicRect = Sys.Process(&quot;CtAMCap&quot.Window(&quot;#1000&quot;, &quot;CTAMCAP&quot;, 1).Window(&quot;VideoRenderer&quot;, &quot;ActiveMovie Window&quot;, 1).Picture(302, 256, 98, 36)
    Log.Picture(PicRect)
    Set OCRObj = OCR.CreateObject(PicRect)
    Call OCRObj.RecognitionRejectionAuto = True
    Log.Message(OCRObj.GetText)

    End Sub</pre><hr /></blockquote><font size="2" face="Verdana, Arial, Helvetica">

  2. #2
    Senior Member
    Join Date
    Oct 2004
    Location
    Las Vegas
    Posts
    473
    Post Thanks / Like
    Mentioned
    0 Post(s)
    Tagged
    0 Thread(s)
    Total Downloaded
    0

    Re: TC4 OCR on capture image

    Hi,

    I dont think is a OCR configuration problem. The problem is that the image you posted here looks too fuzzy. If you open it with an image editor and enlarge the size, you will see that the color of the digits' pixels is not black or dark gray: gray, purple, red and pixels of various intensities of these colors are used for the contour of every digit. When processing an image, the OCR plug-in transforms it to a binary representation where each pixel of the image can only be either black or white. If you save your image as a monochrome bitmap, you will see that it is pretty difficult even for a person to figure out what symbols were on the original image. So the only thing I can suggest you is to try to get the original image at a better quality.

    Atanas

  3. #3
    Member
    Join Date
    May 2004
    Location
    Singapore
    Posts
    96
    Post Thanks / Like
    Mentioned
    0 Post(s)
    Tagged
    0 Thread(s)
    Total Downloaded
    0

    Re: TC4 OCR on capture image

    Thanks Atanas,

    So you mean the image should be a high definition B/W or Grayscale for OCR optimal processing. Is there a reference on what dpi for a photo capture image?

    VAG

  4. #4
    Senior Member
    Join Date
    Oct 2004
    Location
    Las Vegas
    Posts
    473
    Post Thanks / Like
    Mentioned
    0 Post(s)
    Tagged
    0 Thread(s)
    Total Downloaded
    0

    Re: TC4 OCR on capture image

    There is no reference on the recommended DPI quality for a picture because the OCR plug-in was designed mainly to recognize text on images captured from the computer screen. You can use the plug-in to recognize text on graphic images, but the results will be less reliable. The main problem with your image is its sharpness. If you can improve it by making a screenshot at a higher resolution, you will get better results with the OCR plug-in. To check if the image is good enough for recognition with the plug-in, save it as a monochrome image and see if the separate symbols are not merged and if the contour of each symbol is continuous.

    Atanas

 

 

Posting Permissions

  • You may not post new threads
  • You may not post replies
  • You may not post attachments
  • You may not edit your posts
  •  
Search Engine Optimisation provided by DragonByte SEO v2.0.36 (Pro) - vBulletin Mods & Addons Copyright © 2016 DragonByte Technologies Ltd.
Resources saved on this page: MySQL 11.54%
vBulletin Optimisation provided by vB Optimise v2.6.4 (Pro) - vBulletin Mods & Addons Copyright © 2016 DragonByte Technologies Ltd.
User Alert System provided by Advanced User Tagging v3.2.8 (Pro) - vBulletin Mods & Addons Copyright © 2016 DragonByte Technologies Ltd.
vBNominate (Lite) - vBulletin Mods & Addons Copyright © 2016 DragonByte Technologies Ltd.
Feedback Buttons provided by Advanced Post Thanks / Like (Pro) - vBulletin Mods & Addons Copyright © 2016 DragonByte Technologies Ltd.
Username Changing provided by Username Change (Free) - vBulletin Mods & Addons Copyright © 2016 DragonByte Technologies Ltd.
BetaSoft Inc.
Digital Point modules: Sphinx-based search
All times are GMT -8. The time now is 02:33 AM.

Copyright BetaSoft Inc.