Diese Seite mit anderen teilen ...

Informationen zum Thema:
Forum:
WinDev Forum
Beiträge im Thema:
12
Erster Beitrag:
vor 4 Jahren, 4 Monaten
Letzter Beitrag:
vor 2 Jahren, 6 Monaten
Beteiligte Autoren:
mariah, Fabrice Harari, Ivan V., tonytong, Susanna Moore, Cheungxin, Yogi Yang, Frans, Stewart Crisler

Image recognition app

Startbeitrag von Ivan V. am 19.02.2014 13:51

Hi everyone,

Did anyone tried to use WinDev or WinDev mobile to make app for image recognition?
And i would love to know your opinions is this possible to make with WinDev?

(i have project to make app for plants archive, so this would work as someone take photo with camera or phone, uploads it in application and application search on parameters in databe if something match and how much percent it matches)

Thanks

Ivan

Antworten:

Hi Ivan

I haven't tried, but there is no reason why it couldn't be done in wlanguage...

The problem in a case like that is to find the right algorithm to do the image recognition, and I'm pretty sure there are some available on the web (yes there are, I checked)

Then a second problem is being able to understand it enough to implement it in wlanguage :-)

Of course, an alternative is to use an external tool (dll, activeX, etc) to do the image work (there are some too), and that is possible also in wlanguage

So none of the problems is linked to windev, only to the developer...

best regards

von Fabrice Harari - am 19.02.2014 15:12
Hello Ivan,

I would search van an activex, unless you are very very very good in math I wouldn't even try it. And then I think WD is to slow. Buy one and save you hundreds of hours.

Just my two cents.

von Frans - am 19.02.2014 17:40
WinDev has a command that will copy the pixels in an image into an array. I use this capability to take scanned document images and locate and decode a code 39 bar code. It was easier than I thought but a far step from image recognition. Performance was better than I expected and well within my requirements in terms of document turn times.

Stewart Crisler

von Stewart Crisler - am 19.02.2014 19:03
If you are comfortable with using .NET components in WD then check out IEvolution for .NET. It is just superb. It supports so many features that it would be hard to list here. Combine it with IEVision Addon and you have a complete OCR, Face Recognition, Barcode Recognition, etc. features ready to use out of the box.

You will find this at: http://www.xequte.com/imageen/index.html

Technical feature list: http://www.xequte.com/imageen/ievolutionhelp/html/whatsnew.htm

HTH

Yogi Yang

von Yogi Yang - am 20.02.2014 11:53
Hi everyone,

This response i amazing, i ll start my research asap.
Yogi thanks for inputs i think i ll try that way, because i am familiar with .NET and using it in WinDev.

Regards,
Ivan

von Ivan V. - am 20.02.2014 15:33
Quote
Stewart Crisler
WinDev has a command that will copy the pixels in an image into an array. I use this capability to take scanned document images and locate and decode a code 39 bar code. It was easier than I thought but a far step from image recognition. Performance was better than I expected and well within my requirements in terms of document turn times.

Stewart Crisler

you mean when copy the pixels into an array,the image can be detected ?

von mariah - am 26.02.2014 03:56
Hi

what Stewart means is that there is a function allowing to copy an image into an array (in one line)... at this point, each element of the array is the value of one pixel...

After that, all the array manipulations are available for YOU to do what you want with the image data... If I remember correctly, he used that to analyse/read barcode directly in wlanguage instead of using an external library to do so.

Best regards

von Fabrice Harari - am 26.02.2014 12:01
"If you are comfortable with using .NET components in WD then check out IEvolution for .NET. It is just superb. It supports so many features that it would be hard to list here. Combine it with IEVision Addon and you have a complete OCR, Face Recognition, Barcode Recognition, etc. features ready to use out of the box."

Yang, I'm with you.
Automated document recognition and processing of forms, using optical character recognition (OCR) to read text in scanned documents, and optical mark recognition (OMR) to read checkboxes, or bubble sheets for automated testing and grading.

von Susanna Moore - am 28.02.2014 02:36
Quote
Stewart Crisler
WinDev has a command that will copy the pixels in an image into an array. I use this capability to take scanned document images and locate and decode a code 39 bar code. It was easier than I thought but a far step from image recognition. Performance was better than I expected and well within my requirements in terms of document turn times.

Stewart Crisler

which barcode scanner is better

von mariah - am 17.04.2014 06:24
Interested in your mentioned image app for recognition. Is it completed now?

von Cheungxin - am 13.05.2014 03:43
I find a free online ocr to convert image to text, it supports 40+ languages, and can save converted text to editable txt file and searchable pdf document.

von tonytong - am 15.12.2015 13:40
Zur Information:
MySnip.de hat keinen Einfluss auf die Inhalte der Beiträge. Bitte kontaktieren Sie den Administrator des Forums bei Problemen oder Löschforderungen über die Kontaktseite.
Falls die Kontaktaufnahme mit dem Administrator des Forums fehlschlägt, kontaktieren Sie uns bitte über die in unserem Impressum angegebenen Daten.