Hello

The API VisionAPI in Project Oxford also gives us the ability to perform optical character recognition in an image. What we usually known as OCR.

The result of the OCR process, shows us information with

  • the language of the detected language
  • the area where the text has been detected
  • the angle of the text
  • a collection of lines within each area of detected text
  • a collection of words per line

So a McDonalds sign returns the following information

01

Language: en
Orientation: Up
Text Angle: 5.89999999999997
Region

Rectangle:
Left 75, Top 74,
Height 132, Width 210

Lines
please do not
eat the
billboard
all white meat chicken

The About Windows form returns

Clipboard01

Language: en
Orientation: Up
Text Angle: 0
Region

Rectangle:
Left 9, Top 11,
Height 311, Width 402

Lines
About Windows
Windows 10
Microso ft Mndows
Version 1511 (osBui1d 10586.11)
@ 2015 Microsoft Corporaton. Al rights reserved.
The Windows 10 Enterprise operating system and its user interface are
protected by trademark and other pending or existing intellectual property
rights in the United States and other countries/regions.
This product is licensed under the Microsoft Software License
Terms to:
brunocapuano@msn.com

And a live action demo is like this one where PADDINGTON is quickly added into the image information

2015 11 24 Vision Api ocr

 

The source code is avilable in GitHub https://github.com/elbruno/ProjectOxford

Greetings @ Madrid !

El Bruno

References

4 responses to “#AZURE – #VisionAPI and optical character recognition #OCR”

Leave a reply to #ProjectOxford – New features for #FaceAPI: beard, moustache, smile detection and more !!! | El Bruno Cancel reply

Discover more from El Bruno

Subscribe now to keep reading and get access to the full archive.

Continue reading