ImageEn, unit ievision

TIEVisionOCR


Declaration

TIEVisionOCR = interface(TIEVisionBase)


Description

This interface allows you to perform basic OCR (Optical Character Recognition) in English and 100+ other languages.
It is possible to recognize a specific image area or the whole image.
For recognition it means:
- Get the ANSI or Unicode text from a raster image
- Estimate the document orientation (text angle)
- Get each recognized character position (bounding box)
- Get text regions (to reproduce text layout)



To change the language of OCR, specify the path of the language file when calling IEVisionLib.createOCR. You can download language files from:
www.imageen.com/download/

Note: Only one single instance of this object can exist in your application.


Demos

  Demos\IEVision\OCR\OCR.dpr
  Demos\IEVision\OCRwithLayout\OCRwithLayout.dpr


Methods and Properties

  clearAdaptiveInfo
  getBoxes
  getOrientation
  getRegions
  getTextAngle
  getWordBoxes
  isWordValid
  recognize
  setSegmentationMode
      

See Also

  createOCR
  TIEVisionLanguages
  TIEVisionOCRWordBox
  IEVisionLanguageCodeToName
  IEVisionLanguageNameToCode
  IEVisionGetLanguagesInFolder


Example

// perform OCR
str := IEVisionLib.createOCR(IEOCRLanguageList[OCR_English_language].Code).recognize(ImageEnView1.IEBitmap.GetIEVisionImage(), IEVisionRect(0, 0, 0, 0)).c_str();