which defines an abstract OCR engine for recognition of single language text on the entire image or within the image region. The SDK architecture is open and allows to connect to any OCR engine.

From version 11.0.2.1 the SDK includes Tesseract OCR engine v5.0. TesseractOcr class is derived from OcrEngine class and allows to recognize text of single language on the entire image or within the image region.

The process of text recognition consists from the following steps:

1. Preparation of image for text recognition
2. Preparation of OCR engine for text recognition
3. Text recognition in the image
4. Obtaining and editing OCR results
5. Saving OCR result
   1. Saving OCR result to a text file
   2. Saving OCR result to a searchable PDF document
   3. Exporting OCR result to hOCR file