KB00007654: Configure the Thai Language for Tesseract in Ephesoft Transact 2019.2

Issue:

Users want to configure the Thai language for Tesseract in Ephesoft Transact 2019.2.

Solution:

  1. Download the Thai Tesseract data.
  2. Right-click the file and unblock the security option.
  3. Unzip the file.
  4. Navigate to the tessdata
  5. Copy the traineddata file into the following folder: [Ephesoft installed path]:\Ephesoft\Application\native\Tesseract-OCR\tessdata

  1. Open the batch class.
  2. Navigate to the page process workflow.
  3. Remove the Recostar HOCR and replace with Tesseract HOCR.
  4. Turn on Tesseract HOCR.
  5. From the Tesseract HOCR’s OCR language option, manually add the Thai language.

  1. Click Apply and Deploy.
  2. Click the View OCR to test with the sample images. View the results in the Validation module.