Extract Thai and English Text from Document Image or PDF.

  • Supported PNG, JPG, JPEG, and PDF input image file. No more than 30MB.

  • System will recognize the document components automatically as follows:

    • Page boundary

    • Title

    • Paragraph

    • Image

    • Table

    • Thai characters

    • English characters

    • Special characters

  • System will generate the output into three format.

    • the Editable Text (.txt) (Endpoint = /ocr)

    • the Structured JSON (.json) (Endpoint = /layout)

    • the Microsoft Word file! (.docx) (Endpoint = /docx)

Last updated