tesseract.js/docs/tesseract_parameters.md

Tesseract.js Parameters

In the 3rd argument of TesseractWorker.recognize(), you can pass a params object to customize the result of OCR, below are supported parameters in tesseract.js so far.

Example:

import Tesseract from 'tesseract.js';

const { TesseractWorker, OEM, PSM } = Tesseract;
const worker = new TesseractWorker();

worker
  .recognize(image, 'eng', {
    tessedit_ocr_engine_mode: OEM.LSTM_ONLY,
    tessedit_pageseg_mode: PSM.SINGLE_BLOCK,
  })
  .then(result => console.log(result.text));

name	type	default value	description
tessedit_ocr_engine_mode	enum	OEM.LSTM_ONLY	Check HERE for definition of each mode
tessedit_pageseg_mode	enum	PSM.SINGLE_BLOCK	Check HERE for definition of each mode
tessedit_char_whitelist	string	''	setting white list characters makes the result only contains these characters, useful the content in image is limited
tessjs_create_pdf	string	'0'	only 2 values, '0' or '1', when the value is '1', tesseract.js generates a pdf output
tessjs_create_hocr	string	'1'	only 2 values, '0' or '1', when the value is '1', tesseract.js includes hocr in the result
tessjs_create_tsv	string	'1'	only 2 values, '0' or '1', when the value is '1', tesseract.js includes tsv in the result
tessjs_create_box	string	'0'	only 2 values, '0' or '1', when the value is '1', tesseract.js includes box in the result
tessjs_create_unlv	string	'0'	only 2 values, '0' or '1', when the value is '1', tesseract.js includes unlv in the result
tessjs_create_osd	string	'0'	only 2 values, '0' or '1', when the value is '1', tesseract.js includes osd in the result
tessjs_pdf_name	string	'tesseract.js-ocr-result'	the name of the generated pdf file
tessjs_pdf_title	string	'Tesseract.js OCR Result'	the title of the generated pdf file
tessjs_pdf_auto_download	boolean	true	If the value is true, tesseract.js will automatic download/writeFile pdf file
tessjs_pdf_bin	boolean	false	whether to include pdf binary array in the result object (result.files.pdf)
tessjs_image_rectangle_left	number	0	The left of the sub-rectangle of the image.
tessjs_image_rectangle_top	number	0	The top of the sub-rectangle of the image.
tessjs_image_rectangle_width	number	-1	The width of the sub-rectangle of the image, -1 means auto width detection
tessjs_image_rectangle_height	number	-1	The height of the sub-rectangle of the image, -1 means auto height detection