OCR Translate

  1. 이미지를 읽어서 번역하여 읽어주는 프로그램

  2. import pytesseract
    import cv2
    import os
    from PIL import Image
    import numpy as np
    import re
    from google_speech import Speech
    from google_trans_new import google_translator
    
    translator = google_translator()
    
    imgPath = '/home/pi/Desktop/work/doc.jpg'
    
    if __name__=="__main__":
        print("START ... ")
        print(pytesseract.get_languages(config=''))
        ocrString = pytesseract.image_to_string(Image.open(imgPath), lang='kor+eng')
        #print(">>>> " + ocrString.strip())
        regex = re.sub('[-=+,#/\?:^.@*\"※~ㆍ!』‘|\(\)\[\]`\'…》\”\“\’·]', ' ', ocrString.strip())
        print(">>>> " + regex.strip())
        translate_text = translator.translate(regex.strip(), lang_tgt='ko')
        print(">>>> " + translate_text)
        speech = Speech(translate_text, 'ko')
        speech.play()
    
  3. read image doc.jpg


Revision #1
Created 2 June 2023 12:55:31 by Hyeon Su Ryu
Updated 2 June 2023 12:56:47 by Hyeon Su Ryu