6

I am trying to detect text from image after image processing by using paddlepaddle ocr. but paddle ocr is unable to detect the text.

from paddleocr import PaddleOCR,draw_ocr

ocr = PaddleOCR(use_angle_cls=True, lang='en')
img_path = '123.jpg'
result = ocr.ocr(img_path, cls=True)
r=[]
for line in result:
    r.append(line[1][0])

print(r)

[![Image link is here][1]][1]

SHIVAM CHAUHAN
  • 61
  • 1
  • 3
  • @nathancy, thanks for your response, but i have already used pytesseract. Pytesseract also unable to detect text from image which i have send – SHIVAM CHAUHAN Apr 07 '22 at 06:51

1 Answers1

1

try set --det_db_score_mode='slow'

paddleocr --image_dir=./5NwdW.jpeg --det_db_score_mode=slow

I got the results below. [2022/08/17 06:28:19] ppocr INFO: [[[38.0, 11.0], [1139.0, 19.0], [1139.0, 87.0], [38.0, 79.0]], ('P<INDSINGH<<SHRUTI<<<<<<<<<<<<<<人人人人人人人<<<<', 0.8117786645889282)] [2022/08/17 06:28:19] ppocr INFO: [[[43.0, 66.0], [1142.0, 85.0], [1141.0, 161.0], [42.0, 143.0]], ('Z4301759<2ind8507309F2706133<<<<<<<<<<<<<<2', 0.9215003848075867)]

It can be easily found that the < character is wrongly recognized, but the numbers and letters are recognized correctly.

刘威威
  • 21
  • 2