OCR - Paddle OCR

!python3 -m pip install paddlepaddle-gpu
!pip install "paddleocr>=2.0.1"
from paddleocr import PaddleOCR,draw_ocr
# Paddleocr supports Chinese, English, French, German, Korean and Japanese.
# You can set the parameter `lang` as `ch`, `en`, `fr`, `german`, `korean`, `japan`
# to switch the language model in order.
ocr = PaddleOCR(use_angle_cls=True, lang='korean') #
from google.colab.patches import cv2_imshow
import cv2
result = ocr.ocr(img_path, cls=True)
from PIL import Image, ImageDraw, ImageFont
image = Image.open(img_path).convert('RGB')


boxes = []
txts = []
scores = []
for [box , text] in result[0]:
    print('box:', box, 'txt:', text[0], 'score:', text[1])
    boxes.append(box)
    txts.append(text[0])
    scores.append(text[1])
    
print(txts)
font = ImageFont.load_default()
im_show = draw_ocr(image, boxes, txts, scores,font_path='/usr/share/fonts/truetype/humor-sans/Humor-Sans.ttf' )
im_show = Image.fromarray(im_show)
im_show.save('result.jpg')

paddleOCR 버전이 좀 낮은가?
50% 추출이었다...
나중에 버전 업해서 다시 try해보자
지금은 일단 다른 모델 테스트 해보고 싶음