HackOCR/run_ocr.py at master · indenigrate/HackOCR · GitHub

1
2
3
4
5
6
7
8
9
10
11
12
13
14
15
16
17
18
19
20
21
22
23
24
25
26
27
28
29
30
31
32
33
34
35
36
37
38
from paddleocr import PaddleOCR


ocr = PaddleOCR(
    use_doc_orientation_classify=False,
    use_doc_unwarping=False,
    use_textline_orientation=False) # text detection + text recognition
# ocr = PaddleOCR(use_doc_orientation_classify=True, use_doc_unwarping=True) # text image preprocessing + text detection + textline orientation classification + text recognition
# ocr = PaddleOCR(use_doc_orientation_classify=False, use_doc_unwarping=False) # text detection + textline orientation classification + text recognition
# ocr = PaddleOCR(
    # text_detection_model_name="PP-OCRv5_mobile_det",
    # text_recognition_model_name="PP-OCRv5_mobile_rec",
    # use_doc_orientation_classify=False,
    # use_doc_unwarping=False,
    # use_textline_orientation=False) # Switch to PP-OCRv5_mobile models
result = ocr.predict("./test3.jpeg")
for res in result:
    res.print()
    res.save_to_img("output")
    res.save_to_json("output")


from paddleocr import TextDetection
from paddleocr import TextRecognition
model = TextDetection()
output = model.predict("test2.png")
for res in output:
    res.print()
    res.save_to_img(save_path="./outputDetection/")
    res.save_to_json(save_path="./outputDetection/res.json")


model = TextRecognition()
output = model.predict(input="test2.png")
for res in output:
    res.print()
    res.save_to_img(save_path="./outputRecognition/")
    res.save_to_json(save_path="./outputRecognition/res.json")