85 lines
3.2 KiB
Python
85 lines
3.2 KiB
Python
|
from paddleocr import PaddleOCR
|
||
|
|
import time
|
||
|
|
import cv2
|
||
|
|
import numpy as np
|
||
|
|
import os
|
||
|
|
import logging
|
||
|
|
logging.basicConfig(level=logging.INFO)
|
||
|
|
|
||
|
|
# 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(
|
||
|
|
det_model_dir="/mnt/models/ocr/ch_PP-OCRv4_det_server_infer", # https://paddleocr.bj.bcebos.com/PP-OCRv3/chinese/ch_PP-OCRv3_det_infer.tar
|
||
|
|
rec_model_dir="/mnt/models/ocr/ch_PP-OCRv4_rec_server_infer", # https://paddleocr.bj.bcebos.com/PP-OCRv3/chinese/ch_PP-OCRv3_rec_infer.tar
|
||
|
|
cls_model_dir="/mnt/models/ocr/ch_ppocr_mobile_v2.0_cls_infer", # https://paddleocr.bj.bcebos.com/dygraph_v2.0/ch/ch_ppocr_mobile_v2.0_cls_infer.tar
|
||
|
|
use_doc_orientation_classify=False,
|
||
|
|
use_doc_unwarping=False,
|
||
|
|
use_gpu=True,
|
||
|
|
cpu_threads=32,
|
||
|
|
enable_mkldnn=True,
|
||
|
|
use_textline_orientation=False) # Switch to PP-OCRv5_mobile models
|
||
|
|
|
||
|
|
time.sleep(5)
|
||
|
|
total_time = 0
|
||
|
|
WITH_PREPROCESSING = True
|
||
|
|
NOISE_THRESHOLD = int(os.getenv("NOISE_THRESHOLD", "10"))
|
||
|
|
for i in range(1):
|
||
|
|
# img_path = f"test{i%5}.pdf"
|
||
|
|
img_path = f"1.jpg"
|
||
|
|
print(f"run for {img_path}")
|
||
|
|
image = cv2.imread(img_path)
|
||
|
|
start = time.time()
|
||
|
|
|
||
|
|
# height, width = image.shape[:2]
|
||
|
|
# image = cv2.resize(image, (width // 2, height // 2))
|
||
|
|
|
||
|
|
if WITH_PREPROCESSING:
|
||
|
|
# 计算图像的灰度直方图
|
||
|
|
if len(image.shape) == 3: # 如果是彩色图像 (具有三个通道)
|
||
|
|
gray = cv2.cvtColor(image, cv2.COLOR_BGR2GRAY)
|
||
|
|
else:
|
||
|
|
gray = image
|
||
|
|
|
||
|
|
logging.info(f"cvtColor takes {time.time() - start} s")
|
||
|
|
|
||
|
|
# 噪声水平估计（简单地使用标准差作为代理）
|
||
|
|
noise_level = np.std(gray) # 在灰度图像上评估噪声水平
|
||
|
|
logging.info(f"noise_level: {noise_level}")
|
||
|
|
if noise_level > NOISE_THRESHOLD:
|
||
|
|
logging.info("denoising")
|
||
|
|
if len(image.shape) == 3: # 如果是彩色图像
|
||
|
|
logging.info("denoisin for color")
|
||
|
|
processed_img = cv2.fastNlMeansDenoisingColored(image)
|
||
|
|
else: # 如果是灰度图像
|
||
|
|
logging.info("denoising for gray")
|
||
|
|
processed_img = cv2.fastNlMeansDenoising(image)
|
||
|
|
else:
|
||
|
|
processed_img = image
|
||
|
|
|
||
|
|
logging.info(f"Preprocessing takes {time.time() - start} s")
|
||
|
|
else:
|
||
|
|
processed_img = image
|
||
|
|
logging.info("Skip Preprocessing")
|
||
|
|
|
||
|
|
result = ocr.ocr(image)
|
||
|
|
end = time.time()
|
||
|
|
print(f"{img_path} elapsed: {end - start}")
|
||
|
|
total_time += (end - start)
|
||
|
|
|
||
|
|
print(f"total time: {total_time}")
|
||
|
|
for idx in range(len(result)):
|
||
|
|
res = result[idx]
|
||
|
|
print(f"res: {res}")
|
||
|
|
# for line in res:
|
||
|
|
# print(line)
|
||
|
|
|
||
|
|
# result = ocr.predict("docs/images/00006737.jpg")
|
||
|
|
# for res in result:
|
||
|
|
# res.print()
|
||
|
|
# res.save_to_img("output")
|
||
|
|
# res.save_to_json("output")
|