paddle ocr v4 2.6.1实战笔记

目录

效果图:

安装

模型权重是自动下载,如果提前下载会报错。

识别orc,并opencv可视化结果,支持中文可视化

官方原版预测可视化:


效果图:

安装

安装2.5.2识别结果为空

pip install paddlepaddle-gpu==2.6.1

模型权重是自动下载,如果提前下载会报错。

测试代码:


import os
import time
from paddleocr import PaddleOCRfilepath = r"weights/123.jpg"ocr_model = PaddleOCR(use_angle_cls=True, lang="ch", use_gpu=True, show_log=1,det_db_box_thresh=0.1, use_dilation=True,det_model_dir='weight/ch_PP-OCRv4_det_server_infer.tar',cls_model_dir='weight/ch_ppocr_mobile_v2.0_cls_infer.tar',rec_model_dir='weight/ch_PP-OCRv4_rec_server_infer.tar')t1 = time.time()
for i in range(1):result = ocr_model.ocr(img=filepath, det=True, rec=True, cls=True)[0]
t2 = time.time()
print((t2-t1) / 10)for res_str in result:print(res_str)

识别orc,并opencv可视化结果,支持中文可视化

import codecs
import os
import timeimport cv2
import numpy as np
from PIL import ImageFont
from PIL import Image
from PIL import ImageDrawfrom paddleocr import PaddleOCRfilepath = r"weights/124.jpg"ocr_model = PaddleOCR(use_angle_cls=True, lang="ch", use_gpu=True, show_log=1,det_db_box_thresh=0.1, use_dilation=True,det_model_dir='weight/ch_PP-OCRv4_det_server_infer.tar',cls_model_dir='weight/ch_ppocr_mobile_v2.0_cls_infer.tar',rec_model_dir='weight/ch_PP-OCRv4_rec_server_infer.tar')t1 = time.time()
for i in range(1):result = ocr_model.ocr(img=filepath, det=True, rec=True, cls=True)[0]
t2 = time.time()
print((t2-t1) / 10)font_path = 'simhei.ttf'  # 需要替换为你的中文字体路径
font = ImageFont.truetype(font_path, 24)
def cv2AddChineseText(img, text, position, textColor=(0, 255, 0), textSize=30):img = Image.fromarray(cv2.cvtColor(img, cv2.COLOR_BGR2RGB))draw = ImageDraw.Draw(img)draw.text(position, text, textColor, font=font)return cv2.cvtColor(np.asarray(img), cv2.COLOR_RGB2BGR)image=cv2.imread(filepath)ocr_index=0
for res_str in result:if res_str[0][0][0]>36 and res_str[0][2][0]<84:print(ocr_index,res_str)points=res_str[0]text = res_str[1][0]points = np.array(points, dtype=np.int32).reshape((-1, 1, 2))cv2.polylines(image, [points], isClosed=True, color=(255, 0, 0), thickness=2)text_position = (int(points[0][0][0]), int(points[0][0][1] + 20))  # 微调文本位置# cv2.putText(image, '中文文本', (50, 100), cv2.FONT_HERSHEY_SIMPLEX, 2, (255, 255, 255), 3)image= cv2AddChineseText(image, text, text_position, textColor=(0, 255, 0), textSize=30)print(ocr_index)if res_str[0][0][0]>346 and res_str[0][2][0]<391:print(ocr_index,res_str)points=res_str[0]text = res_str[1][0]points = np.array(points, dtype=np.int32).reshape((-1, 1, 2))cv2.polylines(image, [points], isClosed=True, color=(255, 0, 0), thickness=2)text_position = (int(points[0][0][0]), int(points[0][0][1] + 20))  # 微调文本位置# cv2.putText(image, '中文文本', (50, 100), cv2.FONT_HERSHEY_SIMPLEX, 2, (255, 255, 255), 3)image= cv2AddChineseText(image, text, text_position, textColor=(0, 255, 0), textSize=30)if res_str[0][0][0]>658 and res_str[0][2][0]<705:print(ocr_index,res_str)points=res_str[0]text=res_str[1][0]points=np.array(points,dtype=np.int32).reshape((-1, 1, 2))cv2.polylines(image, [points], isClosed=True, color=(255, 0, 0), thickness=2)text_position = (int(points[0][0][0]), int(points[0][0][1] + 20))  # 微调文本位置image= cv2AddChineseText(image, text, text_position, textColor=(0, 255, 0), textSize=30)cv2.imshow('Image with Rectangle and Text', image)
cv2.waitKey(0)

官方原版预测可视化:

# Copyright (c) 2020 PaddlePaddle Authors. All Rights Reserved.
#
# Licensed under the Apache License, Version 2.0 (the "License");
# you may not use this file except in compliance with the License.
# You may obtain a copy of the License at
#
#     http://www.apache.org/licenses/LICENSE-2.0
#
# Unless required by applicable law or agreed to in writing, software
# distributed under the License is distributed on an "AS IS" BASIS,
# WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.
# See the License for the specific language governing permissions and
# limitations under the License.import os
import sys
import importlib__dir__ = os.path.dirname(__file__)import paddle
from paddle.utils import try_importsys.path.append(os.path.join(__dir__, ""))import cv2
import logging
import numpy as np
from pathlib import Path
import base64
from io import BytesIO
from PIL import Image, ImageFont, ImageDraw
from tools.infer import predict_systemdef _import_file(module_name, file_path, make_importable=False):spec = importlib.util.spec_from_file_location(module_name, file_path)module = importlib.util.module_from_spec(spec)spec.loader.exec_module(module)if make_importable:sys.modules[module_name] = modulereturn moduletools = _import_file("tools", os.path.join(__dir__, "tools/__init__.py"), make_importable=True)
ppocr = importlib.import_module("ppocr", "paddleocr")
ppstructure = importlib.import_module("ppstructure", "paddleocr")
from ppocr.utils.logging import get_loggerlogger = get_logger()
from ppocr.utils.utility import (check_and_read, get_image_file_list, alpha_to_color, binarize_img, )
from ppocr.utils.network import (maybe_download, download_with_progressbar, is_link, confirm_model_dir_url, )
from tools.infer.utility import draw_ocr, str2bool, check_gpu
from ppstructure.utility import init_args, draw_structure_result
from ppstructure.predict_system import StructureSystem, save_structure_res, to_excellogger = get_logger()
__all__ = ["PaddleOCR", "PPStructure", "draw_ocr", "draw_structure_result", "save_structure_res", "download_with_progressbar", "to_excel", ]SUPPORT_DET_MODEL = ["DB"]
VERSION = "2.8.0"
SUPPORT_REC_MODEL = ["CRNN", "SVTR_LCNet"]
BASE_DIR = os.path.expanduser("~/.paddleocr/")DEFAULT_OCR_MODEL_VERSION = "PP-OCRv4"
SUPPORT_OCR_MODEL_VERSION = ["PP-OCR", "PP-OCRv2", "PP-OCRv3", "PP-OCRv4"]
DEFAULT_STRUCTURE_MODEL_VERSION = "PP-StructureV2"
SUPPORT_STRUCTURE_MODEL_VERSION = ["PP-Structure", "PP-StructureV2"]
MODEL_URLS = {"OCR": {"PP-OCRv4": {"det": {"ch": {"url": "https://paddleocr.bj.bcebos.com/PP-OCRv4/chinese/ch_PP-OCRv4_det_infer.tar", }, "en": {"url": "https://paddleocr.bj.bcebos.com/PP-OCRv3/english/en_PP-OCRv3_det_infer.tar", },"ml": {"url": "https://paddleocr.bj.bcebos.com/PP-OCRv3/multilingual/Multilingual_PP-OCRv3_det_infer.tar"}, },"rec": {"ch": {"url": "https://paddleocr.bj.bcebos.com/PP-OCRv4/chinese/ch_PP-OCRv4_rec_infer.tar", "dict_path": "./ppocr/utils/ppocr_keys_v1.txt", }, "en": {"url": "https://paddleocr.bj.bcebos.com/PP-OCRv4/english/en_PP-OCRv4_rec_infer.tar", "dict_path": "./ppocr/utils/en_dict.txt", },"korean": {"url": "https://paddleocr.bj.bcebos.com/PP-OCRv4/multilingual/korean_PP-OCRv4_rec_infer.tar", "dict_path": "./ppocr/utils/dict/korean_dict.txt", },"japan": {"url": "https://paddleocr.bj.bcebos.com/PP-OCRv4/multilingual/japan_PP-OCRv4_rec_infer.tar", "dict_path": "./ppocr/utils/dict/japan_dict.txt", },"chinese_cht": {"url": "https://paddleocr.bj.bcebos.com/PP-OCRv3/multilingual/chinese_cht_PP-OCRv3_rec_infer.tar", "dict_path": "./ppocr/utils/dict/chinese_cht_dict.txt", },"ta": {"url": "https://paddleocr.bj.bcebos.com/PP-OCRv4/multilingual/ta_PP-OCRv4_rec_infer.tar", "dict_path": "./ppocr/utils/dict/ta_dict.txt", },"te": {"url": "https://paddleocr.bj.bcebos.com/PP-OCRv4/multilingual/te_PP-OCRv4_rec_infer.tar", "dict_path": "./ppocr/utils/dict/te_dict.txt", },"ka": {"url": "https://paddleocr.bj.bcebos.com/PP-OCRv4/multilingual/ka_PP-OCRv4_rec_infer.tar", "dict_path": "./ppocr/utils/dict/ka_dict.txt", },"latin": {"url": "https://paddleocr.bj.bcebos.com/PP-OCRv3/multilingual/latin_PP-OCRv3_rec_infer.tar", "dict_path": "./ppocr/utils/dict/latin_dict.txt", },"arabic": {"url": "https://paddleocr.bj.bcebos.com/PP-OCRv4/multilingual/arabic_PP-OCRv4_rec_infer.tar", "dict_path": "./ppocr/utils/dict/arabic_dict.txt", },"cyrillic": {"url": "https://paddleocr.bj.bcebos.com/PP-OCRv3/multilingual/cyrillic_PP-OCRv3_rec_infer.tar", "dict_path": "./ppocr/utils/dict/cyrillic_dict.txt", },"devanagari": {"url": "https://paddleocr.bj.bcebos.com/PP-OCRv4/multilingual/devanagari_PP-OCRv4_rec_infer.tar", "dict_path": "./ppocr/utils/dict/devanagari_dict.txt", }, }, "cls": {"ch": {"url": "https://paddleocr.bj.bcebos.com/dygraph_v2.0/ch/ch_ppocr_mobile_v2.0_cls_infer.tar", }}, },"PP-OCRv3": {"det": {"ch": {"url": "https://paddleocr.bj.bcebos.com/PP-OCRv3/chinese/ch_PP-OCRv3_det_infer.tar", }, "en": {"url": "https://paddleocr.bj.bcebos.com/PP-OCRv3/english/en_PP-OCRv3_det_infer.tar", },"ml": {"url": "https://paddleocr.bj.bcebos.com/PP-OCRv3/multilingual/Multilingual_PP-OCRv3_det_infer.tar"}, },"rec": {"ch": {"url": "https://paddleocr.bj.bcebos.com/PP-OCRv3/chinese/ch_PP-OCRv3_rec_infer.tar", "dict_path": "./ppocr/utils/ppocr_keys_v1.txt", }, "en": {"url": "https://paddleocr.bj.bcebos.com/PP-OCRv3/english/en_PP-OCRv3_rec_infer.tar", "dict_path": "./ppocr/utils/en_dict.txt", },"korean": {"url": "https://paddleocr.bj.bcebos.com/PP-OCRv3/multilingual/korean_PP-OCRv3_rec_infer.tar", "dict_path": "./ppocr/utils/dict/korean_dict.txt", },"japan": {"url": "https://paddleocr.bj.bcebos.com/PP-OCRv3/multilingual/japan_PP-OCRv3_rec_infer.tar", "dict_path": "./ppocr/utils/dict/japan_dict.txt", },"chinese_cht": {"url": "https://paddleocr.bj.bcebos.com/PP-OCRv3/multilingual/chinese_cht_PP-OCRv3_rec_infer.tar", "dict_path": "./ppocr/utils/dict/chinese_cht_dict.txt", },"ta": {"url": "https://paddleocr.bj.bcebos.com/PP-OCRv3/multilingual/ta_PP-OCRv3_rec_infer.tar", "dict_path": "./ppocr/utils/dict/ta_dict.txt", },"te": {"url": "https://paddleocr.bj.bcebos.com/PP-OCRv3/multilingual/te_PP-OCRv3_rec_infer.tar", "dict_path": "./ppocr/utils/dict/te_dict.txt", },"ka": {"url": "https://paddleocr.bj.bcebos.com/PP-OCRv3/multilingual/ka_PP-OCRv3_rec_infer.tar", "dict_path": "./ppocr/utils/dict/ka_dict.txt", },"latin": {"url": "https://paddleocr.bj.bcebos.com/PP-OCRv3/multilingual/latin_PP-OCRv3_rec_infer.tar", "dict_path": "./ppocr/utils/dict/latin_dict.txt", },"arabic": {"url": "https://paddleocr.bj.bcebos.com/PP-OCRv3/multilingual/arabic_PP-OCRv3_rec_infer.tar", "dict_path": "./ppocr/utils/dict/arabic_dict.txt", },"cyrillic": {"url": "https://paddleocr.bj.bcebos.com/PP-OCRv3/multilingual/cyrillic_PP-OCRv3_rec_infer.tar", "dict_path": "./ppocr/utils/dict/cyrillic_dict.txt", },"devanagari": {"url": "https://paddleocr.bj.bcebos.com/PP-OCRv3/multilingual/devanagari_PP-OCRv3_rec_infer.tar", "dict_path": "./ppocr/utils/dict/devanagari_dict.txt", }, }, "cls": {"ch": {"url": "https://paddleocr.bj.bcebos.com/dygraph_v2.0/ch/ch_ppocr_mobile_v2.0_cls_infer.tar", }}, },"PP-OCRv2": {"det": {"ch": {"url": "https://paddleocr.bj.bcebos.com/PP-OCRv2/chinese/ch_PP-OCRv2_det_infer.tar", }, }, "rec": {"ch": {"url": "https://paddleocr.bj.bcebos.com/PP-OCRv2/chinese/ch_PP-OCRv2_rec_infer.tar", "dict_path": "./ppocr/utils/ppocr_keys_v1.txt", }},"cls": {"ch": {"url": "https://paddleocr.bj.bcebos.com/dygraph_v2.0/ch/ch_ppocr_mobile_v2.0_cls_infer.tar", }}, }, "PP-OCR": {"det": {"ch": {"url": "https://paddleocr.bj.bcebos.com/dygraph_v2.0/ch/ch_ppocr_mobile_v2.0_det_infer.tar", }, "en": {"url": "https://paddleocr.bj.bcebos.com/dygraph_v2.0/multilingual/en_ppocr_mobile_v2.0_det_infer.tar", },"structure": {"url": "https://paddleocr.bj.bcebos.com/dygraph_v2.0/table/en_ppocr_mobile_v2.0_table_det_infer.tar"}, }, "rec": {"ch": {"url": "https://paddleocr.bj.bcebos.com/dygraph_v2.0/ch/ch_ppocr_mobile_v2.0_rec_infer.tar", "dict_path": "./ppocr/utils/ppocr_keys_v1.txt", },"en": {"url": "https://paddleocr.bj.bcebos.com/dygraph_v2.0/multilingual/en_number_mobile_v2.0_rec_infer.tar", "dict_path": "./ppocr/utils/en_dict.txt", },"french": {"url": "https://paddleocr.bj.bcebos.com/dygraph_v2.0/multilingual/french_mobile_v2.0_rec_infer.tar", "dict_path": "./ppocr/utils/dict/french_dict.txt", },"german": {"url": "https://paddleocr.bj.bcebos.com/dygraph_v2.0/multilingual/german_mobile_v2.0_rec_infer.tar", "dict_path": "./ppocr/utils/dict/german_dict.txt", },"korean": {"url": "https://paddleocr.bj.bcebos.com/dygraph_v2.0/multilingual/korean_mobile_v2.0_rec_infer.tar", "dict_path": "./ppocr/utils/dict/korean_dict.txt", },"japan": {"url": "https://paddleocr.bj.bcebos.com/dygraph_v2.0/multilingual/japan_mobile_v2.0_rec_infer.tar", "dict_path": "./ppocr/utils/dict/japan_dict.txt", },"chinese_cht": {"url": "https://paddleocr.bj.bcebos.com/dygraph_v2.0/multilingual/chinese_cht_mobile_v2.0_rec_infer.tar", "dict_path": "./ppocr/utils/dict/chinese_cht_dict.txt", },"ta": {"url": "https://paddleocr.bj.bcebos.com/dygraph_v2.0/multilingual/ta_mobile_v2.0_rec_infer.tar", "dict_path": "./ppocr/utils/dict/ta_dict.txt", },"te": {"url": "https://paddleocr.bj.bcebos.com/dygraph_v2.0/multilingual/te_mobile_v2.0_rec_infer.tar", "dict_path": "./ppocr/utils/dict/te_dict.txt", },"ka": {"url": "https://paddleocr.bj.bcebos.com/dygraph_v2.0/multilingual/ka_mobile_v2.0_rec_infer.tar", "dict_path": "./ppocr/utils/dict/ka_dict.txt", },"latin": {"url": "https://paddleocr.bj.bcebos.com/dygraph_v2.0/multilingual/latin_ppocr_mobile_v2.0_rec_infer.tar", "dict_path": "./ppocr/utils/dict/latin_dict.txt", },"arabic": {"url": "https://paddleocr.bj.bcebos.com/dygraph_v2.0/multilingual/arabic_ppocr_mobile_v2.0_rec_infer.tar", "dict_path": "./ppocr/utils/dict/arabic_dict.txt", },"cyrillic": {"url": "https://paddleocr.bj.bcebos.com/dygraph_v2.0/multilingual/cyrillic_ppocr_mobile_v2.0_rec_infer.tar", "dict_path": "./ppocr/utils/dict/cyrillic_dict.txt", },"devanagari": {"url": "https://paddleocr.bj.bcebos.com/dygraph_v2.0/multilingual/devanagari_ppocr_mobile_v2.0_rec_infer.tar", "dict_path": "./ppocr/utils/dict/devanagari_dict.txt", },"structure": {"url": "https://paddleocr.bj.bcebos.com/dygraph_v2.0/table/en_ppocr_mobile_v2.0_table_rec_infer.tar", "dict_path": "ppocr/utils/dict/table_dict.txt", }, }, "cls": {"ch": {"url": "https://paddleocr.bj.bcebos.com/dygraph_v2.0/ch/ch_ppocr_mobile_v2.0_cls_infer.tar", }}, }, },"STRUCTURE": {"PP-Structure": {"table": {"en": {"url": "https://paddleocr.bj.bcebos.com/dygraph_v2.0/table/en_ppocr_mobile_v2.0_table_structure_infer.tar", "dict_path": "ppocr/utils/dict/table_structure_dict.txt", }}}, "PP-StructureV2": {"table": {"en": {"url": "https://paddleocr.bj.bcebos.com/ppstructure/models/slanet/en_ppstructure_mobile_v2.0_SLANet_infer.tar", "dict_path": "ppocr/utils/dict/table_structure_dict.txt", },"ch": {"url": "https://paddleocr.bj.bcebos.com/ppstructure/models/slanet/ch_ppstructure_mobile_v2.0_SLANet_infer.tar", "dict_path": "ppocr/utils/dict/table_structure_dict_ch.txt", }, },"layout": {"en": {"url": "https://paddleocr.bj.bcebos.com/ppstructure/models/layout/picodet_lcnet_x1_0_fgd_layout_infer.tar", "dict_path": "ppocr/utils/dict/layout_dict/layout_publaynet_dict.txt", },"ch": {"url": "https://paddleocr.bj.bcebos.com/ppstructure/models/layout/picodet_lcnet_x1_0_fgd_layout_cdla_infer.tar", "dict_path": "ppocr/utils/dict/layout_dict/layout_cdla_dict.txt", }, }, }, }, }def parse_args(mMain=True):import argparseparser = init_args()parser.add_help = mMainparser.add_argument("--lang", type=str, default="ch")parser.add_argument("--det", type=str2bool, default=True)parser.add_argument("--rec", type=str2bool, default=True)parser.add_argument("--type", type=str, default="ocr")parser.add_argument("--savefile", type=str2bool, default=False)parser.add_argument("--ocr_version", type=str, choices=SUPPORT_OCR_MODEL_VERSION, default="PP-OCRv4", help="OCR Model version, the current model support list is as follows: ""1. PP-OCRv4/v3 Support Chinese and English detection and recognition model, and direction classifier model""2. PP-OCRv2 Support Chinese detection and recognition model. ""3. PP-OCR support Chinese detection, recognition and direction classifier and multilingual recognition model.", )parser.add_argument("--structure_version", type=str, choices=SUPPORT_STRUCTURE_MODEL_VERSION, default="PP-StructureV2", help="Model version, the current model support list is as follows:"" 1. PP-Structure Support en table structure model."" 2. PP-StructureV2 Support ch and en table structure model.", )for action in parser._actions:if action.dest in ["rec_char_dict_path", "table_char_dict_path", "layout_dict_path", ]:action.default = Noneif mMain:return parser.parse_args()else:inference_args_dict = {}for action in parser._actions:inference_args_dict[action.dest] = action.defaultreturn argparse.Namespace(**inference_args_dict)def parse_lang(lang):latin_lang = ["af", "az", "bs", "cs", "cy", "da", "de", "es", "et", "fr", "ga", "hr", "hu", "id", "is", "it", "ku", "la", "lt", "lv", "mi", "ms", "mt", "nl", "no", "oc", "pi", "pl", "pt", "ro", "rs_latin", "sk", "sl", "sq", "sv", "sw", "tl", "tr", "uz", "vi", "french", "german", ]arabic_lang = ["ar", "fa", "ug", "ur"]cyrillic_lang = ["ru", "rs_cyrillic", "be", "bg", "uk", "mn", "abq", "ady", "kbd", "ava", "dar", "inh", "che", "lbe", "lez", "tab", ]devanagari_lang = ["hi", "mr", "ne", "bh", "mai", "ang", "bho", "mah", "sck", "new", "gom", "sa", "bgc", ]if lang in latin_lang:lang = "latin"elif lang in arabic_lang:lang = "arabic"elif lang in cyrillic_lang:lang = "cyrillic"elif lang in devanagari_lang:lang = "devanagari"assert (lang in MODEL_URLS["OCR"][DEFAULT_OCR_MODEL_VERSION]["rec"]), "param lang must in {}, but got {}".format(MODEL_URLS["OCR"][DEFAULT_OCR_MODEL_VERSION]["rec"].keys(), lang)if lang == "ch":det_lang = "ch"elif lang == "structure":det_lang = "structure"elif lang in ["en", "latin"]:det_lang = "en"else:det_lang = "ml"return lang, det_langdef get_model_config(type, version, model_type, lang):if type == "OCR":DEFAULT_MODEL_VERSION = DEFAULT_OCR_MODEL_VERSIONelif type == "STRUCTURE":DEFAULT_MODEL_VERSION = DEFAULT_STRUCTURE_MODEL_VERSIONelse:raise NotImplementedErrormodel_urls = MODEL_URLS[type]if version not in model_urls:version = DEFAULT_MODEL_VERSIONif model_type not in model_urls[version]:if model_type in model_urls[DEFAULT_MODEL_VERSION]:version = DEFAULT_MODEL_VERSIONelse:logger.error("{} models is not support, we only support {}".format(model_type, model_urls[DEFAULT_MODEL_VERSION].keys()))sys.exit(-1)if lang not in model_urls[version][model_type]:if lang in model_urls[DEFAULT_MODEL_VERSION][model_type]:version = DEFAULT_MODEL_VERSIONelse:logger.error("lang {} is not support, we only support {} for {} models".format(lang, model_urls[DEFAULT_MODEL_VERSION][model_type].keys(), model_type, ))sys.exit(-1)return model_urls[version][model_type][lang]def img_decode(content: bytes):np_arr = np.frombuffer(content, dtype=np.uint8)return cv2.imdecode(np_arr, cv2.IMREAD_UNCHANGED)def check_img(img, alpha_color=(255, 255, 255)):"""Check the image data. If it is another type of image file, try to decode it into a numpy array.The inference network requires three-channel images, So the following channel conversions are donesingle channel image: Gray to RGB R←Y,G←Y,B←Yfour channel image: alpha_to_colorargs:img: image datafile format: jpg, png and other image formats that opencv can decode, as well as gif and pdf formatsstorage type: binary image, net image file, local image filealpha_color: Background color in images in RGBA formatreturn: numpy.array (h, w, 3) or list (p, h, w, 3) (p: page of pdf), boolean, boolean"""flag_gif, flag_pdf = False, Falseif isinstance(img, bytes):img = img_decode(img)if isinstance(img, str):# download net imageif is_link(img):download_with_progressbar(img, "tmp.jpg")img = "tmp.jpg"image_file = imgimg, flag_gif, flag_pdf = check_and_read(image_file)if not flag_gif and not flag_pdf:with open(image_file, "rb") as f:img_str = f.read()img = img_decode(img_str)if img is None:try:buf = BytesIO()image = BytesIO(img_str)im = Image.open(image)rgb = im.convert("RGB")rgb.save(buf, "jpeg")buf.seek(0)image_bytes = buf.read()data_base64 = str(base64.b64encode(image_bytes), encoding="utf-8")image_decode = base64.b64decode(data_base64)img_array = np.frombuffer(image_decode, np.uint8)img = cv2.imdecode(img_array, cv2.IMREAD_COLOR)except:logger.error("error in loading image:{}".format(image_file))return None, flag_gif, flag_pdfif img is None:logger.error("error in loading image:{}".format(image_file))return None, flag_gif, flag_pdf# single channel image array.shape:h,wif isinstance(img, np.ndarray) and len(img.shape) == 2:img = cv2.cvtColor(img, cv2.COLOR_GRAY2BGR)# four channel image array.shape:h,w,cif isinstance(img, np.ndarray) and len(img.shape) == 3 and img.shape[2] == 4:img = alpha_to_color(img, alpha_color)return img, flag_gif, flag_pdfclass PaddleOCR(predict_system.TextSystem):def __init__(self, **kwargs):"""paddleocr packageargs:**kwargs: other params show in paddleocr --help"""params = parse_args(mMain=False)params.__dict__.update(**kwargs)assert (params.ocr_version in SUPPORT_OCR_MODEL_VERSION), "ocr_version must in {}, but get {}".format(SUPPORT_OCR_MODEL_VERSION, params.ocr_version)params.use_gpu = check_gpu(params.use_gpu)if not params.show_log:logger.setLevel(logging.INFO)self.use_angle_cls = params.use_angle_clslang, det_lang = parse_lang(params.lang)# init model dirdet_model_config = get_model_config("OCR", params.ocr_version, "det", det_lang)params.det_model_dir, det_url = confirm_model_dir_url(params.det_model_dir, os.path.join(BASE_DIR, "whl", "det", det_lang), det_model_config["url"], )rec_model_config = get_model_config("OCR", params.ocr_version, "rec", lang)params.rec_model_dir, rec_url = confirm_model_dir_url(params.rec_model_dir, os.path.join(BASE_DIR, "whl", "rec", lang), rec_model_config["url"], )cls_model_config = get_model_config("OCR", params.ocr_version, "cls", "ch")params.cls_model_dir, cls_url = confirm_model_dir_url(params.cls_model_dir, os.path.join(BASE_DIR, "whl", "cls"), cls_model_config["url"], )if params.ocr_version in ["PP-OCRv3", "PP-OCRv4"]:params.rec_image_shape = "3, 48, 320"else:params.rec_image_shape = "3, 32, 320"# download model if using paddle inferif not params.use_onnx:maybe_download(params.det_model_dir, det_url)maybe_download(params.rec_model_dir, rec_url)maybe_download(params.cls_model_dir, cls_url)if params.det_algorithm not in SUPPORT_DET_MODEL:logger.error("det_algorithm must in {}".format(SUPPORT_DET_MODEL))sys.exit(0)if params.rec_algorithm not in SUPPORT_REC_MODEL:logger.error("rec_algorithm must in {}".format(SUPPORT_REC_MODEL))sys.exit(0)if params.rec_char_dict_path is None:params.rec_char_dict_path = str(Path(__file__).parent / rec_model_config["dict_path"])logger.debug(params)# init det_model and rec_modelsuper().__init__(params)self.page_num = params.page_numdef ocr(self, img, det=True, rec=True, cls=True, bin=False, inv=False, alpha_color=(255, 255, 255), ):"""OCR with PaddleOCRargs:img: img for OCR, support ndarray, img_path and list or ndarraydet: use text detection or not. If False, only rec will be exec. Default is Truerec: use text recognition or not. If False, only det will be exec. Default is Truecls: use angle classifier or not. Default is True. If True, the text with rotation of 180 degrees can be recognized. If no text is rotated by 180 degrees, use cls=False to get better performance. Text with rotation of 90 or 270 degrees can be recognized even if cls=False.bin: binarize image to black and white. Default is False.inv: invert image colors. Default is False.alpha_color: set RGB color Tuple for transparent parts replacement. Default is pure white."""assert isinstance(img, (np.ndarray, list, str, bytes))if isinstance(img, list) and det == True:logger.error("When input a list of images, det must be false")exit(0)if cls == True and self.use_angle_cls == False:logger.warning("Since the angle classifier is not initialized, it will not be used during the forward process")img, flag_gif, flag_pdf = check_img(img, alpha_color)# for infer pdf fileif isinstance(img, list) and flag_pdf:if self.page_num > len(img) or self.page_num == 0:imgs = imgelse:imgs = img[: self.page_num]else:imgs = [img]def preprocess_image(_image):_image = alpha_to_color(_image, alpha_color)if inv:_image = cv2.bitwise_not(_image)if bin:_image = binarize_img(_image)return _imageif det and rec:ocr_res = []for idx, img in enumerate(imgs):img = preprocess_image(img)dt_boxes, rec_res, _ = self.__call__(img, cls)if not dt_boxes and not rec_res:ocr_res.append(None)continuetmp_res = [[box.tolist(), res] for box, res in zip(dt_boxes, rec_res)]ocr_res.append(tmp_res)return ocr_reselif det and not rec:ocr_res = []for idx, img in enumerate(imgs):img = preprocess_image(img)dt_boxes, elapse = self.text_detector(img)if dt_boxes.size == 0:ocr_res.append(None)continuetmp_res = [box.tolist() for box in dt_boxes]ocr_res.append(tmp_res)return ocr_reselse:ocr_res = []cls_res = []for idx, img in enumerate(imgs):if not isinstance(img, list):img = preprocess_image(img)img = [img]if self.use_angle_cls and cls:img, cls_res_tmp, elapse = self.text_classifier(img)if not rec:cls_res.append(cls_res_tmp)rec_res, elapse = self.text_recognizer(img)ocr_res.append(rec_res)if not rec:return cls_resreturn ocr_resclass PPStructure(StructureSystem):def __init__(self, **kwargs):params = parse_args(mMain=False)params.__dict__.update(**kwargs)assert (params.structure_version in SUPPORT_STRUCTURE_MODEL_VERSION), "structure_version must in {}, but get {}".format(SUPPORT_STRUCTURE_MODEL_VERSION, params.structure_version)params.use_gpu = check_gpu(params.use_gpu)params.mode = "structure"if not params.show_log:logger.setLevel(logging.INFO)lang, det_lang = parse_lang(params.lang)if lang == "ch":table_lang = "ch"else:table_lang = "en"if params.structure_version == "PP-Structure":params.merge_no_span_structure = False# init model dirdet_model_config = get_model_config("OCR", params.ocr_version, "det", det_lang)params.det_model_dir, det_url = confirm_model_dir_url(params.det_model_dir, os.path.join(BASE_DIR, "whl", "det", det_lang), det_model_config["url"], )rec_model_config = get_model_config("OCR", params.ocr_version, "rec", lang)params.rec_model_dir, rec_url = confirm_model_dir_url(params.rec_model_dir, os.path.join(BASE_DIR, "whl", "rec", lang), rec_model_config["url"], )table_model_config = get_model_config("STRUCTURE", params.structure_version, "table", table_lang)params.table_model_dir, table_url = confirm_model_dir_url(params.table_model_dir, os.path.join(BASE_DIR, "whl", "table"), table_model_config["url"], )layout_model_config = get_model_config("STRUCTURE", params.structure_version, "layout", lang)params.layout_model_dir, layout_url = confirm_model_dir_url(params.layout_model_dir, os.path.join(BASE_DIR, "whl", "layout"), layout_model_config["url"], )# download modelif not params.use_onnx:maybe_download(params.det_model_dir, det_url)maybe_download(params.rec_model_dir, rec_url)maybe_download(params.table_model_dir, table_url)maybe_download(params.layout_model_dir, layout_url)if params.rec_char_dict_path is None:params.rec_char_dict_path = str(Path(__file__).parent / rec_model_config["dict_path"])if params.table_char_dict_path is None:params.table_char_dict_path = str(Path(__file__).parent / table_model_config["dict_path"])if params.layout_dict_path is None:params.layout_dict_path = str(Path(__file__).parent / layout_model_config["dict_path"])logger.debug(params)super().__init__(params)def __call__(self, img, return_ocr_result_in_table=False, img_idx=0, alpha_color=(255, 255, 255), ):img, flag_gif, flag_pdf = check_img(img, alpha_color)if isinstance(img, list) and flag_pdf:res_list = []for index, pdf_img in enumerate(img):logger.info("processing {}/{} page:".format(index + 1, len(img)))res, _ = super().__call__(pdf_img, return_ocr_result_in_table, img_idx=index)res_list.append(res)return res_listres, _ = super().__call__(img, return_ocr_result_in_table, img_idx=img_idx)return res
def cv2AddChineseText(img, text, position, textColor=(0, 255, 0), textSize=30):img = Image.fromarray(cv2.cvtColor(img, cv2.COLOR_BGR2RGB))draw = ImageDraw.Draw(img)draw.text(position, text, textColor, font=font)return cv2.cvtColor(np.asarray(img), cv2.COLOR_RGB2BGR)if __name__ == '__main__':font_path = 'simhei.ttf'  # 需要替换为你的中文字体路径font = ImageFont.truetype(font_path, 24)# for cmdargs = parse_args(mMain=True)image_dir = args.image_dirimage_file_list=['weights/123.jpg']if args.type == "ocr":engine = PaddleOCR(**(args.__dict__))elif args.type == "structure":engine = PPStructure(**(args.__dict__))else:raise NotImplementedErrorfor img_path in image_file_list:img_name = os.path.basename(img_path).split(".")[0]logger.info("{}{}{}".format("*" * 10, img_path, "*" * 10))if args.type == "ocr":image=cv2.imread(img_path)result = engine.ocr(img_path, det=args.det, rec=args.rec, cls=args.use_angle_cls, bin=args.binarize, inv=args.invert, alpha_color=args.alphacolor, )if result is not None:lines = []for idx in range(len(result)):res = result[idx]for line in res:points = line[0]text = line[1][0]points = np.array(points, dtype=np.int32).reshape((-1, 1, 2))cv2.polylines(image, [points], isClosed=True, color=(255, 0, 0), thickness=2)text_position = (int(points[0][0][0]), int(points[0][0][1] + 20))  # 微调文本位置# cv2.putText(image, '中文文本', (50, 100), cv2.FONT_HERSHEY_SIMPLEX, 2, (255, 255, 255), 3)image = cv2AddChineseText(image, text, text_position, textColor=(0, 255, 0), textSize=30)logger.info(line)val = "["for box in line[0]:val += str(box[0]) + "," + str(box[1]) + ","val = val[:-1]val += "]," + line[1][0] + "," + str(line[1][1]) + "\n"lines.append(val)if args.savefile:if os.path.exists(args.output) is False:os.mkdir(args.output)outfile = args.output + "/" + img_name + ".txt"with open(outfile, "w", encoding="utf-8") as f:f.writelines(lines)elif args.type == "structure":img, flag_gif, flag_pdf = check_and_read(img_path)if not flag_gif and not flag_pdf:img = cv2.imread(img_path)if not flag_pdf:if img is None:logger.error("error in loading image:{}".format(img_path))continueimg_paths = [[img_path, img]]else:img_paths = []for index, pdf_img in enumerate(img):os.makedirs(os.path.join(args.output, img_name), exist_ok=True)pdf_img_path = os.path.join(args.output, img_name, img_name + "_" + str(index) + ".jpg")cv2.imwrite(pdf_img_path, pdf_img)img_paths.append([pdf_img_path, pdf_img])all_res = []for index, (new_img_path, img) in enumerate(img_paths):logger.info("processing {}/{} page:".format(index + 1, len(img_paths)))new_img_name = os.path.basename(new_img_path).split(".")[0]result = engine(img, img_idx=index)save_structure_res(result, args.output, img_name, index)if args.recovery and result != []:from copy import deepcopyfrom ppstructure.recovery.recovery_to_doc import sorted_layout_boxesh, w, _ = img.shaperesult_cp = deepcopy(result)result_sorted = sorted_layout_boxes(result_cp, w)all_res += result_sortedif args.recovery and all_res != []:try:from ppstructure.recovery.recovery_to_doc import convert_info_docxconvert_info_docx(img, all_res, args.output, img_name)except Exception as ex:logger.error("error in layout recovery image:{}, err msg: {}".format(img_name, ex))continuefor item in all_res:item.pop("img")item.pop("res")logger.info(item)logger.info("result save to {}".format(args.output))cv2.imshow('image', image)cv2.waitKey(0)

本文来自互联网用户投稿,该文观点仅代表作者本人,不代表本站立场。本站仅提供信息存储空间服务,不拥有所有权,不承担相关法律责任。如若转载,请注明出处:http://www.hqwc.cn/news/698077.html

如若内容造成侵权/违法违规/事实不符,请联系编程知识网进行投诉反馈email:809451989@qq.com,一经查实,立即删除!

相关文章

智能组网实施步骤?

随着信息技术的快速发展&#xff0c;智能组网正在逐渐成为各个行业的关注焦点。智能组网通过将各种设备、终端和系统连接起来&#xff0c;实现信息的传输和共享&#xff0c;从而提升工作效率和运营效益。本文将介绍智能组网的实施步骤&#xff0c;以及一家名为【天联】的智能组…

YOLOv8独家改进:backbone改进 | 微软新作StarNet:超强轻量级Backbone | CVPR 2024

💡💡💡创新点:star operation(元素乘法)在无需加宽网络下,将输入映射到高维非线性特征空间的能力,这就是StarNet的核心创新,在紧凑的网络结构和较低的能耗下展示了令人印象深刻的性能和低延迟 💡💡💡如何跟YOLOv8结合:替代YOLOv8的backbone 收录 YOLOv8…

如何按值对Python字典进行排序?

在Python中&#xff0c;字典&#xff08;dict&#xff09;是一种非常有用的数据结构&#xff0c;它允许我们以键值对的形式存储数据。有时&#xff0c;我们可能需要根据字典中的值对字典项进行排序。这篇文章将详细讲解如何实现这一功能&#xff0c;并提供一些实用的示例。 基…

游戏中的设计模式一

游戏开发是一个快速迭代的过程&#xff0c;代码复杂度也很高&#xff0c;借助于设计模式&#xff0c;可以帮助我们降低复杂度&#xff0c;降低系统间的耦合&#xff0c;从而高效高质的做出交付。 最近读了这本书&#xff1a;《游戏编程模式》[1]&#xff0c;很受启发&#xff…

MySQL8.0就地升级到MySQL8.4.0

MySQL8.0就地升级到MySQL8.4.0 升级需求&#xff1a;将8.0.35升级到8.4.0,以In-Place方式直接升级到MySQL8.4.0。 数据库版本 操作系统版本 原版本 8.0.35 Centos7.9 x86_64 新版本 8.4.0 Centos7.9 x86_64 关闭现有版本MySQL&#xff0c;将二进制或包替换成新版本并…

Java面试八股之String类的常用方法有哪些

Java中String类的常用方法有哪些 获取字符串信息&#xff1a; length()&#xff1a;返回字符串的字符数。 isEmpty()&#xff1a;判断字符串是否为空&#xff08;即长度为0&#xff09;。 访问单个字符&#xff1a; charAt(int index)&#xff1a;返回指定索引处的字符。 …

对比分析汽车灯罩材料使用聚碳酸酯(PC)和PMMA(亚克力)的优缺点,汽车车灯的灯罩如果破损破裂破洞了要怎么修复?

对比分析汽车灯罩材料使用聚碳酸酯&#xff08;PC&#xff09;和PMMA&#xff08;亚克力&#xff09;的优缺点&#xff0c;并给出建议。 要求&#xff1a; 1. 对比分析两种材料的性能、成本、耐用性、安全性等方面的差异。 2. 给出针对不同应用场景&#xff08;如夜间照明…

光栅化技术在AI去衣应用中的创新探索

引言&#xff1a; 随着计算机视觉和人工智能技术的飞速发展&#xff0c;AI去衣技术逐渐走进公众视野。这一技术以其独特的应用前景和技术挑战引起了广泛的关注。在实现衣物去除的同时保持图像质量的关键技术之一&#xff0c;便是光栅化技术。本文将深入探讨光栅化技术在AI去衣中…

Linux编辑器vim的配置

文章目录 简单vim配置配置文件的位置常用配置选项&#xff0c;用来测试 使用插件 简单vim配置 配置文件的位置 在目录/etc/下面&#xff0c;有个名叫vimrc的文件&#xff0c;这是系统中公共的vim配置文件&#xff0c;对所有用户有效。 [yuiiZbp19b5lvg8xtpf1tzrenZ etc]$ cl…

Davinci工程vBaseEnv模块讲解

配合的模块 要正常使用vBaseEnv模块&#xff0c;要同时使能EcuC、OS、vBRS和vLinkGen模块。 OS是操作系统&#xff0c;除了FBL以外&#xff0c;其他都需要用到OS。 vBaseEnv是基础环境 vBRS是基本运行系统 vLinkGen脚本链接生成器 EcuC是ECU配置 EcuC配置 需要配合vBaseEnv模…

Processor System Reset IP核配置详解

本文描述了如何使用Xilinx的Vivado Design Suite环境中的工具来定制和生成 Processor System Reset IP 核。Vivado Design Suite是一个强大的FPGA设计和开发环境&#xff0c;它允许用户定制和配置各种IP核以适应他们的特定设计需求。 以下是针对如何定制IP核的步骤的简要概述&…

一、VIsual Studio下的Qt环境配置(Visual Studio 2022 + Qt 5.12.10)

一、下载编译器Visual Studio2022和Qt 5.12.10 Visual Studio 2022 社区版就够学习使用了 Qt5.12.10 安装教程网上搜&#xff0c;一大堆 也很简单&#xff0c;配置直接选默认&#xff0c;路径留意一下即可 二、配置环境 Ⅰ&#xff0c;配置Qt环境变量 系统变量下的Path&a…