1. 概述
项目地址https://github.com/RapidAI/RapidStructure?tab=readme-ov-file
2. 文档方向分类示例
安装$ pip install rapid-orientation
import cv2
from rapid_orientation import RapidOrientation
orientation_engine = RapidOrientation()
img = cv2.imread('test_images/layout.png')
orientation_res, elapse = orientation_engine(img)
print(orientation_res)
# 返回结果为str类型，有四类：0 | 90 | 180 | 270
3. 版面分析RapidLayout
安装$ pip install rapid-layout
import cv2
from rapid_layout import RapidLayout, VisLayout
# model_type类型参见上表。指定不同model_type时，会自动下载相应模型到安装目录下的。
layout_engine = RapidLayout(conf_thres=0.5, model_type="pp_layout_cdla")
img = cv2.imread('test_images/layout.png')
boxes, scores, class_names, elapse = layout_engine(img)
ploted_img = VisLayout.draw_detections(img, boxes, scores, class_names)
if ploted_img is not None:
cv2.imwrite("layout_res.png", ploted_img)
4. 文字识别和表格识别rapid_table
from rapid_table import RapidTable, VisTable
# RapidTable类提供model_path参数，可以自行指定上述2个模型，默认是en_ppstructure_mobile_v2_SLANet.onnx
# table_engine = RapidTable(model_path='ch_ppstructure_mobile_v2_SLANet.onnx')
table_engine = RapidTable()
ocr_engine = RapidOCR()
viser = VisTable()
img_path = 'test_images/table.jpg'
ocr_result, _ = ocr_engine(img_path)
table_html_str, table_cell_bboxes, elapse = table_engine(img_path, ocr_result)
5. latex识别rapidLaTexOCR
from rapid_latex_ocr import LatexOCR
model = LatexOCR()
img_path = "tests/test_files/6.png"
with open(img_path, "rb") as f:
data = f.read()
res, elapse = model(data)
6. 整合版：RapidOCRPDF
# 基于CPU 依赖rapidocr_onnxruntime
pip install rapidocr_pdf[onnxruntime]
# 基于CPU 依赖rapidocr_openvino 更快
pip install rapidocr_pdf[openvino]
# 基于GPU 依赖rapidocr_paddle
pip install rapidocr_pdf[paddle]
使用：
from rapidocr_pdf import PDFExtracter
pdf_extracter = PDFExtracter()
pdf_path = 'tests/test_files/direct_and_image.pdf'
texts = pdf_extracter(pdf_path, force_ocr=False)
print(texts)
