doc-page-extractor 0.0.5__py3-none-any.whl → 0.0.7__py3-none-any.whl

doc_page_extractor/onnxocr/utils.py

@@ -0,0 +1,71 @@
+import numpy as np
+import cv2
+
+def get_rotate_crop_image(img, points):
+  """
+  img_height, img_width = img.shape[0:2]
+  left = int(np.min(points[:, 0]))
+  right = int(np.max(points[:, 0]))
+  top = int(np.min(points[:, 1]))
+  bottom = int(np.max(points[:, 1]))
+  img_crop = img[top:bottom, left:right, :].copy()
+  points[:, 0] = points[:, 0] - left
+  points[:, 1] = points[:, 1] - top
+  """
+  assert len(points) == 4, "shape of points must be 4*2"
+  img_crop_width = int(
+    max(
+      np.linalg.norm(points[0] - points[1]), np.linalg.norm(points[2] - points[3])
+    )
+  )
+  img_crop_height = int(
+    max(
+      np.linalg.norm(points[0] - points[3]), np.linalg.norm(points[1] - points[2])
+    )
+  )
+  pts_std = np.float32(
+    [
+      [0, 0],
+      [img_crop_width, 0],
+      [img_crop_width, img_crop_height],
+      [0, img_crop_height],
+    ]
+  )
+  M = cv2.getPerspectiveTransform(points, pts_std)
+  dst_img = cv2.warpPerspective(
+    img,
+    M,
+    (img_crop_width, img_crop_height),
+    borderMode=cv2.BORDER_REPLICATE,
+    flags=cv2.INTER_CUBIC,
+  )
+  dst_img_height, dst_img_width = dst_img.shape[0:2]
+  if dst_img_height * 1.0 / dst_img_width >= 1.5:
+    dst_img = np.rot90(dst_img)
+  return dst_img
+
+
+def get_minarea_rect_crop(img, points):
+  bounding_box = cv2.minAreaRect(np.array(points).astype(np.int32))
+  points = sorted(list(cv2.boxPoints(bounding_box)), key=lambda x: x[0])
+
+  index_a, index_b, index_c, index_d = 0, 1, 2, 3
+  if points[1][1] > points[0][1]:
+    index_a = 0
+    index_d = 1
+  else:
+    index_a = 1
+    index_d = 0
+  if points[3][1] > points[2][1]:
+    index_b = 2
+    index_c = 3
+  else:
+    index_b = 3
+    index_c = 2
+
+  box = [points[index_a], points[index_b], points[index_c], points[index_d]]
+  crop_img = get_rotate_crop_image(img, np.array(box))
+  return crop_img
+
+def str2bool(v):
+  return v.lower() in ("true", "t", "1")

{doc_page_extractor-0.0.5.dist-info → doc_page_extractor-0.0.7.dist-info}/METADATA

@@ -1,6 +1,6 @@
 Metadata-Version: 2.2
 Name: doc-page-extractor
-Version: 0.0.5
+Version: 0.0.7
 Summary: doc page extractor can identify text and format in images and return structured data.
 Home-page: https://github.com/Moskize91/doc-page-extractor
 Author: Tao Zeyu
@@ -9,11 +9,11 @@ Description-Content-Type: text/markdown
 License-File: LICENSE
 Requires-Dist: opencv-python<5.0,>=4.11.0
 Requires-Dist: pillow<11.0,>=10.3
-Requires-Dist: numpy<1.26,>=1.24.0
+Requires-Dist: pyclipper<2.0,>=1.2.0
+Requires-Dist: numpy<2.0,>=1.24.0
 Requires-Dist: shapely<3.0,>=2.0.0
 Requires-Dist: transformers<5.0,>=4.48.0
 Requires-Dist: doclayout_yolo>=0.0.3
-Requires-Dist: paddleocr==2.9.0
 Dynamic: author
 Dynamic: author-email
 Dynamic: description
@@ -36,10 +36,20 @@ doc page extractor can identify text and format in images and return structured
 pip install doc-page-extractor
 ```
 
+```shell
+pip install onnxruntime==1.21.0
+```
+
 ## Using CUDA
 
 Please refer to the introduction of [PyTorch](https://pytorch.org/get-started/locally/) and select the appropriate command to install according to your operating system.
 
+In addition, replace the command to install `onnxruntime` in the previous article with the following:
+
+```shell
+pip install onnxruntime-gpu==1.21.0
+```
+
 ## Example
 
 ```python
@@ -48,7 +58,7 @@ from doc_page_extractor import DocExtractor
 
 extractor = DocExtractor(
   model_dir_path=model_path, # Folder address where AI model is downloaded and installed
-  device="cpu", # If you want to use CUDA, please change to device="cuda:0".
+  device="cpu", # If you want to use CUDA, please change to device="cuda".
 )
 with Image.open("/path/to/your/image.png") as image:
   result = extractor.extract(
@@ -62,6 +72,8 @@ for layout in result.layouts:
 
 ## Acknowledgements
 
+The code of `doc_page_extractor/onnxocr` in this repo comes from [OnnxOCR](https://github.com/jingsongliujing/OnnxOCR).
+
 - [DocLayout-YOLO](https://github.com/opendatalab/DocLayout-YOLO)
-- [PaddleOCR](https://github.com/PaddlePaddle/PaddleOCR)
+- [OnnxOCR](https://github.com/jingsongliujing/OnnxOCR)
 - [layoutreader](https://github.com/ppaanngggg/layoutreader)

doc_page_extractor-0.0.7.dist-info/RECORD

@@ -0,0 +1,33 @@
+doc_page_extractor/__init__.py,sha256=jCf5lo3A9JVDquflYMlvH8nJIs3EjBt8AG5y8mwfS68,210
+doc_page_extractor/clipper.py,sha256=PDafB_9JGwV_dRY7oWe1yf44roSsEaCuEdg3VRMvJNo,3125
+doc_page_extractor/downloader.py,sha256=NbGN9ARnER8-gd4T1uc3W98WMEClVxMrqnShq8HibTw,455
+doc_page_extractor/extractor.py,sha256=D3SLWUAciq8jGU6mlkVwIon-4nHJaYoKpPjGCN_YLhQ,10055
+doc_page_extractor/layoutreader.py,sha256=BdC4oPbtpXoLmYhjuSFrKn6SNoT2zWw_gi95sGAUwrk,4031
+doc_page_extractor/ocr.py,sha256=6eLUVx6NSuRAwrq8Mc2zYs3yocxpOgUQS_4LIIqywnQ,5147
+doc_page_extractor/ocr_corrector.py,sha256=RfRA1jESEuqC8_a2kUEvHblT_B4xBjE0OApLMl1JiRg,3917
+doc_page_extractor/overlap.py,sha256=9_WbHxbKIbHM6R3ZUP2YG33pZlbLCHgwFb--NF3cCG0,5155
+doc_page_extractor/plot.py,sha256=R8hbmdGjtw2pAH1lJkGc7Qbis4aRaaAkrkEo6WjbqyM,1378
+doc_page_extractor/raw_optimizer.py,sha256=1KghECq_rJwuZZITTLQnGTKYivFKg_qDvMLN9g17sks,2844
+doc_page_extractor/rectangle.py,sha256=Tp__NPiY6JlYwYxejST7BUXhv_bl8tkmDXi4JgHCK6E,1539
+doc_page_extractor/rotation.py,sha256=Dp8rXfgCzHQwqlAbU-uQt-zHC6Jm9KsIjcR6IhFQ5EU,4284
+doc_page_extractor/types.py,sha256=UWghDwajMtEKEYUcOOjr5dM-MWiJ-P-8nWYagouf9ds,631
+doc_page_extractor/utils.py,sha256=3rtIxiTJ7W5yOuY0UHedUJ3G34tPOw0jdHnUdOQ1tWI,207
+doc_page_extractor/onnxocr/__init__.py,sha256=BK4YpX4pU0nRxbcI5f5cbIVfdBEsx4W980QYmpNQaH0,38
+doc_page_extractor/onnxocr/cls_postprocess.py,sha256=o879Ned0RMUERYLviuToZ0xTvhn2UsYAb-yPC5gj8h4,822
+doc_page_extractor/onnxocr/db_postprocess.py,sha256=R3yXXfReiQgLaYIvvfnrFfshI202LjHMvcZwcLpjmTY,7913
+doc_page_extractor/onnxocr/imaug.py,sha256=Q192kIsRPI5zTm4RA_UUXlo6tvGJS8wrUaa-xrfnO_w,811
+doc_page_extractor/onnxocr/operators.py,sha256=0nLiV1dWej9vdPa_DO04F7SvqF-l9NOFgHUuHUPNvsw,5556
+doc_page_extractor/onnxocr/predict_base.py,sha256=LzRSPgxgFSRAreJOMpDTUKuBvvO_Qe5_5tK4lNuGl-w,1269
+doc_page_extractor/onnxocr/predict_cls.py,sha256=28MliSQIyHc82EUbdkQb31KaB90rSzSmps1v6WsskQk,3065
+doc_page_extractor/onnxocr/predict_det.py,sha256=VYsvNbCJQi1UuetwvR_hx-U7JScHyFjmJmo8YwHyQt4,4092
+doc_page_extractor/onnxocr/predict_rec.py,sha256=qQrCs5jzCf5PYp-iEKJ53pcx_xRoJdJyavPvsvuh5Ic,10999
+doc_page_extractor/onnxocr/predict_system.py,sha256=yoqXunAsoboPsWe7qQjvQf2_SMW1T1QMriEoiGdX3BM,2721
+doc_page_extractor/onnxocr/rec_postprocess.py,sha256=qZt5Ripal7z9hniKq5e7azOkD9e6NR1ylWpRpznhweg,29556
+doc_page_extractor/onnxocr/utils.py,sha256=AQoHgQyv-jpPo4BsVzq3r7_ze698EZ-a7LJobm2fwUI,1864
+tests/__init__.py,sha256=47DEQpj8HBSa-_TImW-5JCeuQeRkm5NMpJWZG3hSuFU,0
+tests/test_history_bus.py,sha256=WaCUW3U75SESMcLq0f5FKnpVUVRDvmfxLFE7Zo83e48,2517
+doc_page_extractor-0.0.7.dist-info/LICENSE,sha256=TfPDBt3ar0uv_f9cqCDMZ5rIzW3CY8anRRd4PkL6ejs,34522
+doc_page_extractor-0.0.7.dist-info/METADATA,sha256=s-ewJAyPQ1I_fgTee91NN99T42HcAaKFu1MAUhZKqdk,2203
+doc_page_extractor-0.0.7.dist-info/WHEEL,sha256=jB7zZ3N9hIM9adW7qlTAyycLYW9npaWKLRzaoVcLKcM,91
+doc_page_extractor-0.0.7.dist-info/top_level.txt,sha256=ErNybD_lBzAmw8mVBAK4htsAH_hp14jioZVex-tUqvM,25
+doc_page_extractor-0.0.7.dist-info/RECORD,,

doc_page_extractor-0.0.5.dist-info/RECORD

@@ -1,21 +0,0 @@
-doc_page_extractor/__init__.py,sha256=CeBP-ggpQ-MIMjaOm_MDNNkFfrlDyJshYDgYGjY8OoI,222
-doc_page_extractor/clipper.py,sha256=PDafB_9JGwV_dRY7oWe1yf44roSsEaCuEdg3VRMvJNo,3125
-doc_page_extractor/downloader.py,sha256=0rI8Ysafkq2jPpWm_FLWli68WTuBxxQYHAPJ8jn16sM,294
-doc_page_extractor/extractor.py,sha256=rksJO7nS0gmxCW_Xi3I-SLvh0c4WfYZQg8P1TZhdy8E,10328
-doc_page_extractor/layoutreader.py,sha256=BdC4oPbtpXoLmYhjuSFrKn6SNoT2zWw_gi95sGAUwrk,4031
-doc_page_extractor/ocr.py,sha256=KiT2rVALlJvIuW0p7fIs3Anrtmxutt4PZwlrZTSgYGY,4001
-doc_page_extractor/ocr_corrector.py,sha256=gaI_nj9xFGFp5KV5EBUZ3qtjG2pVRi8EMU_UT0obvVc,3953
-doc_page_extractor/overlap.py,sha256=9_WbHxbKIbHM6R3ZUP2YG33pZlbLCHgwFb--NF3cCG0,5155
-doc_page_extractor/plot.py,sha256=R8hbmdGjtw2pAH1lJkGc7Qbis4aRaaAkrkEo6WjbqyM,1378
-doc_page_extractor/raw_optimizer.py,sha256=1KghECq_rJwuZZITTLQnGTKYivFKg_qDvMLN9g17sks,2844
-doc_page_extractor/rectangle.py,sha256=Tp__NPiY6JlYwYxejST7BUXhv_bl8tkmDXi4JgHCK6E,1539
-doc_page_extractor/rotation.py,sha256=Dp8rXfgCzHQwqlAbU-uQt-zHC6Jm9KsIjcR6IhFQ5EU,4284
-doc_page_extractor/types.py,sha256=UWghDwajMtEKEYUcOOjr5dM-MWiJ-P-8nWYagouf9ds,631
-doc_page_extractor/utils.py,sha256=3rtIxiTJ7W5yOuY0UHedUJ3G34tPOw0jdHnUdOQ1tWI,207
-tests/__init__.py,sha256=47DEQpj8HBSa-_TImW-5JCeuQeRkm5NMpJWZG3hSuFU,0
-tests/test_history_bus.py,sha256=WaCUW3U75SESMcLq0f5FKnpVUVRDvmfxLFE7Zo83e48,2517
-doc_page_extractor-0.0.5.dist-info/LICENSE,sha256=TfPDBt3ar0uv_f9cqCDMZ5rIzW3CY8anRRd4PkL6ejs,34522
-doc_page_extractor-0.0.5.dist-info/METADATA,sha256=m5uJPWjeEqkoPqevT-M79nyFnrh6UmiOAgxY9Dgx34U,1882
-doc_page_extractor-0.0.5.dist-info/WHEEL,sha256=jB7zZ3N9hIM9adW7qlTAyycLYW9npaWKLRzaoVcLKcM,91
-doc_page_extractor-0.0.5.dist-info/top_level.txt,sha256=ErNybD_lBzAmw8mVBAK4htsAH_hp14jioZVex-tUqvM,25
-doc_page_extractor-0.0.5.dist-info/RECORD,,