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
39
40
41
42
43
44
45
46
47
48
49
50
51
52
53
54
55
56
57
58
59
60
61
62
63
64
65
66
67
68
69
70
71
72
73
74
75
76
77
78
79
80
81
82
83
84
85
86
87
88
89
90
91
92
93
94
95
96
97
98
99
100
101
102
103
104
105
106
107
108
109
110
111
112
113
114
115
116
117
118
119
120
121
122
123
124
125
126
127
128
129
130
131
132
133
134
135
136
137
138
139
140
141
142
143
144
145
146
147
148
149
150
151
152
153
154
155
156
157
158
159
160
161
162
163
164
165
166
167
168
169
170
171
172
173
174
175
176
177
178
179
180
181
182
183
184
185
186
187
188
189
190
191
192
193
194
195
196
197
198
199
200
201
202
203
204
205
206
207
208
209
210
211
212
213
214
215
216
217
218
219
220
221
222
223
224
225
226
227
228
229
230
231
232
233
234
235
236
237
238
239
240
241
242
243
244
245
246
247
248
249
250
251
252
253
254
255
256
257
258
259
260
261
262
263
264
265
266
267
268
269
270
271
272
273
274
275
276
277
278
279
280
281
282
283
284
285
286
287
288
289
290
291
292
293
294
295
296
297
298
299
300
301
302
303
304
305
306
307
308
309
310
311
312
313
314
315
316
317
318
319
320
321
322
323
324
325
326
327
328
329
330
331
332
333
334
335
336
337
338
|
# -*- encoding=utf-8 -*-
"""
@Author: Kang
@Modified by:
@Datetime: 2025/07/15 13:57
@Description: OCR test script
"""
import os
import time
import copy
from pathlib import Path
from typing import List, Dict, Any
import cv2
import numpy as np
from loguru import logger
from paddlex import create_model
class OCRProcessor:
"""OCR processor class"""
def __init__(self,
det_model_dir: str = "/opt/models/ocr/PP-OCRv4_server_det_infer_om_310P",
rec_model_dir: str = "/opt/models/ocr/PP-OCRv4_server_rec_infer_om_310P",
ori_model_dir: str = "/opt/models/ocr/PP-LCNet_x1_0_textline_ori_infer",
device: str = "npu:0",
output_dir: str = "/opt/output/"):
self.output_dir = Path(output_dir)
self.output_dir.mkdir(parents=True, exist_ok=True)
# Configure parameters
hpi_config = {
"auto_config": False,
"backend": "om",
}
# Initialize classification model
logger.info("Loading classification model...")
self.model_ori = create_model(
model_name="PP-LCNet_x1_0_textline_ori",
model_dir=ori_model_dir,
)
# Initialize detection model
logger.info("Loading detection model...")
self.model_det = create_model(
model_name="PP-OCRv4_server_det",
model_dir=det_model_dir,
device=device,
use_hpip=True,
hpi_config=hpi_config,
input_shape=[3, 640, 480]
)
# Initialize recognition model
logger.info("Loading recognition model...")
self.model_rec = create_model(
model_name="PP-OCRv4_server_rec",
model_dir=rec_model_dir,
device=device,
use_hpip=True,
hpi_config=hpi_config,
input_shape=[3, 48, 320]
)
logger.info("Model loaded successfully")
def _crop_by_polys(self, img: np.ndarray, dt_polys: List[list]) -> List[dict]:
"""
Call method to crop images based on detection boxes.
Args:
img (nd.ndarray): The input image.
dt_polys (list[list]): List of detection polygons.
Returns:
list[dict]: A list of dictionaries containing cropped images and their sizes.
Raises:
NotImplementedError: If det_box_type is not 'quad' or 'poly'.
"""
dt_boxes = np.array(dt_polys)
output_list = []
for bno in range(len(dt_boxes)):
tmp_box = copy.deepcopy(dt_boxes[bno])
img_crop = self.get_minarea_rect_crop(img, tmp_box)
output_list.append(img_crop)
return output_list
def get_minarea_rect_crop(self, img: np.ndarray, points: np.ndarray) -> np.ndarray:
"""
Get the minimum area rectangle crop from the given image and points.
Args:
img (np.ndarray): The input image.
points (np.ndarray): A list of points defining the shape to be cropped.
Returns:
np.ndarray: The cropped image with the minimum area rectangle.
"""
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 = self.get_rotate_crop_image(img, np.array(box))
return crop_img
def _rotate_image(self, image_array_list: List[np.ndarray], rotate_angle_list: List[int]):
assert len(image_array_list) == len(
rotate_angle_list
), f"Length of image ({len(image_array_list)}) must match length of angle ({len(rotate_angle_list)})"
for angle in rotate_angle_list:
assert angle in [0, 1], f"rotate_angle must be 0 or 1, now it's {angle}"
rotated_images = []
for image_array, rotate_indicator in zip(image_array_list, rotate_angle_list):
# Convert 0/1 indicator to actual rotation angle
rotate_angle = rotate_indicator * 180
if rotate_angle < 0 or rotate_angle >= 360:
raise ValueError("`angle` should be in range [0, 360)")
if rotate_angle < 1e-7:
rotated_images.append(image_array)
continue
# Should we align corners?
h, w = image_array.shape[:2]
center = (w / 2, h / 2)
scale = 1.0
mat = cv2.getRotationMatrix2D(center, rotate_angle, scale)
cos = np.abs(mat[0, 0])
sin = np.abs(mat[0, 1])
new_w = int((h * sin) + (w * cos))
new_h = int((h * cos) + (w * sin))
mat[0, 2] += (new_w - w) / 2
mat[1, 2] += (new_h - h) / 2
dst_size = (new_w, new_h)
rotated = cv2.warpAffine(
image_array,
mat,
dst_size,
flags=cv2.INTER_CUBIC,
)
rotated_images.append(rotated)
logger.info(f"Number of rotated images: {len(rotated_images)}")
return rotated_images
def get_rotate_crop_image(self, img: np.ndarray, points: list) -> np.ndarray:
"""
Crop and rotate the input image based on the given four points to form a perspective-transformed image.
Args:
img (np.ndarray): The input image array.
points (list): A list of four 2D points defining the crop region in the image.
Returns:
np.ndarray: The transformed image array.
"""
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 process_image(self, image_path: str) -> List[Dict[str, Any]]:
"""
Process single image for OCR recognition
Args:
image_path: Image path
Returns:
List of recognition results
"""
if not os.path.exists(image_path):
logger.error(f"Image file does not exist: {image_path}")
return []
try:
# Read image
image = cv2.imread(image_path)
if image is None:
logger.error(f"Failed to read image: {image_path}")
return []
logger.info(f"Start processing image: {image_path}")
start_time = time.time()
# Text detection
logger.info(f"Start text detection")
det_start = time.time()
output_det = self.model_det.predict(image)
det_time = time.time() - det_start
logger.info(f"Text detection time: {det_time}s")
results = []
result_det = []
for res in output_det:
det_polys = res.get("dt_polys", [])
det_scores = res.get("dt_scores", [])
for idx, det_poly in enumerate(det_polys):
result_det.append({
"idx": idx,
"dt_polys": det_poly,
"dt_scores": det_scores[idx],
})
logger.info(f"Detected {len(det_polys)} text regions")
images_det = self._crop_by_polys(image, det_polys)
for idx, img in enumerate(images_det):
cv2.imwrite(f"{self.output_dir}/cropped_det_{idx}.png", img)
# Text direction classification
logger.info(f"Start text direction classification")
ori_start = time.time()
output_ori = self.model_ori.predict(images_det)
ori_time = time.time() - ori_start
logger.info(f"Text direction classification time: {ori_time}s")
angles = [
int(ori_res["class_ids"][0])
for ori_res in output_ori
]
images_ori = self._rotate_image(images_det, angles)
for idx, img in enumerate(images_ori):
cv2.imwrite(f"{self.output_dir}/cropped_ori_{idx}.png", img)
# Text recognition
logger.info(f"Start text recognition")
rec_start = time.time()
for item in result_det:
output_rec = self.model_rec.predict(images_ori[item["idx"]])
for rec_res in output_rec:
rec_text = rec_res.get("rec_text", "")
rec_score = rec_res.get("rec_score", 0)
results.append({
"idx": item["idx"],
"dt_polys": item["dt_polys"].tolist(),
"dt_scores": item["dt_scores"],
"rec_res": rec_text,
"rec_score": rec_score,
})
rec_time = time.time() - rec_start
logger.info(f"Detection time-text recognition: {rec_time}s")
total_time = time.time() - start_time
logger.info(f"Total processing time: {total_time:.3f}s")
return results
except Exception as e:
logger.exception(f"Failed to process image: {e}")
return []
def batch_process(self, image_paths: List[str]) -> Dict[str, List[Dict[str, Any]]]:
"""
Batch process images
Args:
image_paths: List of image paths
Returns:
Batch processing results
"""
batch_results = {}
for image_path in image_paths:
results = self.process_image(image_path)
batch_results[image_path] = results
return batch_results
def main():
"""Main function"""
# Initialize OCR processor
ocr_processor = OCRProcessor(
output_dir="/opt/output/"
)
# Process single image
image_path = "/opt/test/test.png"
results = ocr_processor.process_image(image_path)
# Output results
print("\n=== OCR results ===")
for result in results:
print(result)
if __name__ == "__main__":
main()
|
