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
|
import os
from decimal import Decimal
import numpy as np
import cv2
import easyocr
import json
import shutil
from tqdm import tqdm
from PIL import Image
from pypinyin import pinyin, Style
lan_code = ['ru', 'ind', 'tur', 'deu', 'ita', 'jpn', 'fra', 'tha', 'por', 'spa', 'vie', 'ara', 'kor', 'msa']
language_map = {
'俄语': 'ru',
'印尼': 'ind',
'土耳其': 'tur',
'德语': 'deu',
'意大利语': 'ita',
'日语': 'jpn',
'法语': 'fra',
'泰语': 'tha',
'葡萄牙': 'por',
'西班牙语': 'spa',
'越南语': 'vie',
'阿拉伯语': 'ara',
'韩语': 'kor',
'马来语': 'msa'
}
reader = easyocr.Reader(['ru'], gpu=True)
def convert_to_pinyin(text):
"""
将中文字符转换为拼音。
"""
result = pinyin(text, style=Style.NORMAL)
return ''.join([item[0] for item in result])
def clean_path(path):
"""
将���径中的非法字符替换为拼音。
"""
illegal_chars = r'[\/:*?"<>|]'
path_parts = path.split(os.sep)
cleaned_parts = []
for part in path_parts:
part = convert_to_pinyin(part)
cleaned_parts.append(part)
return os.sep.join(cleaned_parts)
def check_language_code_in_directory(directory_path, lan_codes):
"""
检查指定路径中是否包含语言代码列表中的任何一个内容。
"""
found_codes = []
try:
for lan_code in lan_codes:
if lan_code in directory_path:
found_codes.append(lan_code)
return found_codes
except Exception as e:
print(f"发生错误: {e}")
return []
def numpy_encoder(obj):
"""
自定义 JSON 序列化函数。
"""
if isinstance(obj, np.ndarray):
return obj.tolist()
raise TypeError(f"Type {type(obj)} not serializable")
def extract_text_with_coords(image_path, folder, lan_code):
"""
从图像中提取文字及其坐标，并返回格式化的 JSON 数据。
"""
try:
lan_zh = check_language_code_in_directory(image_path, folder)
language_codes = "ru"
img = Image.open(image_path)
img = cv2.cvtColor(np.array(img), cv2.COLOR_RGB2BGR)
if img is None:
return {"error": f"无法读取图像: {image_path}"}
results = reader.readtext(image_path)
formatted_results = []
for result in results:
bbox, text, _ = result
if text.strip():
x_min, y_min = bbox[0]
x_max, y_max = bbox[2]
coords = np.array([
[x_min, y_min],
[x_max, y_min],
[x_max, y_max],
[x_min, y_max]
], dtype=np.float64)
result_dict = {
"label": text,
"points": numpy_encoder(coords),
"language": lan_zh[0],
"textType": "Mix" if len(text) > 1 else "Single",
"textDirection": "Horizontal_0",
"assign": "Normal",
"group_id": None,
"shape_type": "polygon",
"flags": {}
}
formatted_results.append(result_dict)
cv2.rectangle(img, (int(x_min), int(y_min)), (int(x_max), int(y_max)), (0, 255, 0), 2)
output_image_path = os.path.splitext(image_path)[0] + "_with_boxes.jpg"
output_image_path = clean_path(output_image_path)
output_folder = os.path.dirname(output_image_path)
if not os.path.exists(output_folder):
os.makedirs(output_folder)
result = cv2.imwrite(output_image_path, img)
print(f"已保存带框图像: {output_image_path}, result: {result}")
original_image_path = clean_path(image_path)
original_output_folder = os.path.dirname(original_image_path)
if not os.path.exists(original_output_folder):
os.makedirs(original_output_folder)
shutil.copy(image_path, original_image_path)
print(f"原图已复制到: {original_image_path}")
return formatted_results
except Exception as e:
return {"error": f"发生错误: {str(e)}"}
def save_json_result(image_path, result):
"""
将识别结果保存为 JSON 文件。
"""
try:
image_name = os.path.splitext(os.path.basename(image_path))[0]
json_path = os.path.join(os.path.dirname(image_path), f"{image_name}.json")
json_path = clean_path(json_path)
with open(json_path, 'w', encoding='utf-8') as json_file:
json.dump(result, json_file, ensure_ascii=False, indent=4)
print(f"结果已保存到: {json_path}")
except Exception as e:
print(f"保存 JSON 文件时发生错误: {str(e)}")
def get_all_images_in_directory(directory_path):
"""
递归读取指定目录及其子目录中的所有图像文件。
"""
image_files = []
for root, dirs, files in os.walk(directory_path):
for file in files:
if file.lower().endswith(('.png', '.jpg', '.jpeg', '.bmp')):
image_files.append(os.path.join(root, file))
return image_files
def process_images_in_directory(directory_path, folders, lan_code):
"""
批量处理指定目录中的所有图像文件。
"""
image_paths = get_all_images_in_directory(directory_path)
for image_path in tqdm(image_paths, desc="Processing images"):
try:
print(f"正在处理图像: {image_path}")
folder_name = os.path.basename(os.path.dirname(image_path))
if folder_name in language_map:
lan_code = language_map[folder_name]
else:
print(f"未找到对应的语言代码: {folder_name}")
continue
result = extract_text_with_coords(image_path, folders, lan_code)
if isinstance(result, dict) and "error" in result:
print(f"处理 {image_path} 时发生错误: {result['error']}")
elif isinstance(result, list) and result:
save_json_result(image_path, result)
else:
print(f"处理 {image_path} 时没有检测到有效文本。")
except Exception as e:
print(f"处理 {image_path} 时发生错误: {str(e)}")
def get_all_folders_in_directory(directory_path):
"""
获取目录下所有文件夹名。
"""
try:
items = os.listdir(directory_path)
folders = [item for item in items if os.path.isdir(os.path.join(directory_path, item))]
return folders
except Exception as e:
print(f"发生错误: {e}")
return []
def fix_non_ascii_path(path):
"""
修复路径中的非 ASCII 字符问题。
"""
return path.encode('utf-8').decode('utf-8')
image_directory = r"C:\Users\DELL\Desktop\CZQ\俄语"
image_directory = fix_non_ascii_path(image_directory)
folders = get_all_folders_in_directory(image_directory)
print("文件夹列表:", folders)
process_images_in_directory(image_directory, folders, lan_code)
|
