質問編集履歴
1
追記
test
CHANGED
File without changes
|
test
CHANGED
@@ -91,3 +91,101 @@
|
|
91
91
|
print(txt)
|
92
92
|
|
93
93
|
```
|
94
|
+
|
95
|
+
###追記
|
96
|
+
|
97
|
+
環境変数「TESSDATA_PREFIX」を設定しようと試みましたが
|
98
|
+
|
99
|
+
改善の余地は見られませんでした。
|
100
|
+
|
101
|
+
以下ソースコード
|
102
|
+
|
103
|
+
```python
|
104
|
+
|
105
|
+
from PIL import Image
|
106
|
+
|
107
|
+
import sys
|
108
|
+
|
109
|
+
import os
|
110
|
+
|
111
|
+
import pyocr
|
112
|
+
|
113
|
+
import pyocr.builders
|
114
|
+
|
115
|
+
|
116
|
+
|
117
|
+
|
118
|
+
|
119
|
+
|
120
|
+
|
121
|
+
TESSERACT_PATH = 'C:\Program Files (x86)\Tesseract-OCR'
|
122
|
+
|
123
|
+
TESSDATA_PATH = 'C:\Program Files (x86)\Tesseract-OCR\tessdata'
|
124
|
+
|
125
|
+
|
126
|
+
|
127
|
+
os.environ["PATH"] += os.pathsep +TESSERACT_PATH
|
128
|
+
|
129
|
+
os.environ["TESSDATA_PREFIX"] = TESSDATA_PATH
|
130
|
+
|
131
|
+
|
132
|
+
|
133
|
+
tools = pyocr.get_available_tools()
|
134
|
+
|
135
|
+
if len(tools) == 0:
|
136
|
+
|
137
|
+
print("p")
|
138
|
+
|
139
|
+
tool = tools[0]
|
140
|
+
|
141
|
+
|
142
|
+
|
143
|
+
print(tool)
|
144
|
+
|
145
|
+
picture = Image.open("test1.png")
|
146
|
+
|
147
|
+
txt = tool.image_to_string(
|
148
|
+
|
149
|
+
picture,
|
150
|
+
|
151
|
+
lang="jpn",
|
152
|
+
|
153
|
+
builder = pyocr.builders.TextBuilder(tesseract_layout = 3)
|
154
|
+
|
155
|
+
)
|
156
|
+
|
157
|
+
print(txt)
|
158
|
+
|
159
|
+
|
160
|
+
|
161
|
+
```
|
162
|
+
|
163
|
+
以下エラー内容
|
164
|
+
|
165
|
+
```
|
166
|
+
|
167
|
+
<module 'pyocr.tesseract' from 'C:\Users\プライベート\AppData\Local\Packages\PythonSoftwareFoundation.Python.3.9_qbz5n2kfra8p0\LocalCache\local-packages\Python39\site-packages\pyocr\tesseract.py'>
|
168
|
+
|
169
|
+
|
170
|
+
|
171
|
+
Warning (from warnings module):
|
172
|
+
|
173
|
+
File "C:\Users\プライベート\AppData\Local\Packages\PythonSoftwareFoundation.Python.3.9_qbz5n2kfra8p0\LocalCache\local-packages\Python39\site-packages\PIL\Image.py", line 975
|
174
|
+
|
175
|
+
warnings.warn(
|
176
|
+
|
177
|
+
UserWarning: Palette images with Transparency expressed in bytes should be converted to RGBA images
|
178
|
+
|
179
|
+
Traceback (most recent call last):
|
180
|
+
|
181
|
+
File "C:\Users\プライベート\Desktop\python\test.py", line 23, in <module>
|
182
|
+
|
183
|
+
txt = tool.image_to_string(
|
184
|
+
|
185
|
+
File "C:\Users\プライベート\AppData\Local\Packages\PythonSoftwareFoundation.Python.3.9_qbz5n2kfra8p0\LocalCache\local-packages\Python39\site-packages\pyocr\tesseract.py", line 369, in image_to_string
|
186
|
+
|
187
|
+
raise TesseractError(status, errors)
|
188
|
+
|
189
|
+
pyocr.error.TesseractError: (1, b'Error opening data file C:\Program Files (x86)\Tesseract-OCR\tessdata/jpn.traineddata\r\nPlease make sure the TESSDATA_PREFIX environment variable is set to your "tessdata" directory.\r\nFailed loading language \'jpn\'\r\nTesseract couldn\'t load any languages!\r\nCould not initialize tesseract.\r\n')
|
190
|
+
|
191
|
+
```
|