将 ctypes 与 tesserac-ocr 一起使用的例外 TessPageIteratorBoundingBox.

Exception on using ctypes with tesserac-ocr TessPageIteratorBoundingBox

本文关键字：TessPageIteratorBoundingBox ctypes tesserac-ocr 一起更新时间：2023-10-16

import ctypes
import os
os.putenv("PATH", r'C:Program FilesTesseract-OCR')
os.environ["TESSDATA_PREFIX"] = r'C:Program FilesTesseract-OCRtessdata'
liblept = ctypes.cdll.LoadLibrary('liblept-5.dll')
pix = liblept.pixRead('test.png'.encode())
print(pix)
tesseractLib = ctypes.cdll.LoadLibrary('libtesseract-5.dll')
tesseractHandle = tesseractLib.TessBaseAPICreate()
tesseractLib.TessBaseAPIInit3(tesseractHandle, '.', 'eng')
tesseractLib.TessBaseAPISetImage2(tesseractHandle, pix)
# text_out = tesseractLib.TessBaseAPIGetUTF8Text(tesseractHandle)
# print(ctypes.string_at(text_out))
tessPageIterator = tesseractLib.TessResultIteratorGetPageIterator(tesseractHandle)
iteratorLevel = 3  # RIL_BLOCK,  RIL_PARA,  RIL_TEXTLINE,  RIL_WORD,  RIL_SYMBOL
tesseractLib.TessPageIteratorBoundingBox(tessPageIterator, iteratorLevel, ctypes.c_int(0), ctypes.c_int(0), ctypes.c_int(0), ctypes.c_int(0))

我有例外：

Traceback (most recent call last):
File "D:BaiduYunDownloadprogrammingPythonCtypesOCR.py", line 25, in <module>
tesseractLib.TessPageIteratorBoundingBox(tessPageIterator, iteratorLevel, ctypes.c_int(0), ctypes.c_int(0), ctypes.c_int(0), ctypes.c_int(0))
OSError: exception: access violation reading 0x00000018

那么怎么了呢？该程序的目的是获取每个单词的边框。我知道像tesserocr和PyOCR这样的项目

。附言：为 DLL 函数指定所需的参数类型(函数原型(在这里无关紧要。人们可以取消注释的行并注释最后三行以对其进行测试。我之前发布了这个问题，但由于这个原因它被关闭了

我自己解决了我的问题

import ctypes
import os
import io
os.putenv("PATH", r'C:Program FilesTesseract-OCR')
os.environ["TESSDATA_PREFIX"] = r'C:Program FilesTesseract-OCRtessdata'
liblept = ctypes.cdll.LoadLibrary('liblept-5.dll')
pix = liblept.pixRead(b'test.png')  # 必须encode
print(pix)
tesseractLib = ctypes.cdll.LoadLibrary('libtesseract-5.dll')
tesseractHandle = tesseractLib.TessBaseAPICreate()
tesseractLib.TessBaseAPIInit3(tesseractHandle, b'.', b'eng')  # (TessBaseAPI* handle, const char* datapath,const char* language);
# from PIL import Image
# pixmap = Image.open("test.png")
# image = io.BytesIO()
# pixmap.save(image, 'png')  # 没有什么类型，这里就任意指定个吧；For images created by the library itself (via a factory function, or by running a method on an existing image), this attribute is set to None.
# image.seek(0)  # 要回到开始才行，不然后面requests读的时候会从结尾读，读不到数据
tesseractLib.TessBaseAPISetImage2(tesseractHandle, pix)  # pixmap.tobytes("raw", "RGB")
# text_out = tesseractLib.TessBaseAPIGetUTF8Text(tesseractHandle)
# print(ctypes.string_at(text_out))
tesseractLib.TessBaseAPIRecognize(tesseractHandle, None)  # 必须有，否则下面会出问题
tessResultIterator = tesseractLib.TessBaseAPIGetIterator(tesseractHandle)  # TessResultIteratorGetPageIterator要用
tessPageIterator = tesseractLib.TessResultIteratorGetPageIterator(tessResultIterator)
wordLevel = 3  # RIL_BLOCK,  RIL_PARA,  RIL_TEXTLINE,  RIL_WORD,  RIL_SYMBOL

left = ctypes.c_int(0)  # 这几个是要用来写入数据的，所以要构造出来 可写；byref() argument must be a ctypes instance, not 'int'
top = ctypes.c_int(0)
right = ctypes.c_int(0)
bottom = ctypes.c_int(0)
while True:
r = tesseractLib.TessPageIteratorBoundingBox(
tessPageIterator,
wordLevel,
ctypes.byref(left),  # byref behaves similar to pointer(obj), but the construction is a lot faster.
ctypes.byref(top),
ctypes.byref(right),
ctypes.byref(bottom)
)
text_out = tesseractLib.TessResultIteratorGetUTF8Text(tessPageIterator, wordLevel)
print(ctypes.string_at(text_out), left.value, top.value, right.value, bottom.value)
if not tesseractLib.TessPageIteratorNext(tessPageIterator, wordLevel):
break

没有找到相关文章