默认restype is c_int，并且从整数的默认参数转换也是c_int。您会在网络上找到假设 32 位平台具有以下功能的示例：sizeof(int) == sizeof(void *)。这从来都不是一个好的假设。要保护 64 位指针在与 Python 整数相互转换时不被截断，请设置函数指针的argtypes and restype。无论如何，这样做是个好主意，因为它允许 ctypes 提出ArgumentError当使用错误的类型或数量的参数时。
如果您不想为每个函数定义原型，那么至少设置TessBaseAPICreate.restype到不透明的指针类型。
以下ctypes定义基于标头api/capi.h https://github.com/tesseract-ocr/tesseract/blob/3.02.02/api/capi.h。为了方便起见，我将 API 打包成Tesseract class.
import sys
import cv2
import ctypes
import ctypes.util
if sys.platform == 'win32':
LIBNAME = 'libtesseract302'
else:
LIBNAME = 'tesseract'
class TesseractError(Exception):
pass
class Tesseract(object):
_lib = None
_api = None
class TessBaseAPI(ctypes._Pointer):
_type_ = type('_TessBaseAPI', (ctypes.Structure,), {})
@classmethod
def setup_lib(cls, lib_path=None):
if cls._lib is not None:
return
if lib_path is None:
lib_path = ctypes.util.find_library(LIBNAME)
if lib_path is None:
raise TesseractError('tesseract library not found')
cls._lib = lib = ctypes.CDLL(lib_path)
# source:
# https://github.com/tesseract-ocr/tesseract/
# blob/3.02.02/api/capi.h
lib.TessBaseAPICreate.restype = cls.TessBaseAPI
lib.TessBaseAPIDelete.restype = None # void
lib.TessBaseAPIDelete.argtypes = (
cls.TessBaseAPI,) # handle
lib.TessBaseAPIInit3.argtypes = (
cls.TessBaseAPI, # handle
ctypes.c_char_p, # datapath
ctypes.c_char_p) # language
lib.TessBaseAPISetImage.restype = None
lib.TessBaseAPISetImage.argtypes = (
cls.TessBaseAPI, # handle
ctypes.c_void_p, # imagedata
ctypes.c_int, # width
ctypes.c_int, # height
ctypes.c_int, # bytes_per_pixel
ctypes.c_int) # bytes_per_line
lib.TessBaseAPIGetUTF8Text.restype = ctypes.c_char_p
lib.TessBaseAPIGetUTF8Text.argtypes = (
cls.TessBaseAPI,) # handle
def __init__(self, language='eng', datapath=None, lib_path=None):
if self._lib is None:
self.setup_lib(lib_path)
self._api = self._lib.TessBaseAPICreate()
if self._lib.TessBaseAPIInit3(self._api, datapath, language):
raise TesseractError('initialization failed')
def __del__(self):
if not self._lib or not self._api:
return
if not getattr(self, 'closed', False):
self._lib.TessBaseAPIDelete(self._api)
self.closed = True
def _check_setup(self):
if not self._lib:
raise TesseractError('lib not configured')
if not self._api:
raise TesseractError('api not created')
def set_image(self, imagedata, width, height,
bytes_per_pixel, bytes_per_line=None):
self._check_setup()
if bytes_per_line is None:
bytes_per_line = width * bytes_per_pixel
self._lib.TessBaseAPISetImage(self._api,
imagedata, width, height,
bytes_per_pixel, bytes_per_line)
def get_utf8_text(self):
self._check_setup()
return self._lib.TessBaseAPIGetUTF8Text(self._api)
def get_text(self):
self._check_setup()
result = self._lib.TessBaseAPIGetUTF8Text(self._api)
if result:
return result.decode('utf-8')
用法示例：
if __name__ == '__main__':
imcv = cv2.imread('ocrtest.png')
height, width, depth = imcv.shape
tess = Tesseract()
tess.set_image(imcv.ctypes, width, height, depth)
text = tess.get_text()
print text.strip()
我在 Linux 上使用 libtesseract.so.3 对此进行了测试。注意cv2.imread返回一个 NumPy 数组。这有一个ctypes属性包括_as_parameter_钩子，设置为c_void_p指向数组的指针。另请注意，问题中显示的代码已转换宽度和高度。本来应该是h, w, d = imcv.shape.
ocrtest.png：
Output:
I am trying to use Tesseract 3.02 with ctypes and cv2 in python. Tesseract
provides a DLL exposed set of C style APIs, one of them is as following:
