Hi Thanks a lot for the great post. I am trying to use cffi wrapper in my
project as the pytesseract was really slow.
I use opencv to read my image and I am trying to use your cffi setup and
initiate. But I the tesseract is not recognizing any text.
import ctypes
import os
import cffi
import cv2
tessdata = "/home/vagrant/reelz_base/shared/tessdata/"
ffi = cffi.FFI()
ffi.cdef("""
typedef signed char l_int8;
typedef unsigned char l_uint8;
typedef short l_int16;
typedef unsigned short l_uint16;
typedef int l_int32;
typedef unsigned int l_uint32;
typedef float l_float32;
typedef double l_float64;
typedef long long l_int64;
typedef unsigned long long l_uint64;
typedef int l_ok; /*!< return type 0 if OK, 1 on error */
typedef struct TessBaseAPI TessBaseAPI;
typedef struct ETEXT_DESC ETEXT_DESC;
typedef struct TessPageIterator TessPageIterator;
typedef struct TessResultIterator TessResultIterator;
typedef int BOOL;
typedef enum TessOcrEngineMode {
OEM_TESSERACT_ONLY = 0,
OEM_LSTM_ONLY = 1,
OEM_TESSERACT_LSTM_COMBINED = 2,
OEM_DEFAULT = 3} TessOcrEngineMode;
typedef enum TessPageSegMode {
PSM_OSD_ONLY = 0,
PSM_AUTO_OSD = 1,
PSM_AUTO_ONLY = 2,
PSM_AUTO = 3,
PSM_SINGLE_COLUMN = 4,
PSM_SINGLE_BLOCK_VERT_TEXT = 5,
PSM_SINGLE_BLOCK = 6,
PSM_SINGLE_LINE = 7,
PSM_SINGLE_WORD = 8,
PSM_CIRCLE_WORD = 9,
PSM_SINGLE_CHAR = 10,
PSM_SPARSE_TEXT = 11,
PSM_SPARSE_TEXT_OSD = 12,
PSM_COUNT = 13} TessPageSegMode;
typedef enum TessPageIteratorLevel {
RIL_BLOCK = 0,
RIL_PARA = 1,
RIL_TEXTLINE = 2,
RIL_WORD = 3,
RIL_SYMBOL = 4} TessPageIteratorLevel;
TessPageIterator* TessBaseAPIAnalyseLayout(TessBaseAPI* handle);
TessPageIterator* TessResultIteratorGetPageIterator(TessResultIterator*
handle);
BOOL TessPageIteratorNext(TessPageIterator* handle, TessPageIteratorLevel
level);
BOOL TessPageIteratorBoundingBox(const TessPageIterator* handle,
TessPageIteratorLevel level,
int* left, int* top, int* right, int*
bottom);
const char* TessVersion();
TessBaseAPI* TessBaseAPICreate();
void TessBaseAPIDelete(TessBaseAPI* handle);
size_t TessBaseAPIGetOpenCLDevice(TessBaseAPI* handle, void **device);
void TessBaseAPISetInputName( TessBaseAPI* handle, const char* name);
const char* TessBaseAPIGetInputName(TessBaseAPI* handle);
void TessBaseAPISetInputImage(TessBaseAPI* handle, struct Pix* pix);
int TessBaseAPIGetSourceYResolution(TessBaseAPI* handle);
BOOL TessBaseAPISetVariable(TessBaseAPI* handle, const char* name, const
char* value);
BOOL TessBaseAPISetDebugVariable(TessBaseAPI* handle, const char* name,
const char* value);
void TessBaseAPIPrintVariables( const TessBaseAPI* handle, FILE* fp);
BOOL TessBaseAPIPrintVariablesToFile(const TessBaseAPI* handle, const
char* filename);
int TessBaseAPIInit1(TessBaseAPI* handle, const char* datapath, const
char* language, TessOcrEngineMode oem,
char** configs, int configs_size);
int TessBaseAPIInit2(TessBaseAPI* handle, const char* datapath, const
char* language, TessOcrEngineMode oem);
int TessBaseAPIInit3(TessBaseAPI* handle, const char* datapath, const
char* language);
int TessBaseAPIInit4(TessBaseAPI* handle, const char* datapath, const char*
language, TessOcrEngineMode mode,
char** configs, int configs_size,
char** vars_vec, char** vars_values, size_t vars_vec_size,
BOOL set_only_non_debug_params);
void TessBaseAPISetImage(TessBaseAPI* handle, const unsigned char*
imagedata, int width, int height,
int bytes_per_pixel, int
bytes_per_line);
int TessBaseAPIRecognize(TessBaseAPI* handle, ETEXT_DESC* monitor);
TessResultIterator* TessBaseAPIGetIterator(TessBaseAPI* handle);
BOOL TessResultIteratorNext(TessResultIterator* handle,
TessPageIteratorLevel level);
char* TessResultIteratorGetUTF8Text(const TessResultIterator* handle,
TessPageIteratorLevel level);
float TessResultIteratorConfidence(const TessResultIterator* handle,
TessPageIteratorLevel level);
char* TessBaseAPIGetUTF8Text(TessBaseAPI* handle);
const char* TessResultIteratorWordFontAttributes(const TessResultIterator*
handle, BOOL* is_bold, BOOL* is_italic,
BOOL*
is_underlined, BOOL* is_monospace, BOOL* is_serif,
BOOL*
is_smallcaps, int* pointsize, int* font_id);
BOOL TessResultIteratorWordIsFromDictionary(const TessResultIterator*
handle);
BOOL TessResultIteratorWordIsNumeric(const TessResultIterator* handle);
BOOL TessResultIteratorSymbolIsSuperscript(const TessResultIterator*
handle);
BOOL TessResultIteratorSymbolIsSubscript(const TessResultIterator* handle);
BOOL TessResultIteratorSymbolIsDropcap(const TessResultIterator* handle);
void TessBaseAPIEnd(TessBaseAPI* handle);
""")
tess_libname = "/usr/local/lib/libtesseract.so.4"
if os.path.exists(tess_libname):
tesseract = ffi.dlopen(tess_libname)
api = None
tesseract_version = ffi.string(tesseract.TessVersion())
print('Tesseract-ocr version', tesseract_version.decode('utf-8'))
api = tesseract.TessBaseAPICreate()
c_ubyte_p = ctypes.POINTER(ctypes.c_ubyte)
lang="eng"
oem = tesseract.OEM_DEFAULT
tesseract.TessBaseAPIInit3(api, tessdata.encode(), lang.encode())
img = cv2.imread("/data/framecache/testing.jpg")
tesseract.TessBaseAPISetDebugVariable(api, "tesseract_char_whitelist",
"ABCDEFGHIJKLMNOPQRSTUVWXYZ")
tesseract.TessBaseAPISetDebugVariable(api, "tessedit_pageseg_mode", "8")
tesseract.TessBaseAPISetVariable(api, "image_default_resolution", "72")
tesseract.TessBaseAPISetImage(api, ffi.cast("unsigned char*",
img.ctypes.data), img.shape[0], img.shape[1], 1, img.shape[1])
# tesseract.TessBaseAPIRecognize(api, ffi.NULL)
utf8_text =
ffi.string(tesseract.TessBaseAPIGetUTF8Text(api)).decode('utf-8')
print utf8_text
On Sunday, March 24, 2019 at 10:10:36 AM UTC-7, zdenop wrote:
>
> Hi all,
>
> I publish my test / example how to use tesseract C-API in python3 via
> cffi[1].
>
> I am aware of pytesseract module, which seems to be widely used. It is
> wrapping tesseract executable, so IMO it could have some limitation e.g.
> from point of performance (it using disk operation for input and output).
>
> It is in form of jupyter notebook[3] (github is able to show it, but not
> run ;-)) so you can interactively view what is happening.
>
> My aim is not to create new tesseract python wrapper (I do not have a time
> for it, and I am not able to create nice python code as pytesseract has
> :-) ) so it is not robust: I just did it on windows 64 bit, but IMO is
> should be possible with small modification to use in Linux and Mac. If
> needed I can add 32bit windows libs...
>
> Personally I would like have python tesseract and leptonica module using
> directly its API... I know that James Barlow already started to wrapping
> leptonica, but it is (not yet?) available as independent module (it is part
> of OCRmyPDF).
>
> Anyway I hope this will help somebody.
>
> [1] https://github.com/zdenop/SimpleTesseractPythonWrapper
> [2] https://pypi.org/project/pytesseract/
> [3]
> https://github.com/zdenop/SimpleTesseractPythonWrapper/blob/master/SimpleTesseractPythonWrapper.ipynb
>
> [4] https://github.com/jbarlow83/OCRmyPDF/tree/master/src/ocrmypdf/lib
>
> Zdenko
>
--
You received this message because you are subscribed to the Google Groups
"tesseract-ocr" group.
To unsubscribe from this group and stop receiving emails from it, send an email
to tesseract-ocr+unsubscr...@googlegroups.com.
To post to this group, send email to tesseract-ocr@googlegroups.com.
Visit this group at https://groups.google.com/group/tesseract-ocr.
To view this discussion on the web visit
https://groups.google.com/d/msgid/tesseract-ocr/d6253a61-d796-4cce-8412-f2cc61e83000%40googlegroups.com.
For more options, visit https://groups.google.com/d/optout.
