Chiebot-Mirror
/
opencv_contrib
mirror of https://github.com/opencv/opencv_contrib.git
8
0
Fork 0
Code Issues Projects Releases Wiki Activity

moves implementation to cpp file and removes using directive from header file

Browse Source
pull/60/head
lluis 10 years ago
parent 3ab6308272
commit 493785a785
2 changed files with 102 additions and 96 deletions
Whitespace
Show all changes Ignore whitespace when comparing lines Ignore changes in amount of whitespace Ignore changes in whitespace at EOL
Split View
Diff Options
Show Stats Download Patch File Download Diff File
  1. 28
      modules/text/include/opencv2/text/ocr.hpp
  2. 170
      modules/text/src/ocr_tesseract.cpp

28
modules/text/include/opencv2/text/ocr.hpp
Unescape View File

@ -46,7 +46,6 @@
#include <vector>
#include <string>
using namespace std;
namespace cv
{
@ -65,29 +64,20 @@ class CV_EXPORTS BaseOCR
{
public:
virtual ~BaseOCR() {};
virtual void run(Mat& image, string& output_text, vector<Rect>* component_rects=NULL,
vector<string>* component_texts=NULL, vector<float>* component_confidences=NULL,
int component_level=0) = 0;
virtual void run(Mat& image, std::string& output_text, std::vector<Rect>* component_rects=NULL,
std::vector<std::string>* component_texts=NULL, std::vector<float>* component_confidences=NULL,
int component_level=0) = 0;
};
class CV_EXPORTS OCRTesseract : public BaseOCR
{
public:
virtual void run(Mat& image, string& output_text, vector<Rect>* component_rects=NULL,
vector<string>* component_texts=NULL, vector<float>* component_confidences=NULL,
int component_level=0)
{
CV_Assert( (image.type() == CV_8UC1) || (image.type() == CV_8UC1) );
CV_Assert( (component_level == OCR_LEVEL_TEXTLINE) || (component_level == OCR_LEVEL_WORD) );
output_text.clear();
if (component_rects != NULL)
component_rects->clear();
if (component_texts != NULL)
component_texts->clear();
if (component_confidences != NULL)
component_confidences->clear();
}
static Ptr<OCRTesseract> create(const char* datapath=NULL, const char* language=NULL, const char* char_whitelist=NULL, int oem=3, int psmode=3);
virtual void run(Mat& image, std::string& output_text, std::vector<Rect>* component_rects=NULL,
std::vector<std::string>* component_texts=NULL, std::vector<float>* component_confidences=NULL,
int component_level=0);
static Ptr<OCRTesseract> create(const char* datapath=NULL, const char* language=NULL,
const char* char_whitelist=NULL, int oem=3, int psmode=3);
};

170
modules/text/src/ocr_tesseract.cpp
Unescape View File

@ -47,13 +47,28 @@
#include <iostream>
#include <fstream>
#include <queue>
using namespace std;
namespace cv
{
namespace text
{
using namespace std;
void OCRTesseract::run(Mat& image, string& output_text, vector<Rect>* component_rects,
vector<string>* component_texts, vector<float>* component_confidences,
int component_level)
{
CV_Assert( (image.type() == CV_8UC1) || (image.type() == CV_8UC1) );
CV_Assert( (component_level == OCR_LEVEL_TEXTLINE) || (component_level == OCR_LEVEL_WORD) );
output_text.clear();
if (component_rects != NULL)
component_rects->clear();
if (component_texts != NULL)
component_texts->clear();
if (component_confidences != NULL)
component_confidences->clear();
}
class OCRTesseractImpl : public OCRTesseract
{
@ -68,42 +83,42 @@ public:
{
#ifdef HAVE_TESSERACT
const char *lang = "eng";
if (language != NULL)
lang = language;
if (tess.Init(datapath, lang, (tesseract::OcrEngineMode)oemode))
{
cout << "OCRTesseract: Could not initialize tesseract." << endl;
throw 1;
}
const char *lang = "eng";
if (language != NULL)
lang = language;
if (tess.Init(datapath, lang, (tesseract::OcrEngineMode)oemode))
{
cout << "OCRTesseract: Could not initialize tesseract." << endl;
throw 1;
}
//cout << "OCRTesseract: tesseract version " << tess.Version() << endl;
//cout << "OCRTesseract: tesseract version " << tess.Version() << endl;
tesseract::PageSegMode pagesegmode = (tesseract::PageSegMode)psmode;
tess.SetPageSegMode(pagesegmode);
tesseract::PageSegMode pagesegmode = (tesseract::PageSegMode)psmode;
tess.SetPageSegMode(pagesegmode);
if(char_whitelist != NULL)
tess.SetVariable("tessedit_char_whitelist", char_whitelist);
else
tess.SetVariable("tessedit_char_whitelist", "0123456789abcdefghijklmnopqrstuvwxyzABCDEFGHIJKLMNOPQRSTUVWXYZ");
if(char_whitelist != NULL)
tess.SetVariable("tessedit_char_whitelist", char_whitelist);
else
tess.SetVariable("tessedit_char_whitelist", "0123456789abcdefghijklmnopqrstuvwxyzABCDEFGHIJKLMNOPQRSTUVWXYZ");
tess.SetVariable("save_best_choices", "T");
tess.SetVariable("save_best_choices", "T");
#else
cout << "OCRTesseract("<<oemode<<psmode<<"): Tesseract not found." << endl;
if (datapath != NULL)
cout << " " << datapath << endl;
if (language != NULL)
cout << " " << language << endl;
if (char_whitelist != NULL)
cout << " " << char_whitelist << endl;
cout << "OCRTesseract("<<oemode<<psmode<<"): Tesseract not found." << endl;
if (datapath != NULL)
cout << " " << datapath << endl;
if (language != NULL)
cout << " " << language << endl;
if (char_whitelist != NULL)
cout << " " << char_whitelist << endl;
#endif
}
~OCRTesseractImpl()
{
#ifdef HAVE_TESSERACT
tess.End();
tess.End();
#endif
}
@ -111,72 +126,73 @@ public:
vector<string>* component_texts=NULL, vector<float>* component_confidences=NULL,
int component_level=0)
{
CV_Assert( (image.type() == CV_8UC1) || (image.type() == CV_8UC1) );
#ifdef HAVE_TESSERACT
if (component_texts != 0)
component_texts->clear();
if (component_rects != 0)
component_rects->clear();
if (component_confidences != 0)
component_confidences->clear();
CV_Assert( (image.type() == CV_8UC1) || (image.type() == CV_8UC1) );
tess.SetImage((uchar*)image.data, image.size().width, image.size().height, image.channels(), image.step1());
tess.Recognize(0);
output = string(tess.GetUTF8Text());
#ifdef HAVE_TESSERACT
if ( (component_rects != NULL) || (component_texts != NULL) || (component_confidences != NULL) )
{
tesseract::ResultIterator* ri = tess.GetIterator();
tesseract::PageIteratorLevel level = tesseract::RIL_WORD;
if (component_level == OCR_LEVEL_TEXTLINE)
level = tesseract::RIL_TEXTLINE;
if (ri != 0) {
do {
const char* word = ri->GetUTF8Text(level);
if (word == NULL)
continue;
float conf = ri->Confidence(level);
int x1, y1, x2, y2;
ri->BoundingBox(level, &x1, &y1, &x2, &y2);
if (component_texts != 0)
component_texts->push_back(string(word));
if (component_rects != 0)
component_rects->push_back(Rect(x1,y1,x2-x1,y2-y1));
if (component_confidences != 0)
component_confidences->push_back(conf);
delete[] word;
} while (ri->Next(level));
if (component_texts != 0)
component_texts->clear();
if (component_rects != 0)
component_rects->clear();
if (component_confidences != 0)
component_confidences->clear();
tess.SetImage((uchar*)image.data, image.size().width, image.size().height, image.channels(), image.step1());
tess.Recognize(0);
output = string(tess.GetUTF8Text());
if ( (component_rects != NULL) || (component_texts != NULL) || (component_confidences != NULL) )
{
tesseract::ResultIterator* ri = tess.GetIterator();
tesseract::PageIteratorLevel level = tesseract::RIL_WORD;
if (component_level == OCR_LEVEL_TEXTLINE)
level = tesseract::RIL_TEXTLINE;
if (ri != 0) {
do {
const char* word = ri->GetUTF8Text(level);
if (word == NULL)
continue;
float conf = ri->Confidence(level);
int x1, y1, x2, y2;
ri->BoundingBox(level, &x1, &y1, &x2, &y2);
if (component_texts != 0)
component_texts->push_back(string(word));
if (component_rects != 0)
component_rects->push_back(Rect(x1,y1,x2-x1,y2-y1));
if (component_confidences != 0)
component_confidences->push_back(conf);
delete[] word;
} while (ri->Next(level));
}
delete ri;
}
delete ri;
}
tess.Clear();
tess.Clear();
#else
cout << "OCRTesseract(" << component_level << image.type() <<"): Tesseract not found." << endl;
output.clear();
if(component_rects)
component_rects->clear();
if(component_texts)
component_texts->clear();
if(component_confidences)
component_confidences->clear();
cout << "OCRTesseract(" << component_level << image.type() <<"): Tesseract not found." << endl;
output.clear();
if(component_rects)
component_rects->clear();
if(component_texts)
component_texts->clear();
if(component_confidences)
component_confidences->clear();
#endif
}
};
Ptr<OCRTesseract> OCRTesseract::create(const char* datapath, const char* language, const char* char_whitelist, int oem, int psmode)
Ptr<OCRTesseract> OCRTesseract::create(const char* datapath, const char* language,
const char* char_whitelist, int oem, int psmode)
{
return makePtr<OCRTesseractImpl>(datapath,language,char_whitelist,oem,psmode);
return makePtr<OCRTesseractImpl>(datapath,language,char_whitelist,oem,psmode);
}

Write Preview
Loading…
Cancel
Save