Tesseract ResultIterator.cpp

// 參照 Tesseract API for VS2017

// 依據字符辨識，列出所有候選字

#include "pch.h"

#include <iostream>

#include <tesseract/baseapi.h>

#include <leptonica/allheaders.h>

int main()

{

Pix *image = pixRead("D:\\TensorFlow\\OCR\\aaa.png");

tesseract::TessBaseAPI *api = new tesseract::TessBaseAPI();

if (api->Init(NULL, "eng")) {

std::cerr << "Could not initialize tesseract.\n";

}

api->SetPageSegMode(tesseract::PSM_AUTO_OSD);

api->SetImage(image);

api->Recognize(0);

tesseract::ResultIterator* ri = api->GetIterator();

tesseract::PageIteratorLevel level = tesseract::RIL_SYMBOL;

//tesseract::PageIteratorLevel level = tesseract::RIL_TEXTLINE;

if (ri != 0) {

do {

const char* word = ri->GetUTF8Text(level);

float conf = ri->Confidence(level);

int x1, y1, x2, y2;

ri->BoundingBox(level, &x1, &y1, &x2, &y2);

printf("word: '%s';  \tconf: %.2f; BoundingBox: %d,%d,%d,%d;\n",

word, conf, x1, y1, x2, y2);

if (level = tesseract::RIL_SYMBOL) {

// 列出所有可能的候選字

tesseract::ChoiceIterator ci(*ri);

do {

const char* choice = ci.GetUTF8Text();

printf("\t\t%s conf: %f\n", choice, ci.Confidence());

} while (ci.Next());

printf("---------------------------------------------\n");

}

delete[] word;

} while (ri->Next(level));

}

api->End();

pixDestroy(&image);

}