hans

sudo apt-get install libicu-dev
sudo apt-get install libpango1.0-dev
sudo apt-get install libcairo2-dev

#include <tesseract/baseapi.h>
#include <leptonica/allheaders.h>
#include <opencv2/core/core.hpp>
#include <opencv2/imgproc/imgproc.hpp>
#include <opencv2/highgui/highgui.hpp>


int main()
{
    char *outText;

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

    //設置識別引擎,如果要用cube引擎，需要去上面下載cube對應的預訓練模型。
    tesseract::OcrEngineMode enginemode = static_cast
  
   (0);
	/*
	"OCR Engine modes:"
	"  0    Original Tesseract only."
	"  1    Cube only."
	"  2    Tesseract + cube."
	"  3    Default, based on what is available."
           4   Neural nets (LSTM) only.（版本4.0才有）
	*/

    // 初始化，NULL可以替換成你存放預訓練模型的路徑。下面"eng"可以是"eng++chi_sim"形式。
    if (api->Init(NULL, "eng", enginemode)) 
    {
        fprintf(stderr, "Could not initialize tesseract.\n");
        exit(1);
    }
    //下面兩句話都是設置只識別數字，第一種方法是打開識別開關，第二種方法是只識別白名單內字符。當然還有黑名單。具體看下面我給的API地址。
    //api->SetVariable("classify_bln_numeric_mode", "1");
    //api->SetVariable("tessedit_char_whitelist", "0123456789");

    //設置識別頁面類型
    tesseract::PageSegMode pagesegmode = static_cast
   
    (7);
    api->SetPageSegMode(pagesegmode);
    /*
    "Page segmentation modes:"
    "  0    Orientation and script detection (OSD) only."
    "  1    Automatic page segmentation with OSD."
    "  2    Automatic page segmentation, but no OSD, or OCR."
    "  3    Fully automatic page segmentation, but no OSD. (Default)"
    "  4    Assume a single column of text of variable sizes."
    "  5    Assume a single uniform block of vertically aligned text."
    "  6    Assume a single uniform block of text."
    "  7    Treat the image as a single text line."
    "  8    Treat the image as a single word."
    "  9    Treat the image as a single word in a circle."
    " 10    Treat the image as a single character."
    " 11    Sparse text. Find as much text as possible in no particular order."
    " 12    Sparse text with OSD."
    " 13    Raw line. Treat the image as a single text line,"
    */


    // Open input image with leptonica library
    Pix *image = pixRead("/usr/src/tesseract/testing/phototest.tif");
    api->SetImage(image);

    //下面是通過opencv讀取圖片
    //cv::Mat gray_img, thres_img;
    //cv::Mat img = cv::imread("");
    //cv::cvtColor(img, gray_img, cv::COLOR_BGR2GRAY);
    //cv::threshold(gray_img, thres_img, 127., 255., cv::THRESH_BINARY);
    //api->SetImage((uchar*)thres_img.data, thres_img.cols, thres_img.rows, 1, thres_img.cols);


    // Get OCR result
    outText = api->GetUTF8Text();
    printf("OCR output:\n%s", outText);

    // Destroy used object and release memory
    api->End();
    delete [] outText;
    pixDestroy(&image);

    return 0;
}