akoo's profile - activity

Yeah pyro, I've realized this solution gives me some false positives. I guess I would do any other thing to avoid these false positives. And how can I pass the bounding boxes to the function for computing the histogram, because they are not Mat, as you can see in the code. Thanks

I'm trying to use an OCR to recognize these characters from inside the license plate that is the reason I want to select only the bounding box containing characters, to run after an OCR engine. Anyway I think I've found one way to select it. It has worked with some pictures, not only this. I have calculated the aspect ratio of a bounding boxes, and if it is between 3 and 6 then is a possible license plate. Thanks pyro.

Hi everybody, I'm doing a program to obtain bounding boxes and once obtained these bounding boxes I would like to select only one of these. Is there any way to select only the desired bounding box. For example, in the attached picture, I would like to select only the bounding box where is a license plate inside, but I don't know how can I do that. Any help? Thanks in advance.

Mat findBox(Mat imagen){

//blur(imagen,imagen,Size(3,3));
Mat threshold_output;
vector<vector<Point> > contours;
vector<Vec4i> hierarchy;

/// Detect edges using Threshold
threshold( imagen, threshold_output, 140, 255, THRESH_BINARY );
/// Find contours
findContours( threshold_output, contours, hierarchy, CV_RETR_TREE, CV_CHAIN_APPROX_SIMPLE, Point(0, 0) );

/// Approximate contours to polygons + get bounding rects and circles
vector<vector<Point> > contours_poly( contours.size() );
vector<Rect> boundRect( contours.size() );
vector<Point2f>center( contours.size() );
vector<float>radius( contours.size() );

for( uint i = 0; i < contours.size(); i++ ){
    approxPolyDP( Mat(contours[i]), contours_poly[i], 3, true );
    boundRect[i] = boundingRect( Mat(contours_poly[i]) );
    minEnclosingCircle( (Mat)contours_poly[i], center[i], radius[i] );
}
/// Draw polygonal contour + bonding rects
Mat drawing = Mat::zeros( threshold_output.size(), CV_8UC3 );
cvtColor(imagen,imagen,CV_GRAY2BGR);
Scalar colorRed( 0,0,255);
Scalar colorWhite( 255,255,255);
Point inici;Point fin;
//Point un, dos;
float ratio;

for( uint i = 0; i< contours.size(); i++ ){

    double area=contourArea(contours[i]); //calculamos area de contornos
    cout<<area<<endl;
    /*si mayor que 1000 tengo la placa matricula
     * si mayor que 200 los caracteres y calculamos el aspect ratio */
    if( area >= 1000 ){
        if(area <= 8000){


            //Point uno(boundRect[i].x,boundRect[i].y);
            //inici=uno;
            //cout<<"Bound:"<<boundRect[i].br()<<" "<<inici.y<<endl;
            drawContours( drawing, contours_poly, i, colorWhite, 1, 8, vector<Vec4i>(), 0, Point() );
            //rectangle( imagen, boundRect[i].tl(), boundRect[i].br(), colorRed, 1, 8, 0 );
            //Point dos(boundRect[i].br());
            //fin=dos;

            ratio = boundRect[i].width/boundRect[i].height;
            if(ratio >= 3){
                if(ratio <= 6){
                    cout<<"ratio:"<<ratio<<endl;
                    rectangle( imagen, boundRect[i].tl(), boundRect[i].br(), colorRed, 1, 8, 0 );

                    Point p1(boundRect[i].x,boundRect[i].y);
                    Point p2(boundRect[i].br());
                    inici=p1;
                    fin=p2;
                }
            }
        }
    }

}

imshow("Image",imagen);
return drawing;

}

Hi all, I'm doing a project where i obtain contours of an image and draw the rectangle of minimum area which contains that contours. Now I would like to draw only some rectangles, I would like to avoid rectangles with small area for having a better detection, but I don't know how to draw only the greater rectangles obtained. As you can see in the attached image I would like to draw only the rectangles that contain some character. Some help would be appreciated. Thanks in advance.

I attach the code I have for finding contours and draw the rectangles, as well as the image obtained.

Mat encuentraRect(Mat imagen){

blur(imagen,imagen,Size(3,3));

Mat threshold_output;

vector<vector<Point> > contours;

vector<Vec4i> hierarchy;

/// Detect edges using Threshold
threshold( imagen, threshold_output, 100, 255, THRESH_BINARY );
/// Find contours
findContours( threshold_output, contours, hierarchy, CV_RETR_TREE, CV_CHAIN_APPROX_SIMPLE, Point(0, 0) );

/// Find the rotated rectangles for each contour
vector<RotatedRect> minRect( contours.size() );

for( uint i = 0; i < contours.size(); i++ ){
    minRect[i] = minAreaRect( Mat(contours[i]) );

}

/// Draw contours + rotated rects
Mat drawing = Mat::zeros( threshold_output.size(), CV_8UC3 );
for( uint i = 0; i< contours.size(); i++ ){
    Scalar red(0,0,255) ;
    Scalar white(255,255,255);
    // contour
    drawContours( drawing, contours, i, white, 1, 8, vector<Vec4i>(), 0, Point() );

    // rotated rectangle
    Point2f rect_points[4];
    minRect[i].points( rect_points );
    float angle;

    for( int j = 0; j < 4; j++ ){
        line(region , rect_points[j], rect_points[(j+1)%4], red, 1, 8 );

    }
}
imwrite("/home/adrian/workspace/OCR_2/resultados/rectangulos.png",region);
return region;
//imshow("contornos",drawing);

}

Hi 123ezone, I am doing a license plate recognition using an OCR too and at this moment I'd like to use horizontal projection. Could you tell me please how have you done it?

Thanks

Hi all, I am trying to write a software to recognize some text from an image, but when I binarize the image and I call to tesseract engine, this does not recognize text in image. Does somebody know why text it is not recognized? Must I do something extra to recognize? I leave the image I am trying to recognize text. tesseract output is: "24"

I've also tried with another image like this:

And the output is also wrong. Output: "L I"

Could anybody help me?

Thanks in advance.

I know cuenta is not the same value now, I have changed that just after post the code here.

Thank you berak! It works fine!

Hello everybody,

I've got a code where I show a video from a camera, but now I want to take a snapshot when a key is pressed, but I don't know exactly what function I need to use and how. Could anyone help me please?

Thanks. I post my code.

int main( ) {

  VideoCapture vcap;
  const std::string VideoStreamAddress ="rtsp://192.168.1.10/MediaInput/mpeg4";

  if (!vcap.open(VideoStreamAddress)) {
    std::cout << "Error abriendo stream de video o archivo" << std::endl;
    return 0;
  }
  while (true) {
            if (!vcap.read(image)) {
            std::cout << "No frame" << std::endl;
            cv::waitKey();
            }
            imshow("original", image);

            if (waitKey(1) >= 0){
                            //TAKE A PHOTO
            TakePhoto();
              }
    }
     return 0;

}

Hi again, The code to take snapshots it works fine, I can take a photo when a key is pressed, but now I'm trying to recognize text in that photo using tesseract engine and I'm having an error like this:

Error: Illegal min or max specification! signal_termination_handler:Error:Signal_termination_handler called:Code 5002

I've only just added the code for text recognition within the waitkey if as follows:

if (waitKey(10) >= 0){

            imwrite( format("foto_%3d.png",cuenta++), image); //take snapshot when key is pressed

            // initilize tesseract OCR engine
                 tesseract::TessBaseAPI *myOCR = new tesseract::TessBaseAPI();

                 if (myOCR->Init(NULL, "spa")) {
                          fprintf( stderr, " Could not intialize tesseract.\n" );
                          exit(1);
                 }

                // read image
                  namedWindow("tesseract-opencv", 0);
                  Mat imagen = imread(format("/home/adrian/workspace/foto_%3d.png",cuenta), 0);

                // set region of interest (ROI), i.e. regions that contain text
                  Rect text1ROI(162, 110, 157 , 129);

                // recognize text
                   myOCR->TesseractRect( imagen.data, 1, imagen.step1(), text1ROI.x, text1ROI.y, text1ROI.width, text1ROI.height);
                   const char *text1 = myOCR->GetUTF8Text();

                // remove "newline"
                   string t1(text1);
                   t1.erase( std::remove(t1.begin(), t1.end(), '\n'), t1.end() );

                // print found text
                   printf("text: \n");
                   printf( "%s",t1.c_str() );
                   printf("\n");
        }

Any idea of that error????

Thanks

What are the leptonica libs?? Could you tell me what libraries I need to add?

Hi everybody!, I am trying to link the tesseract libraries to Eclipse but I do not how to do it. I have downloaded and installed tesseract via command console. Then I have configured opencv to use it in Eclipse, but I do not know how to link tesseract to use it. Could anyone help me? What I have to do?

Thanks in advance! I post an image of errors I have.

I think I should add the libraries to the project properties, but I don't know what are the libraries.