CODEWITHSUNDEEP
c++opencv
user1179321
user1179321

Reputation: 801

Transforming an Image with OpenCV

I'm new to using OpenCV and i'm testing it out trying to grab a licence plate from a car. I'm stuck on how to go about doing that. For example i will start off with an image like this: enter image description here

and i want my final result to be something like:

enter image description here

I know how to use adaptivethreshold and things i'm confused at the steps need to go from 1 to 2. Thanks for the help!

Upvotes: 0

Views: 375

Answers (2)

ssb
ssb

Reputation: 7502

This is exactly what you want - https://github.com/MasteringOpenCV/code/tree/master/Chapter5_NumberPlateRecognition

Its from the Mastering OpenCV Book. It segments number plates as well as dopes rudimentary OCR to recognise characters.

Upvotes: 0

Zaw Lin
Zaw Lin

Reputation: 5708

too many hardcoded thresholds but will this work?

enter image description here

#include "opencv2/imgproc/imgproc.hpp"
#include "opencv2/highgui/highgui.hpp"
using namespace cv;

int main( int argc, char** argv )
{
    Mat src = imread( "C:/test/single/license.jpg");
    cvtColor(src,src,CV_BGR2GRAY);

    blur( src, src, Size(3,3) );
    Canny( src, src, 130, 130*4, 3 );
    imshow( "edge", src );

    GaussianBlur(src,src,Size(3,3),60);
    threshold(src,src,0,255,CV_THRESH_OTSU);

    vector<vector<Point> > contours;
    vector<Vec4i> hierarchy;
    findContours(src, contours, hierarchy, CV_RETR_EXTERNAL, CV_CHAIN_APPROX_SIMPLE);
    Mat todraw=Mat::zeros(src.size(), CV_8UC1);
    for(size_t i = 0; i < contours.size(); i++)
    {     
        double area = fabs(contourArea(Mat(contours[i])));
        if(area<600)
            drawContours(todraw,contours,i,Scalar(255),-1);
    }
    imshow( "plate", todraw );
    waitKey(0);
    return 0;
}

Upvotes: 1

Related Questions