Detect boxes on shelf Android OpenCV

edit

i suggest the following approach as a starting point

step 1. by using the code below you will get horizontal & vertical mean graphs of the image like:

step 2. by using vertical mean graph ( showed on the first image) you can easily get four ROI ( take a look at another question)

step 3. by applying step 1 for each ROI and using horizontal mean graph you can divide each box

try to implement this approach and if you get stuck on some point please ask.

UPDATE 1 see updated code which has result image like

this approach fails on misaligned pictures like below,

so it needs to an alignment process ( i will work on it )

---

UPDATE 2

you can keep following my further work on github

---

#include <opencv2/highgui.hpp>
#include <opencv2/imgproc.hpp>

using namespace cv;

int main( int argc, char** argv )
{
    Mat img = imread( argv[1] );
    if (img.empty())
        return -1;

    Mat resized,gray,reduced_h,reduced_w;
    resize( img, resized, Size(), 0.25, 0.25 );

    cvtColor( resized, gray, CV_BGR2GRAY );

    reduce( gray, reduced_h, 0, REDUCE_AVG );
    reduce( gray, reduced_w, 1, REDUCE_AVG );

    GaussianBlur( reduced_h, reduced_h, Size(),3);
    GaussianBlur( reduced_w, reduced_w, Size(),3);

    Mat reduced_h_graph = resized.clone();
    Mat reduced_w_graph = resized.clone();

    for ( int i = 0; i < img.cols; i++)
    {
        line( reduced_h_graph,Point(i,0),Point(i,reduced_h.at<uchar>(0,i)),Scalar(255,255,0),1);
    }

    for ( int i = 0; i < img.rows; i++)
    {
        line( reduced_w_graph,Point(0,i),Point(reduced_w.at<uchar>(i,0),i),Scalar(0,255,0),1);
    }

    imshow("reduced_h_graph", reduced_h_graph );
    imshow("reduced_w_graph", reduced_w_graph );
    waitKey(0);
    return 0;
}

UPDATE 1

#include <opencv2/highgui.hpp>
#include <opencv2/imgproc.hpp>

using namespace cv;
using namespace std;

vector<Rect> divideHW( Mat src, int dim, double threshold1, double threshold2 )
{
    Mat gray, reduced, canny;

    if( src.channels() == 1 )
    {
        gray = src;
    }

    if( src.channels() == 3 )
    {
        cvtColor( src, gray, CV_BGR2GRAY );
    }

    reduce( gray, reduced, dim, REDUCE_AVG );

    Canny( reduced, canny, threshold1, threshold2, 3, true );

    vector<Point> pts;
    findNonZero( canny, pts);

    vector<Rect> rects;

    Rect rect(0,0,gray.cols,gray.rows);
    int ref_x = 0;
    int ref_y = 0;

    for( size_t i=0; i< pts.size(); i++ )
    {
        if( dim )
        {
           rect.height = pts[i].y-ref_y;
           rects.push_back( rect );
           rect.y = pts[i].y;
           ref_y = rect.y;
           if( i == pts.size()-1 )
           {
             rect.height = gray.rows - pts[i].y;
             rects.push_back( rect );
           }
        }

        else
        {
           rect.width = pts[i].x-ref_x;
           rects.push_back( rect );
           rect.x = pts[i].x;
           ref_x = rect.x;
           if( i == pts.size()-1 )
           {
             rect.width = gray.cols - pts[i].x;
             rects.push_back( rect );
           }
        }

    }
    return rects;
}

int main( int argc, char** argv )
{
    Mat img = imread( argv[1] );
    if (img.empty())
        return -1;

    Mat resized;
    resize( img, resized, Size(), 0.25, 0.25 );

    vector<Rect> rois_h = divideHW( resized, 1, 0, 255 );

    for( size_t i=0; i< rois_h.size(); i++ )
    {
    Mat roi_h = resized( rois_h[i]);


        vector<Rect> rois_w = divideHW( roi_h, 0, 0, 255 );

    for( size_t j=0; j< rois_w.size(); j++ )
    {
    rois_w[j].y += rois_h[i].y;
    rectangle( resized, rois_w[j], Scalar( 0, 255, 0), 1 );
    rois_w[j].x = rois_w[j].x * 4;
    rois_w[j ...