Revision history [back]

I am starting with the following image

and I am identifying the horizontal lines in order to find the form fields. I am using the following code

Mat src=imread(filename);

if(!src.data)
    cerr<<"problem loading image"<<endl;

Mat rsz;

Size size(800,900);

resize(src, rsz, size);

Mat gray;

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

Mat bw;
adaptiveThreshold(~gray, bw, 255,CV_ADAPTIVE_THRESH_MEAN_C,THRESH_BINARY, 15,-2);

Mat horizontal = bw.clone();
Mat vertical =bw.clone();

int scale = 25;

int horizontalsize = horizontal.cols/scale;

Mat horizontalStructure = getStructuringElement(MORPH_RECT,Size(horizontalsize,1));

erode(horizontal, horizontal, horizontalStructure, Point(-1, -1));
dilate(horizontal, horizontal, horizontalStructure, Point(-1, -1));

vector<Vec4i> hierarchy;
vector<vector<Point> > contours;

findContours(horizontal, contours, hierarchy, CV_RETR_EXTERNAL,CV_CHAIN_APPROX_SIMPLE, Point(0, 0));

vector<vector<Point> > contours_poly( contours.size() );
vector<Rect> boundRect( contours.size() );
vector<Mat> rois;

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

    approxPolyDP( Mat(contours[i]), contours_poly[i], 3,true );
    boundRect[i] = boundingRect( Mat(contours_poly[i]) );

    rois.push_back(rsz(boundRect[i]).clone());
    rectangle( rsz, boundRect[i].tl(), boundRect[i].br(),Scalar(0, 255, 0), 1, 8, 0 );
}

which gives me

which seems to work almost perfectly except it finds the line in the www.labor.ny.gov link in the top right. I don't want this line to be found. So somehow I have to filter the bounding rectangles based on whether they have empty space above them (the link obviously would not pass this filter). Does anyone know how I can implement this filter? From the code you can see that I have the bounding rectangle objects which contain their position, so I think I just need to check if some small bounding rectangle above it is empty.