c++opencvimage-processingedge-detection
Robust card detection/persecutive correction OpenCV
I currently have a method for detecting a card in an image and for the most part it works when the lighting is fairly consistent and the background is very calm.
Here is the code I am using to preform this operation:
Mat img = inImg.clone();
outImg = Mat(inImg.size(), CV_8UC1);
inImg.copyTo(outImg);
Mat img_fullRes = img.clone();
pyrDown(img, img);
Mat imgGray;
cvtColor(img, imgGray, CV_RGB2GRAY);
outImg_gray = imgGray.clone();
// Find Edges //
Mat detectedEdges = imgGray.clone();
bilateralFilter(imgGray, detectedEdges, 0, 185, 3, 0);
Canny( detectedEdges, detectedEdges, 20, 65, 3 );
dilate(detectedEdges, detectedEdges, Mat::ones(3,3,CV_8UC1));
Mat cdst = img.clone();
vector<Vec4i> lines;
HoughLinesP(detectedEdges, lines, 1, CV_PI/180, 60, 50, 3 );
for( size_t i = 0; i < lines.size(); i++ )
{
Vec4i l = lines[i];
// For debug
//line( cdst, cv::Point(l[0], l[1]), cv::Point(l[2], l[3]), Scalar(0,0,255), 1);
}
//cdst.copyTo(inImg);
// // Find points of intersection //
cv::Rect imgROI;
int ext = 10;
imgROI.x = ext;
imgROI.y = ext;
imgROI.width = img.size().width - ext;
imgROI.height = img.size().height - ext;
int N = lines.size();
// Creating N amount of points // N == lines.size()
cv::Point** poi = new cv::Point*[N];
for( int i = 0; i < N; i++ )
poi[i] = new cv::Point[N];
vector<cv::Point> poiList;
for( int i = 0; i < N; i++ )
{
poi[i][i] = cv::Point(-1,-1);
Vec4i line1 = lines[i];
for( int j = i + 1; j < N; j++ )
{
Vec4i line2 = lines[j];
cv::Point p = computeIntersect(line1, line2, imgROI);
if( p.x != -1 )
{
//line(cdst, p-cv::Point(2,0), p+cv::Point(2,0), Scalar(0,255,0));
//line(cdst, p-cv::Point(0,2), p+cv::Point(0,2), Scalar(0,255,0));
poiList.push_back(p);
}
poi[i][j] = p;
poi[j][i] = p;
}
}
cdst.copyTo(inImg);
if(poiList.size()==0)
{
outImg = inImg.clone();
//circle(outImg, cv::Point(100,100), 50, Scalar(255,0,0), -1);
return;
}
convexHull(poiList, poiList, false, true);
for( int i=0; i<poiList.size(); i++ )
{
cv::Point p = poiList[i];
//circle(cdst, p, 3, Scalar(255,0,0), 2);
}
//Evaluate all possible quadrilaterals
cv::Point cardCorners[4];
float metric_max = 0;
int Npoi = poiList.size();
for( int p1=0; p1<Npoi; p1++ )
{
cv::Point pts[4];
pts[0] = poiList[p1];
for( int p2=p1+1; p2<Npoi; p2++ )
{
pts[1] = poiList[p2];
if( isCloseBy(pts[1],pts[0]) )
continue;
for( int p3=p2+1; p3<Npoi; p3++ )
{
pts[2] = poiList[p3];
if( isCloseBy(pts[2],pts[1]) || isCloseBy(pts[2],pts[0]) )
continue;
for( int p4=p3+1; p4<Npoi; p4++ )
{
pts[3] = poiList[p4];
if( isCloseBy(pts[3],pts[0]) || isCloseBy(pts[3],pts[1])
|| isCloseBy(pts[3],pts[2]) )
continue;
// get the metrics
float area = getArea(pts);
cv::Point a = pts[0]-pts[1];
cv::Point b = pts[1]-pts[2];
cv::Point c = pts[2]-pts[3];
cv::Point d = pts[3]-pts[0];
float oppLenDiff = abs(a.dot(a)-c.dot(c)) + abs(b.dot(b)-d.dot(d));
float metric = area - 0.35*oppLenDiff;
if( metric > metric_max )
{
metric_max = metric;
cardCorners[0] = pts[0];
cardCorners[1] = pts[1];
cardCorners[2] = pts[2];
cardCorners[3] = pts[3];
}
}
}
}
}
// find the corners corresponding to the 4 corners of the physical card
sortPointsClockwise(cardCorners);
// Calculate Homography //
vector<Point2f> srcPts(4);
srcPts[0] = cardCorners[0]*2;
srcPts[1] = cardCorners[1]*2;
srcPts[2] = cardCorners[2]*2;
srcPts[3] = cardCorners[3]*2;
vector<Point2f> dstPts(4);
cv::Size outImgSize(1400,800);
dstPts[0] = Point2f(0,0);
dstPts[1] = Point2f(outImgSize.width-1,0);
dstPts[2] = Point2f(outImgSize.width-1,outImgSize.height-1);
dstPts[3] = Point2f(0,outImgSize.height-1);
Mat Homography = findHomography(srcPts, dstPts);
// Apply Homography
warpPerspective( img_fullRes, outImg, Homography, outImgSize, INTER_CUBIC );
outImg.copyTo(inImg);
Where computeIntersect is defined as:
cv::Point computeIntersect(cv::Vec4i a, cv::Vec4i b, cv::Rect ROI)
{
int x1 = a[0], y1 = a[1], x2 = a[2], y2 = a[3];
int x3 = b[0], y3 = b[1], x4 = b[2], y4 = b[3];
cv::Point p1 = cv::Point (x1,y1);
cv::Point p2 = cv::Point (x2,y2);
cv::Point p3 = cv::Point (x3,y3);
cv::Point p4 = cv::Point (x4,y4);
// Check to make sure all points are within the image boundrys, if not reject them.
if( !ROI.contains(p1) || !ROI.contains(p2)
|| !ROI.contains(p3) || !ROI.contains(p4) )
return cv::Point (-1,-1);
cv::Point vec1 = p1-p2;
cv::Point vec2 = p3-p4;
float vec1_norm2 = vec1.x*vec1.x + vec1.y*vec1.y;
float vec2_norm2 = vec2.x*vec2.x + vec2.y*vec2.y;
float cosTheta = (vec1.dot(vec2))/sqrt(vec1_norm2*vec2_norm2);
float den = ((float)(x1-x2) * (y3-y4)) - ((y1-y2) * (x3-x4));
if(den != 0)
{
cv::Point2f pt;
pt.x = ((x1*y2 - y1*x2) * (x3-x4) - (x1-x2) * (x3*y4 - y3*x4)) / den;
pt.y = ((x1*y2 - y1*x2) * (y3-y4) - (y1-y2) * (x3*y4 - y3*x4)) / den;
if( !ROI.contains(pt) )
return cv::Point (-1,-1);
// no-confidence metric
float d1 = MIN( dist2(p1,pt), dist2(p2,pt) )/vec1_norm2;
float d2 = MIN( dist2(p3,pt), dist2(p4,pt) )/vec2_norm2;
float no_confidence_metric = MAX(sqrt(d1),sqrt(d2));
// If end point ratios are greater than .5 reject
if( no_confidence_metric < 0.5 && cosTheta < 0.707 )
return cv::Point (int(pt.x+0.5), int(pt.y+0.5));
}
return cv::Point(-1, -1);
}
sortPointsClockWise is defined as:
void sortPointsClockwise(cv::Point a[])
{
cv::Point b[4];
cv::Point ctr = (a[0]+a[1]+a[2]+a[3]);
ctr.x /= 4;
ctr.y /= 4;
b[0] = a[0]-ctr;
b[1] = a[1]-ctr;
b[2] = a[2]-ctr;
b[3] = a[3]-ctr;
for( int i=0; i<4; i++ )
{
if( b[i].x < 0 )
{
if( b[i].y < 0 )
a[0] = b[i]+ctr;
else
a[3] = b[i]+ctr;
}
else
{
if( b[i].y < 0 )
a[1] = b[i]+ctr;
else
a[2] = b[i]+ctr;
}
}
}
getArea is defined as:
float getArea(cv::Point arr[])
{
cv::Point diag1 = arr[0]-arr[2];
cv::Point diag2 = arr[1]-arr[3];
return 0.5*(diag1.cross(diag2));
}
isCloseBy is defined as:
bool isCloseBy( cv::Point p1, cv::Point p2 )
{
int D = 10;
// Checking that X values are within 10, same for Y values.
return ( abs(p1.x-p2.x)<=D && abs(p1.y-p2.y)<=D );
}
And finally dist2:
float dist2( cv::Point p1, cv::Point p2 )
{
return float((p1.x-p2.x)*(p1.x-p2.x) + (p1.y-p2.y)*(p1.y-p2.y));
}
Here are several test images and their results:
Sorry for the very lengthy post, however I am hoping someone can suggest a way I can make my method for extracting the card from the image more robust. One that can better handle disruptive backgrounds along with inconsistent lighting.
When a card is placed on a contrasting background with good lighting my method works nearly 90% of the time. But it is clear I need a more robust approach.
Does anyone have any suggestions?
Thanks.
ATTEMPT of dhanushka's soloution
Mat gray, bw; pyrDown(inImg, inImg);
cvtColor(inImg, gray, CV_RGB2GRAY);
int morph_size = 3;
Mat element = getStructuringElement( MORPH_ELLIPSE, cv::Size( 4*morph_size + 1, 2*morph_size+1 ), cv::Point( morph_size, morph_size ) );
morphologyEx(gray, gray, 2, element);
threshold(gray, bw, 160, 255, CV_THRESH_BINARY);
vector<vector<cv::Point> > contours;
vector<Vec4i> hierarchy;
findContours( bw, contours, hierarchy, CV_RETR_TREE, CV_CHAIN_APPROX_SIMPLE, cv::Point(0, 0) );
int largest_area=0;
int largest_contour_index=0;
cv::Rect bounding_rect;
for( int i = 0; i< contours.size(); i++ )
{
double a=contourArea( contours[i],false); // Find the area of contour
if(a>largest_area){
largest_area=a;
largest_contour_index=i; //Store the index of largest contour
bounding_rect=boundingRect(contours[i]);
}
}
//Scalar color( 255,255,255);
rectangle(inImg, bounding_rect, Scalar(0,255,0),1, 8,0);
Mat biggestRect = inImg(bounding_rect);
Mat card1 = biggestRect.clone();
Solution
A more general approach would definitely be something like Rutger Nijlunsing suggested in his answer. However, in your case, at least for the provided sample images, a very simple approach like morphological opening followed by thresholding, contour processing and convexhull would yield the result you want. Use a scaled down version of the images for processing so that you don't have to use a large kernel for morphological operations. Below are the images processed this way.
pyrDown(large, rgb0);
pyrDown(rgb0, rgb0);
pyrDown(rgb0, rgb0);
Mat small;
cvtColor(rgb0, small, CV_BGR2GRAY);
Mat morph;
Mat kernel = getStructuringElement(MORPH_ELLIPSE, Size(11, 11));
morphologyEx(small, morph, MORPH_OPEN, kernel);
Mat bw;
threshold(morph, bw, 0, 255.0, CV_THRESH_BINARY | CV_THRESH_OTSU);
Mat bdry;
kernel = getStructuringElement(MORPH_ELLIPSE, Size(3, 3));
erode(bw, bdry, kernel);
subtract(bw, bdry, bdry);
// do contour processing on bdry
This approach will not work in general, so I would strongly recommend something like Rutger suggested.
- C typedef name conflict
- How to use 32-bit pointers in 64-bit application?
- problems with scanf input stream
- Is it guaranteed to be safe to perform memcpy(0,0,0)?
- Need help understanding pointer to a type of n elements in C (int (*p)[10])?
- Local variables performance vs global in example
- How to Print SOAP Message Request Body generated using GSOAP when calling service
- Big Number Subtraction in C
- Docker custom program stop
- GTK4 Windows Multiple File Choosing
- Cannot get lldb to read file input through redirect
- Modeling nested lists in C
- Linker and Memory map for shared memory in autosar embedded environment
- Why is only the numerator cast to float to obtain a float quotient while dividing two integers?
- $gcc problemMatcher doesn't show all errors or warnings
- What registers to save in the ARM C calling convention?
- What does ** do in C language?
- How to install pywin32 module in windows 7
- How to differentiate a Cypher clause from an SQL clause in C?
- How do I check if my executable is running for a service or for a normal program?
- How to fix a simple error in Atmel studio
- Given day, month, year calculate day in year
- Definition of int64_t
- Can we have multiple c files to define functions for one header file?
- Check if array is ASCII
- What does C or GCC do when implicit function declaration exists
- How can I programmatically find the CPU frequency with C
- Can I use a binary literal in C or C++?
- Want to Convert Integer to String without itoa function
- How to permanently configure VSCode to use cl.exe without launching it from the Developer Command Prompt?