How to count the number of pixels in each circle in OpenCV? - c++

I currently have a source image of: Source image
And I have made a bounding rects for each as an ROI: Rects
My goal is to find the number of red pixels inside each rect. However, I do not know how to proceed.
I have used the area (30*30) and countNonZero for finding the number of pixels for each circle by individually manually cropping and saving as a separate image. However I want to implement it in the whole image where I could just iterate through the bounding rects.
Edit: If it will help, this is the code that I use to get the bounding rects.
for (int i = 0; i < contours.size(); i++)
{
approxPolyDP(Mat(contours[i]), contours_poly[i], 0.1, true);
//Get the width and heights of the bounding rectangles
int w = boundingRect(Mat(contours[i])).width;
int h = boundingRect(Mat(contours[i])).height;
//Apply aspect ratio for filtering rects (optional)
double ar = (double)w / h;
//Apply a bounding Rects/Circles
//Rect/contour filter optional
if (hierarchy[i][3] == -1) //No parent
if ((w >= 28 && w <= 32) && (h >= 28 && h <= 32) && ar < 1.1 && ar > 0.9) {
//Apply a bounding Rects/Circles
boundRect[i] = boundingRect(Mat(contours_poly[i]));
minEnclosingCircle((Mat)contours_poly[i], center[i], radius[i]);
//Add to a new
filtered_contours.push_back(contours_poly[i]);
std::cout << i << " w: " << w << " h: " << h << std::endl;
}
}

Maybe, this helps you.
// Load image.
cv::Mat circles = cv::imread("circles.jpg", cv::IMREAD_GRAYSCALE);
// Use simple threshold to get rid of compression artifacts.
cv::Mat circlesThr;
cv::threshold(circles, circlesThr, 128, 255, cv::THRESH_BINARY_INV);
// Find contours in binary image (cv::RETR_EXTERNAL -> only most outer contours).
std::vector<std::vector<cv::Point>> contours;
std::vector<cv::Vec4i> hierarchy;
cv::findContours(circlesThr, contours, hierarchy, cv::RETR_EXTERNAL, cv::CHAIN_APPROX_NONE);
// Iterate all contours...
// Iterate all contours...
for (std::vector<cv::Point>& contour : contours)
{
// Determine bounding rectangle of contour.
cv::Rect rect = cv::boundingRect(contour);
// Count non-zero pixels within bounding rect.
std::string count = std::to_string(cv::countNonZero(circlesThr(rect)));
// Output text to image.
cv::putText(circlesThr, count, cv::Point(rect.x - 5, rect.y - 5), cv::FONT_HERSHEY_SIMPLEX, 0.5, cv::Scalar(255));
}
// Save output image.
cv::imwrite("output.jpg", circlesThr);
Results in:

Related

Detect the coin and from there measure the leaf in the image

Friends, I am trying to detect the coin first, since I already know its size is 1.011cm2. And then measure the leaves in the image.
I am using findContours, but I am not always able to distinguish the currency first, I have also tried to use hougCircles but it is not working in my case. Would anyone have any ideas?
OpenCv 4.5.0 C++
My code
//variables for segmentation image
cv::Mat imagem_original, imagem_gray, imagem_binaria, imagem_inRange, imagem_threshold, dst, src;
vector<Vec3f> circles;
cv::Scalar min_color = Scalar(50, 50, 50);
cv::Scalar max_color = Scalar(90, 120, 180);
imagem_original = load_image("IMG_1845.jpg");
//imshow("Imagem Original", imagem_original);
cv::cvtColor(imagem_original, imagem_gray, COLOR_BGR2GRAY);
//imshow("imagem_gray", imagem_gray);
//cv::inRange(imagem_gray, min_color, max_color, imagem_inRange);
cv::threshold(imagem_gray, imagem_threshold, 0, 255, THRESH_BINARY_INV | THRESH_OTSU);
imshow(" Threshold", imagem_threshold);
// find outer-contours in the image these should be the circles!
cv::Mat conts = imagem_threshold.clone();
std::vector<std::vector<cv::Point> > contours;
std::vector<cv::Vec4i> hierarchy;
cv::findContours(conts, contours, hierarchy, RETR_EXTERNAL, CHAIN_APPROX_SIMPLE, cv::Point(0, 0));
int total_IAF = 0;
cout << "\n\n";
cout << contours.size() << "\n\n";
for (int i = 0; i < contours.size(); i++) {
int area = contourArea(contours[i]);
if (area <= 10) {
cv::drawContours(imagem_original, contours, i, Scalar(0, 0, 255));
}
else {
cout << area << "\n";
cv::drawContours(imagem_original, contours, i, Scalar(255, 0, 0));
}
if (area > 5000) {
total_IAF += contourArea(contours[i]);
}
}
imshow(" ORIGINAL ", imagem_original);
double iAF_cm2 = total_IAF / 4658;
cout << "\n\n TOTAL AREA IAF: " << total_IAF;
cout << "\n IAF em cm2: " << iAF_cm2 << " cm2\n\n";
If your setup has constant white-ish/gray-ish background and green leaves, I'd use the HSV color space to detect all objects using the S channel (the green leaves and the golden part of the coin will have significantly more saturation than the background) and then distinguish between the coin and the leaves using the H channel (the green leaves will have hue values around 45). The remainder is to determine the image areas of all contours, and set the coin's image area as some kind of reference area to calculate the object areas w.r.t. the coin's object area of 1.011.
That's the saturation channel of the given image:
The saturation channel thresholded at 64:
That's the hue channel of the image:
Here's some code executing the above idea:
int main()
{
// Read image
cv::Mat img = cv::imread("Wcj1R.jpg", cv::IMREAD_COLOR);
// Convert image to HSV color space, and split H, S, V channels
cv::Mat img_hsv;
cv::cvtColor(img, img_hsv, cv::COLOR_BGR2HSV);
std::vector<cv::Mat> hsv;
cv::split(img_hsv, hsv);
// Binary threshold S channel at fixed threshold
cv::Mat img_thr;
cv::threshold(hsv[1], img_thr, 64, 255, cv::THRESH_BINARY);
// Find most outer contours only
std::vector<std::vector<cv::Point>> cnts;
std::vector<cv::Vec4i> hier;
cv::findContours(img_thr.clone(), cnts, hier, cv::RETR_EXTERNAL, cv::CHAIN_APPROX_NONE);
// Iterate found contours
std::vector<cv::Point> cnt_centers;
std::vector<double> cnt_areas;
double ref_area = -1;
for (int i = 0; i < cnts.size(); i++)
{
// Current contour
std::vector<cv::Point> cnt = cnts[i];
// If contour is too small, discard
if (cnt.size() < 100)
continue;
// Calculate and store center (just for visualization) and area of contour
cv::Moments m = cv::moments(cnt);
cnt_centers.push_back(cv::Point(m.m10 / m.m00 - 30, m.m01 / m.m00));
cnt_areas.push_back(cv::contourArea(cnt));
// Check H channel, whether the contour's image parts are mostly green
cv::Mat mask = hsv[0].clone().setTo(cv::Scalar(0));
cv::drawContours(mask, cnts, i, cv::Scalar(255), cv::FILLED);
double h_mean = cv::mean(hsv[0], mask)[0];
// If it's not mostly green, that's the coin, thus the reference area
if (h_mean < 40 || h_mean > 50)
ref_area = cv::contourArea(cnt);
}
// Iterate all contours again
for (int i = 0; i < cnt_centers.size(); i++)
{
// Calculate actual object area
double area = cnt_areas[i] / ref_area * 1.011;
// Put area on image w.r.t. the contour's center
cv::putText(img, std::to_string(area), cnt_centers[i], cv::FONT_HERSHEY_COMPLEX_SMALL, 1, cv::Scalar(255, 255, 255));
}
return 0;
}
And, that'd be the output:
Your code finds all contours in a image and shows them. So I'm confused about the meaning of "detect the coin first".
If you want to draw the contour of the coin first, sort contours vector by size. The coin is the smallest object so it would be the first element of the vector after sorting.(Of course, some unwanted contours should removed before sorting.)

OpenCV Finding square center c++

To begin, I am a complete novice in OpenCV and am beginner/reasonable in c++ code.
But OpenCV is new to me and I try to learn by doing projects and stuff.
Now for my new project I am trying to find the centre of square in a picture.
In my case there is only 1 square in picture.
I would like to build further upon the square.cpp example of OpenCV.
For my project there are 2 things I need some help with,
1: The edge of the window is detected as a square, I do not want this. Example
2: How could I get the centre of 1 square from the squares array?
This is the code from the example "square.cpp"
// The "Square Detector" program.
// It loads several images sequentially and tries to find squares in
// each image
#include "opencv2/core.hpp"
#include "opencv2/imgproc.hpp"
#include "opencv2/imgcodecs.hpp"
#include "opencv2/highgui.hpp"
#include <iostream>
using namespace cv;
using namespace std;
static void help(const char* programName)
{
cout <<
"\nA program using pyramid scaling, Canny, contours and contour simplification\n"
"to find squares in a list of images (pic1-6.png)\n"
"Returns sequence of squares detected on the image.\n"
"Call:\n"
"./" << programName << " [file_name (optional)]\n"
"Using OpenCV version " << CV_VERSION << "\n" << endl;
}
int thresh = 50, N = 11;
const char* wndname = "Square Detection Demo";
// helper function:
// finds a cosine of angle between vectors
// from pt0->pt1 and from pt0->pt2
static double angle(Point pt1, Point pt2, Point pt0)
{
double dx1 = pt1.x - pt0.x;
double dy1 = pt1.y - pt0.y;
double dx2 = pt2.x - pt0.x;
double dy2 = pt2.y - pt0.y;
return (dx1 * dx2 + dy1 * dy2) / sqrt((dx1 * dx1 + dy1 * dy1) * (dx2 * dx2 + dy2 * dy2) + 1e-10);
}
// returns sequence of squares detected on the image.
static void findSquares(const Mat& image, vector<vector<Point> >& squares)
{
squares.clear();
Mat pyr, timg, gray0(image.size(), CV_8U), gray;
// down-scale and upscale the image to filter out the noise
pyrDown(image, pyr, Size(image.cols / 2, image.rows / 2));
pyrUp(pyr, timg, image.size());
vector<vector<Point> > contours;
// find squares in every color plane of the image
for (int c = 0; c < 3; c++)
{
int ch[] = { c, 0 };
mixChannels(&timg, 1, &gray0, 1, ch, 1);
// try several threshold levels
for (int l = 0; l < N; l++)
{
// hack: use Canny instead of zero threshold level.
// Canny helps to catch squares with gradient shading
if (l == 0)
{
// apply Canny. Take the upper threshold from slider
// and set the lower to 0 (which forces edges merging)
Canny(gray0, gray, 0, thresh, 5);
// dilate canny output to remove potential
// holes between edge segments
dilate(gray, gray, Mat(), Point(-1, -1));
}
else
{
// apply threshold if l!=0:
// tgray(x,y) = gray(x,y) < (l+1)*255/N ? 255 : 0
gray = gray0 >= (l + 1) * 255 / N;
}
// find contours and store them all as a list
findContours(gray, contours, RETR_LIST, CHAIN_APPROX_SIMPLE);
vector<Point> approx;
// test each contour
for (size_t i = 0; i < contours.size(); i++)
{
// approximate contour with accuracy proportional
// to the contour perimeter
approxPolyDP(contours[i], approx, arcLength(contours[i], true) * 0.02, true);
// square contours should have 4 vertices after approximation
// relatively large area (to filter out noisy contours)
// and be convex.
// Note: absolute value of an area is used because
// area may be positive or negative - in accordance with the
// contour orientation
if (approx.size() == 4 &&
fabs(contourArea(approx)) > 1000 &&
isContourConvex(approx))
{
double maxCosine = 0;
for (int j = 2; j < 5; j++)
{
// find the maximum cosine of the angle between joint edges
double cosine = fabs(angle(approx[j % 4], approx[j - 2], approx[j - 1]));
maxCosine = MAX(maxCosine, cosine);
}
// if cosines of all angles are small
// (all angles are ~90 degree) then write quandrange
// vertices to resultant sequence
if (maxCosine < 0.3)
squares.push_back(approx);
}
}
}
}
}
int main(int argc, char** argv)
{
static const char* names[] = { "testimg.jpg", 0 };
help(argv[0]);
if (argc > 1)
{
names[0] = argv[1];
names[1] = "0";
}
for (int i = 0; names[i] != 0; i++)
{
string filename = samples::findFile(names[i]);
Mat image = imread(filename, IMREAD_COLOR);
if (image.empty())
{
cout << "Couldn't load " << filename << endl;
continue;
}
vector<vector<Point> > squares;
findSquares(image, squares);
polylines(image, squares, true, Scalar(0, 0, 255), 3, LINE_AA);
imshow(wndname, image);
int c = waitKey();
if (c == 27)
break;
}
return 0;
}
I would like some help to start off.
How could I get some information from 1 of the squares out of the array called "squares" (I am having a difficult time understand what exactly is in the array as well; is it an array of points?)
If something is not clear please let me know and I will try to re-explain.
Thank you in advance
Firstly, you are talking about squares but you are actually detecting rectangles. I provided a shorter code to be able to better answer your questions.
I read the image, apply a Canny filter for binarization and detect all contours. After that I iterate through the contours and find the ones which can be approximated by exactly four points and are convex:
int main(int argc, char** argv)
{
// Reading the images
cv::Mat img = cv::imread("squares_image.jpg", cv::IMREAD_GRAYSCALE);
cv::Mat edge_img;
std::vector <std::vector<cv::Point>> contours;
// Convert the image into a binary image using Canny filter - threshold could be automatically determined using OTSU method
cv::Canny(img, edge_img, 30, 100);
// Find all contours in the Canny image
findContours(edge_img, contours, cv::RETR_LIST, cv::CHAIN_APPROX_SIMPLE);
// Iterate through the contours and test if contours are square
std::vector<std::vector<cv::Point>> all_rectangles;
std::vector<cv::Point> single_rectangle;
for (size_t i = 0; i < contours.size(); i++)
{
// 1. Contours should be approximateable as a polygon
approxPolyDP(contours[i], single_rectangle, arcLength(contours[i], true) * 0.01, true);
// 2. Contours should have exactly 4 vertices and be convex
if (single_rectangle.size() == 4 && cv::isContourConvex(single_rectangle))
{
// 3. Determine if the polygon is really a square/rectangle using its properties (parallelity, angles etc.)
// Not necessary for the provided image
// Push the four points into your vector of squares (could be also std::vector<cv::Rect>)
all_rectangles.push_back(single_rectangle);
}
}
for (size_t num_contour = 0; num_contour < all_rectangles.size(); ++num_contour) {
cv::drawContours(img, all_rectangles, num_contour, cv::Scalar::all(-1));
}
cv::imshow("Detected rectangles", img);
cv::waitKey(0);
return 0;
}
1: The edge of the window is detected as a square, I do not want this.
There are several options depending on your applications. You can filter the outer boundary already using the Canny thresholds, using a different contour retrieval method for finding contours in findContours or by filtering single_rectangle using the area of the found contour (e.g. cv::contourArea(single_rectangle) < 1000).
2: How could I get the centre of 1 square from the squares array?
Since the code is already detecting the four corner points you could e.g. find the intersection of the diagonals. If you know that there are only rectangles in your image you could also try to detect all centroids of the detected contours using the Hu moments.
I am having a difficult time understand what exactly is in the array as well; is it an array of points?
One contour in OpenCV is always represented as a vector of single points. If you are adding multiple contours you are using a vector of vector of points. In the example you provided squares is a vector of a vector of exactly 4 points. You could also use a vector of cv::Rect in this case.

How to determine a region of interest and then crop an image using OpenCV

I asked a similar question here but that is focused more on tesseract.
I have a sample image as below. I would like to make the white square my Region of Interest and then crop out that part (square) and create a new image with it. I will be working with different images so the square won't always be at the same location in all images. So I will need to somehow detect the edges of the square.
What are some pre-processing methods I can perform to achieve the result?
Using your test image I was able to remove all the noises with a simple erosion operation.
After that, a simple iteration on the Mat to find for the corner pixels is trivial, and I talked about that on this answer. For testing purposes we can draw green lines between those points to display the area we are interested at in the original image:
At the end, I set the ROI in the original image and crop out that part.
The final result is displayed on the image below:
I wrote a sample code that performs this task using the C++ interface of OpenCV. I'm confident in your skills to translate this code to Python. If you can't do it, forget the code and stick with the roadmap I shared on this answer.
#include <cv.h>
#include <highgui.h>
int main(int argc, char* argv[])
{
cv::Mat img = cv::imread(argv[1]);
std::cout << "Original image size: " << img.size() << std::endl;
// Convert RGB Mat to GRAY
cv::Mat gray;
cv::cvtColor(img, gray, CV_BGR2GRAY);
std::cout << "Gray image size: " << gray.size() << std::endl;
// Erode image to remove unwanted noises
int erosion_size = 5;
cv::Mat element = cv::getStructuringElement(cv::MORPH_CROSS,
cv::Size(2 * erosion_size + 1, 2 * erosion_size + 1),
cv::Point(erosion_size, erosion_size) );
cv::erode(gray, gray, element);
// Scan the image searching for points and store them in a vector
std::vector<cv::Point> points;
cv::Mat_<uchar>::iterator it = gray.begin<uchar>();
cv::Mat_<uchar>::iterator end = gray.end<uchar>();
for (; it != end; it++)
{
if (*it)
points.push_back(it.pos());
}
// From the points, figure out the size of the ROI
int left, right, top, bottom;
for (int i = 0; i < points.size(); i++)
{
if (i == 0) // initialize corner values
{
left = right = points[i].x;
top = bottom = points[i].y;
}
if (points[i].x < left)
left = points[i].x;
if (points[i].x > right)
right = points[i].x;
if (points[i].y < top)
top = points[i].y;
if (points[i].y > bottom)
bottom = points[i].y;
}
std::vector<cv::Point> box_points;
box_points.push_back(cv::Point(left, top));
box_points.push_back(cv::Point(left, bottom));
box_points.push_back(cv::Point(right, bottom));
box_points.push_back(cv::Point(right, top));
// Compute minimal bounding box for the ROI
// Note: for some unknown reason, width/height of the box are switched.
cv::RotatedRect box = cv::minAreaRect(cv::Mat(box_points));
std::cout << "box w:" << box.size.width << " h:" << box.size.height << std::endl;
// Draw bounding box in the original image (debugging purposes)
//cv::Point2f vertices[4];
//box.points(vertices);
//for (int i = 0; i < 4; ++i)
//{
// cv::line(img, vertices[i], vertices[(i + 1) % 4], cv::Scalar(0, 255, 0), 1, CV_AA);
//}
//cv::imshow("Original", img);
//cv::waitKey(0);
// Set the ROI to the area defined by the box
// Note: because the width/height of the box are switched,
// they were switched manually in the code below:
cv::Rect roi;
roi.x = box.center.x - (box.size.height / 2);
roi.y = box.center.y - (box.size.width / 2);
roi.width = box.size.height;
roi.height = box.size.width;
std::cout << "roi # " << roi.x << "," << roi.y << " " << roi.width << "x" << roi.height << std::endl;
// Crop the original image to the defined ROI
cv::Mat crop = img(roi);
// Display cropped ROI
cv::imshow("Cropped ROI", crop);
cv::waitKey(0);
return 0;
}
Seeing that the text is the only large blob, and everything else is barely larger than a pixel, a simple morphological opening should suffice
You can do this in opencv
or with imagemagic
Afterwards the white rectangle should be the only thing left in the image. You can find it with opencvs findcontours, with the CvBlobs library for opencv or with the imagemagick -crop function
Here is your image with 2 steps of erosion followed by 2 steps of dilation applied:
You can simply plug this image into the opencv findContours function as in the Squares tutorial example to get the position
input
#objective:
#1)compress large images to less than 1000x1000
#2)identify region of interests
#3)save rois in top to bottom order
import cv2
import os
def get_contour_precedence(contour, cols):
tolerance_factor = 10
origin = cv2.boundingRect(contour)
return ((origin[1] // tolerance_factor) * tolerance_factor) * cols + origin[0]
# Load image, grayscale, Gaussian blur, adaptive threshold
image = cv2.imread('./images/sample_0.jpg')
#compress the image if image size is >than 1000x1000
height, width, color = image.shape #unpacking tuple (height, width, colour) returned by image.shape
while(width > 1000):
height = height/2
width = width/2
print(int(height), int(width))
height = int(height)
width = int(width)
image = cv2.resize(image, (width, height))
gray = cv2.cvtColor(image, cv2.COLOR_BGR2GRAY)
blur = cv2.GaussianBlur(gray, (9,9), 0)
thresh = cv2.adaptiveThreshold(gray,255,cv2.ADAPTIVE_THRESH_GAUSSIAN_C, cv2.THRESH_BINARY_INV,11,30)
# Dilate to combine adjacent text contours
kernel = cv2.getStructuringElement(cv2.MORPH_RECT, (9,9))
ret,thresh3 = cv2.threshold(image,127,255,cv2.THRESH_BINARY_INV)
dilate = cv2.dilate(thresh, kernel, iterations=4)
# Find contours, highlight text areas, and extract ROIs
cnts = cv2.findContours(dilate, cv2.RETR_EXTERNAL, cv2.CHAIN_APPROX_SIMPLE)
#cnts = cv2.findContours(thresh3, cv2.RETR_EXTERNAL, cv2.CHAIN_APPROX_SIMPLE)
cnts = cnts[0] if len(cnts) == 2 else cnts[1]
#ORDER CONTOURS top to bottom
cnts.sort(key=lambda x:get_contour_precedence(x, image.shape[1]))
#delete previous roi images in folder roi to avoid
dir = './roi/'
for f in os.listdir(dir):
os.remove(os.path.join(dir, f))
ROI_number = 0
for c in cnts:
area = cv2.contourArea(c)
if area > 10000:
x,y,w,h = cv2.boundingRect(c)
#cv2.rectangle(image, (x, y), (x + w, y + h), (36,255,12), 3)
cv2.rectangle(image, (x, y), (x + w, y + h), (100,100,100), 1)
#use below code to write roi when results are good
ROI = image[y:y+h, x:x+w]
cv2.imwrite('roi/ROI_{}.jpg'.format(ROI_number), ROI)
ROI_number += 1
cv2.imshow('thresh', thresh)
cv2.imshow('dilate', dilate)
cv2.imshow('image', image)
cv2.waitKey()
roi detection
output

OpenCV C++/Obj-C: Advanced square detection

A while ago I asked a question about square detection and karlphillip came up with a decent result.
Now I want to take this a step further and find squares which edge aren't fully visible. Take a look at this example:
Any ideas? I'm working with karlphillips code:
void find_squares(Mat& image, vector<vector<Point> >& squares)
{
// blur will enhance edge detection
Mat blurred(image);
medianBlur(image, blurred, 9);
Mat gray0(blurred.size(), CV_8U), gray;
vector<vector<Point> > contours;
// find squares in every color plane of the image
for (int c = 0; c < 3; c++)
{
int ch[] = {c, 0};
mixChannels(&blurred, 1, &gray0, 1, ch, 1);
// try several threshold levels
const int threshold_level = 2;
for (int l = 0; l < threshold_level; l++)
{
// Use Canny instead of zero threshold level!
// Canny helps to catch squares with gradient shading
if (l == 0)
{
Canny(gray0, gray, 10, 20, 3); //
// Dilate helps to remove potential holes between edge segments
dilate(gray, gray, Mat(), Point(-1,-1));
}
else
{
gray = gray0 >= (l+1) * 255 / threshold_level;
}
// Find contours and store them in a list
findContours(gray, contours, CV_RETR_LIST, CV_CHAIN_APPROX_SIMPLE);
// Test contours
vector<Point> approx;
for (size_t i = 0; i < contours.size(); i++)
{
// approximate contour with accuracy proportional
// to the contour perimeter
approxPolyDP(Mat(contours[i]), approx, arcLength(Mat(contours[i]), true)*0.02, true);
// Note: absolute value of an area is used because
// area may be positive or negative - in accordance with the
// contour orientation
if (approx.size() == 4 &&
fabs(contourArea(Mat(approx))) > 1000 &&
isContourConvex(Mat(approx)))
{
double maxCosine = 0;
for (int j = 2; j < 5; j++)
{
double cosine = fabs(angle(approx[j%4], approx[j-2], approx[j-1]));
maxCosine = MAX(maxCosine, cosine);
}
if (maxCosine < 0.3)
squares.push_back(approx);
}
}
}
}
}
You might try using HoughLines to detect the four sides of the square. Next, locate the four resulting line intersections to detect the corners. The Hough transform is fairly robust to noise and occlusions, so it could be useful here. Also, here is an interactive demo showing how the Hough transform works (I thought it was cool at least :). Here is one of my previous answers that detects a laser cross center showing most of the same math (except it just finds a single corner).
You will probably have multiple lines on each side, but locating the intersections should help to determine the inliers vs. outliers. Once you've located candidate corners, you can also filter these candidates by area or how "square-like" the polygon is.
EDIT : All these answers with code and images were making me think my answer was a bit lacking :) So, here is an implementation of how you could do this:
#include <opencv2/core/core.hpp>
#include <opencv2/highgui/highgui.hpp>
#include <opencv2/imgproc/imgproc.hpp>
#include <iostream>
#include <vector>
using namespace cv;
using namespace std;
Point2f computeIntersect(Vec2f line1, Vec2f line2);
vector<Point2f> lineToPointPair(Vec2f line);
bool acceptLinePair(Vec2f line1, Vec2f line2, float minTheta);
int main(int argc, char* argv[])
{
Mat occludedSquare = imread("Square.jpg");
resize(occludedSquare, occludedSquare, Size(0, 0), 0.25, 0.25);
Mat occludedSquare8u;
cvtColor(occludedSquare, occludedSquare8u, CV_BGR2GRAY);
Mat thresh;
threshold(occludedSquare8u, thresh, 200.0, 255.0, THRESH_BINARY);
GaussianBlur(thresh, thresh, Size(7, 7), 2.0, 2.0);
Mat edges;
Canny(thresh, edges, 66.0, 133.0, 3);
vector<Vec2f> lines;
HoughLines( edges, lines, 1, CV_PI/180, 50, 0, 0 );
cout << "Detected " << lines.size() << " lines." << endl;
// compute the intersection from the lines detected...
vector<Point2f> intersections;
for( size_t i = 0; i < lines.size(); i++ )
{
for(size_t j = 0; j < lines.size(); j++)
{
Vec2f line1 = lines[i];
Vec2f line2 = lines[j];
if(acceptLinePair(line1, line2, CV_PI / 32))
{
Point2f intersection = computeIntersect(line1, line2);
intersections.push_back(intersection);
}
}
}
if(intersections.size() > 0)
{
vector<Point2f>::iterator i;
for(i = intersections.begin(); i != intersections.end(); ++i)
{
cout << "Intersection is " << i->x << ", " << i->y << endl;
circle(occludedSquare, *i, 1, Scalar(0, 255, 0), 3);
}
}
imshow("intersect", occludedSquare);
waitKey();
return 0;
}
bool acceptLinePair(Vec2f line1, Vec2f line2, float minTheta)
{
float theta1 = line1[1], theta2 = line2[1];
if(theta1 < minTheta)
{
theta1 += CV_PI; // dealing with 0 and 180 ambiguities...
}
if(theta2 < minTheta)
{
theta2 += CV_PI; // dealing with 0 and 180 ambiguities...
}
return abs(theta1 - theta2) > minTheta;
}
// the long nasty wikipedia line-intersection equation...bleh...
Point2f computeIntersect(Vec2f line1, Vec2f line2)
{
vector<Point2f> p1 = lineToPointPair(line1);
vector<Point2f> p2 = lineToPointPair(line2);
float denom = (p1[0].x - p1[1].x)*(p2[0].y - p2[1].y) - (p1[0].y - p1[1].y)*(p2[0].x - p2[1].x);
Point2f intersect(((p1[0].x*p1[1].y - p1[0].y*p1[1].x)*(p2[0].x - p2[1].x) -
(p1[0].x - p1[1].x)*(p2[0].x*p2[1].y - p2[0].y*p2[1].x)) / denom,
((p1[0].x*p1[1].y - p1[0].y*p1[1].x)*(p2[0].y - p2[1].y) -
(p1[0].y - p1[1].y)*(p2[0].x*p2[1].y - p2[0].y*p2[1].x)) / denom);
return intersect;
}
vector<Point2f> lineToPointPair(Vec2f line)
{
vector<Point2f> points;
float r = line[0], t = line[1];
double cos_t = cos(t), sin_t = sin(t);
double x0 = r*cos_t, y0 = r*sin_t;
double alpha = 1000;
points.push_back(Point2f(x0 + alpha*(-sin_t), y0 + alpha*cos_t));
points.push_back(Point2f(x0 - alpha*(-sin_t), y0 - alpha*cos_t));
return points;
}
NOTE : The main reason I resized the image was so I could see it on my screen, and speed-up processing.
Canny
This uses Canny edge detection to help greatly reduce the number of lines detected after thresholding.
Hough transform
Then the Hough transform is used to detect the sides of the square.
Intersections
Finally, we compute the intersections of all the line pairs.
Hope that helps!
I tried to use convex hull method which is pretty simple.
Here you find convex hull of the contour detected. It removes the convexity defects at the bottom of paper.
Below is the code (in OpenCV-Python):
import cv2
import numpy as np
img = cv2.imread('sof.jpg')
img = cv2.resize(img,(500,500))
gray = cv2.cvtColor(img,cv2.COLOR_BGR2GRAY)
ret,thresh = cv2.threshold(gray,127,255,0)
contours,hier = cv2.findContours(thresh,cv2.RETR_LIST,cv2.CHAIN_APPROX_SIMPLE)
for cnt in contours:
if cv2.contourArea(cnt)>5000: # remove small areas like noise etc
hull = cv2.convexHull(cnt) # find the convex hull of contour
hull = cv2.approxPolyDP(hull,0.1*cv2.arcLength(hull,True),True)
if len(hull)==4:
cv2.drawContours(img,[hull],0,(0,255,0),2)
cv2.imshow('img',img)
cv2.waitKey(0)
cv2.destroyAllWindows()
(Here, i haven't found square in all planes. Do it yourself if you want.)
Below is the result i got:
I hope this is what you needed.
1st: start experimenting with threshold techniques to isolate the white paper sheet from the rest of the image. This is a simple way:
Mat new_img = imread(argv[1]);
double thres = 200;
double color = 255;
threshold(new_img, new_img, thres, color, CV_THRESH_BINARY);
imwrite("thres.png", new_img);
but there are other alternatives that could provide better result. One is to investigate inRange(), and another is to detect through color by converting the image to the HSV color space.
This thread also provides an interest discussion on the subject.
2nd: after you execute one of this procedures, you could try to feed the result directly into find_squares():
An alternative to find_squares() is to implement the bounding box technique, which has the potential to provide a more accurate detection of the rectangular area (provided that you have a perfect result of threshold). I've used it here and here. It's worth noting that OpenCV has it's own bounding box tutorial.
Another approach besides find_squares(), as pointed by Abid on his answer, is to use the convexHull method. Check OpenCV's C++ tutorial on this method for code.
convert to lab space
use kmeans for 2 clusters
detect suqares one internal cluster it will solve many thing in the rgb space

OpenCV Line Detection

I am trying to find the edges of the centered box in this image:
I have tried using a HoughLines using dRho=img_width/1000, dTheta=pi/180, and threshold=250
It works great on this image, scaled to 1/3 of the size, but on the full size image it just gets lines everywhere in every direction...
What can I do to tune this to be more accurate?
The code to achieve the result below is a slight modification of the one presented in this answer: how to detect a square:
The original program can be found inside OpenCV, it's called squares.cpp. The code below was modified to search squares only in the first color plane, but as it still detects many squares, at the end of the program I discard all of them except the first, and then call draw_squares() to show what was detected. You can change this easilly to draw all of them and see everything that was detected.
You can do all sorts of thing from now own, including setting a (ROI) region of interest to extract the area that's inside the square (ignore everything else around it).
You can see that the detected rectangle is not perfectly aligned with the lines in the image. You should perform some pre-processing (erode?) operations in the image to decrease the thickness of lines and improve the detection. But from here on it's all on you:
#include <cv.h>
#include <highgui.h>
using namespace cv;
double angle( cv::Point pt1, cv::Point pt2, cv::Point pt0 ) {
double dx1 = pt1.x - pt0.x;
double dy1 = pt1.y - pt0.y;
double dx2 = pt2.x - pt0.x;
double dy2 = pt2.y - pt0.y;
return (dx1*dx2 + dy1*dy2)/sqrt((dx1*dx1 + dy1*dy1)*(dx2*dx2 + dy2*dy2) + 1e-10);
}
void find_squares(Mat& image, vector<vector<Point> >& squares)
{
// TODO: pre-processing
// blur will enhance edge detection
Mat blurred(image);
medianBlur(image, blurred, 9);
Mat gray0(blurred.size(), CV_8U), gray;
vector<vector<Point> > contours;
// find squares in the first color plane.
for (int c = 0; c < 1; c++)
{
int ch[] = {c, 0};
mixChannels(&blurred, 1, &gray0, 1, ch, 1);
// try several threshold levels
const int threshold_level = 2;
for (int l = 0; l < threshold_level; l++)
{
// Use Canny instead of zero threshold level!
// Canny helps to catch squares with gradient shading
if (l == 0)
{
Canny(gray0, gray, 10, 20, 3); //
// Dilate helps to remove potential holes between edge segments
dilate(gray, gray, Mat(), Point(-1,-1));
}
else
{
gray = gray0 >= (l+1) * 255 / threshold_level;
}
// Find contours and store them in a list
findContours(gray, contours, CV_RETR_LIST, CV_CHAIN_APPROX_SIMPLE);
// Test contours
vector<Point> approx;
for (size_t i = 0; i < contours.size(); i++)
{
// approximate contour with accuracy proportional
// to the contour perimeter
approxPolyDP(Mat(contours[i]), approx, arcLength(Mat(contours[i]), true)*0.02, true);
// Note: absolute value of an area is used because
// area may be positive or negative - in accordance with the
// contour orientation
if (approx.size() == 4 &&
fabs(contourArea(Mat(approx))) > 1000 &&
isContourConvex(Mat(approx)))
{
double maxCosine = 0;
for (int j = 2; j < 5; j++)
{
double cosine = fabs(angle(approx[j%4], approx[j-2], approx[j-1]));
maxCosine = MAX(maxCosine, cosine);
}
if (maxCosine < 0.3)
squares.push_back(approx);
}
}
}
}
}
void draw_squares(Mat& img, vector<vector<Point> > squares)
{
for (int i = 0; i < squares.size(); i++)
{
for (int j = 0; j < squares[i].size(); j++)
{
cv::line(img, squares[i][j], squares[i][(j+1) % 4], cv::Scalar(0, 255, 0), 1, CV_AA);
}
}
}
int main(int argc, char* argv[])
{
Mat img = imread(argv[1]);
vector<vector<Point> > squares;
find_squares(img, squares);
std::cout << "* " << squares.size() << " squares were found." << std::endl;
// Ignore all the detected squares and draw just the first found
vector<vector<Point> > tmp;
if (squares.size() > 0)
{
tmp.push_back(squares[0]);
draw_squares(img, tmp);
}
//imshow("squares", img);
//cvWaitKey(0);
imwrite("out.png", img);
return 0;
}
when resizing the image, the image is normally first blurred with a filter, e.g. Gaussian, in order to get rid of high frequencies. The fact that resized one works better is likely because your original image is somehow noisy.
Try blur the image first, e.g. with cv::GaussianBlur(src, target, Size(0,0), 1.5), then it should be equivalent to resizing. (It forgot the theory, if it does not work, try 3 and 6 as well)
Try using a preprocessing pass with the erosion filter. It will give you the same effect as the downscaling - the lines will become thinner and will not disappear at the same time.
The "Blur" filter is also a good idea, as chaiy says.
This way (with blur) it will become something like http://www.ic.uff.br/~laffernandes/projects/kht/index.html (Kernel Based Hough Transform)