I have a set of discrete points shown in an image, like the following
I want to reconstruct or up sampling (I'm not sure what's the correct way to describe it) the image, so that the result image would be like the following. It doesn't need to be exactly the same as the example image, but the main idea is to fill up the original one.
I have an initial idea about how to do it. But I don't know how to do it after the first step. My idea is to first separate image using kmeans and find out the different objects. And I have successfully done it. The resulting images after kmeans are: .
After kmeans, I want to use find contour or something like concave to get the outline of these shapes and fill the shape using functions like fill holes. However, I found "find contour" does not work, it will consider each single pixel as a contour.
The other way I'm thinking is to use interpolation. But I'm not sure whether it is possible with so sparse points. Does anyone have any ideas about how to do this? I'm not sure whether I'm on the right way and I'm open to any solutions.
Thanks a lot!
Take a look at the morphological transformations. I would start with a dilation operation using a large kernel, say the MORPH_ELLIPSE with a size(15,15). Afterwards, thin the blobs back down using the erosion operation with the same size kernel. Take a look at the docs here. Note that OpenCV offers chained, or sequenced, morphological operations, too. See here. You'll then see that my suggestion is a "closing" operation.
Update:
I experimented with simple dilation and contouring to yield the results shown in the image. The results appear to satisfy the general requirements of the problem.
Likewise, what "realtime" means for the application isn't specified, but this set of operations may be quickly executed and could easily be applied to a 30fps application.
Code snippet below:
// Convert image to grayscale
cvtColor(src, gray, CV_BGR2GRAY);
threshold(gray, gray, 128.0, 128.0, THRESH_BINARY);
// Dilate to fill holes
dilate(gray, dest, getStructuringElement(MORPH_ELLIPSE, Size(13,13)));
// Find contours
vector<vector<Point> > contours;
vector<Vec4i> hierarchy;
findContours(dest, contours, hierarchy, CV_RETR_TREE, CV_CHAIN_APPROX_SIMPLE, Point(0,0));
// Prune contours
float maxArea = 0.0f;
for (size_t i = 0; i< contours.size(); i++)
{
if (contourArea(contours[i]) >= maxArea)
{
maxArea = contourArea(contours[i]);
}
}
float minArea = 0.20f * maxArea;
vector<vector<Point> > prunedContours;
for (size_t i = 0; i< contours.size(); i++)
{
if (contourArea(contours[i]) >= minArea)
{
prunedContours.push_back(contours[i]);
}
}
// Smooth the contours
vector<vector<Point> > smoothedContours;
smoothedContours.resize(prunedContours.size());
for (size_t i=0;i<prunedContours.size();i++)
{
vector<float> x;
vector<float> y;
const size_t n = prunedContours[i].size();
for (size_t j=0;j<n;j++)
{
x.push_back(prunedContours[i][j].x);
y.push_back(prunedContours[i][j].y);
}
Mat G;
transpose(getGaussianKernel(11,4.0,CV_32FC1),G);
vector<float> xSmooth;
vector<float> ySmooth;
filter2D(x,xSmooth, CV_32FC1, G);
filter2D(y,ySmooth, CV_32FC1, G);
for (size_t j=0;j<n;j++)
{
smoothedContours[i].push_back(Point2f(xSmooth[j],ySmooth[j]));
}
}
Related
I'm trying to count the number of erythrocytes on a microscope image. These are the smaller cells. (I've tried first using CNN and sliding window, but it was too slow, so I'm looking for a simplier segmentation)
My approach is:
threshold
find and draw all contours filled so that the cells won't have holes,
make distance transform
iterating over all maxima
masking out a current maximum with a circle having the radius of the maximum and storing the maximum position
My problem is, some cells have a "hole" in the middle - bright area similar by the value to background. If I threshold the image, some of the cell-masks become not a circle but a half circle, with the distance-transform values far below expected value.
I've marked the cells having the "holes" on the mask image.
Hov could I close the hole or the circle? Is there a threshold method or trick?
Below is the part of code responsible for cell extraction:
cv::adaptiveThreshold(_imgIn ,th, 255, ADAPTIVE_THRESH_GAUSSIAN_C, (bgblack ? CV_THRESH_BINARY: CV_THRESH_BINARY_INV), 35, 5 );//| CV_THRESH_OTSU);
Mat kernel1 = Mat::ones(3, 3, CV_8UC1);
for (int i=0; i< 5;i++)
{
dilate(th, th, kernel1);
erode(th, th, kernel1);
}
vector<vector<Point> > contours;
findContours(th, contours, CV_RETR_EXTERNAL, CV_CHAIN_APPROX_NONE);
mask = 0;
for( unsigned int i = 0; i < contours.size(); i++ )
{
drawContours(mask, contours, i, Scalar(255), CV_FILLED);
}
cv::distanceTransform(mask, dist, CV_DIST_L2, 3);
}
double min, max;
cv::Point pmax;
Mat tmp1 = dist.clone();
while (true)
{
cv::minMaxLoc(tmp1, 0, &max, 0, &pmax);
if ( max < 5 )
break;
cv::circle(_imgIn, pmax, 3 , cv::Scalar(0), CV_FILLED );
cv::circle(tmp1, pmax, max , cv::Scalar(0), CV_FILLED );
}
Closing holes
Closing is an important operator from the field of mathematical morphology. Like its dual operator opening, it can be derived from the fundamental operations of erosion and dilation. Like those operators it is normally applied to binary images, although there are graylevel versions. Closing is similar in some ways to dilation in that it tends to enlarge the boundaries of foreground (bright) regions in an image (and shrink background color holes in such regions), but it is less destructive of the original boundary shape. As with other morphological operators, the exact operation is determined by a structuring element. The effect of the operator is to preserve background regions that have a similar shape to this structuring element, or that can completely contain the structuring element, while eliminating all other regions of background pixels.
In Open CV this looks as follows
import cv2 as cv
import numpy as np
img = cv.imread('j.png',0)
kernel = np.ones((5,5),np.uint8)
erosion = cv.erode(img,kernel,iterations = 1)
closing = cv.morphologyEx(img, cv.MORPH_CLOSE, kernel)
Full documentation here.
After some simple preprocessing I am receiving boolean mask of segmented images.
I want to "enhance" borders of the mask and make them more smooth. For that I am using OPEN morphology filter with a rather big circle kernel , it works very well until the distance between segmented objects is enough. But In alot of samples objects stick together. Is there exists some more or less simple method to smooth such kind of images without changing its morphology ?
Without applying a morphological filter first, you can try to detect the external contours of the image. Now you can draw these external contours as filled contours and then apply your morphological filter. This works because now you don't have any holes to fill. This is fairly simple.
Another approach:
find external contours
take the x, y of coordinates of the contour points. you can consider these as 1-D signals and apply a smoothing filter to these signals
In the code below, I've applied the second approach to a sample image.
Input image
External contours without any smoothing
After applying a Gaussian filter to x and y 1-D signals
C++ code
Mat im = imread("4.png", 0);
Mat cont = im.clone();
Mat original = Mat::zeros(im.rows, im.cols, CV_8UC3);
Mat smoothed = Mat::zeros(im.rows, im.cols, CV_8UC3);
// contour smoothing parameters for gaussian filter
int filterRadius = 5;
int filterSize = 2 * filterRadius + 1;
double sigma = 10;
vector<vector<Point> > contours;
vector<Vec4i> hierarchy;
// find external contours and store all contour points
findContours(cont, contours, hierarchy, CV_RETR_EXTERNAL, CV_CHAIN_APPROX_NONE, Point(0, 0));
for(size_t j = 0; j < contours.size(); j++)
{
// draw the initial contour shape
drawContours(original, contours, j, Scalar(0, 255, 0), 1);
// extract x and y coordinates of points. we'll consider these as 1-D signals
// add circular padding to 1-D signals
size_t len = contours[j].size() + 2 * filterRadius;
size_t idx = (contours[j].size() - filterRadius);
vector<float> x, y;
for (size_t i = 0; i < len; i++)
{
x.push_back(contours[j][(idx + i) % contours[j].size()].x);
y.push_back(contours[j][(idx + i) % contours[j].size()].y);
}
// filter 1-D signals
vector<float> xFilt, yFilt;
GaussianBlur(x, xFilt, Size(filterSize, filterSize), sigma, sigma);
GaussianBlur(y, yFilt, Size(filterSize, filterSize), sigma, sigma);
// build smoothed contour
vector<vector<Point> > smoothContours;
vector<Point> smooth;
for (size_t i = filterRadius; i < contours[j].size() + filterRadius; i++)
{
smooth.push_back(Point(xFilt[i], yFilt[i]));
}
smoothContours.push_back(smooth);
drawContours(smoothed, smoothContours, 0, Scalar(255, 0, 0), 1);
cout << "debug contour " << j << " : " << contours[j].size() << ", " << smooth.size() << endl;
}
Not 100% sure what you are trying to achieve, but this may be an avenue to explore... the tool potrace takes images and converts them to vectorised images which involves smoothing. It prefers PGM format input files so I use ImageMagick to prepare them. Anyway, here is an example of the command and the result so see what you think:
convert disks.png pgm:- | potrace - -s -o out.svg
I have converted the resulting SVG file to a PNG so I can upload it to SO.
What is the most efficient way to find the bounding box of the largest blob in a binary image using OpenCV? Unfortunately, OpenCV does not have specific functionality for blob detection. Should I just use findContours() and search for the largest in the list?
Here. It. Is.
(FYI: try not to be lazy and figure out what happens in my function below.
cv::Mat findBiggestBlob(cv::Mat & matImage){
int largest_area=0;
int largest_contour_index=0;
vector< vector<Point> > contours; // Vector for storing contour
vector<Vec4i> hierarchy;
findContours( matImage, contours, hierarchy,CV_RETR_CCOMP, CV_CHAIN_APPROX_SIMPLE ); // Find the contours in the image
for( int i = 0; i< contours.size(); i++ ) {// iterate through each contour.
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]); // Find the bounding rectangle for biggest contour
}
}
drawContours( matImage, contours, largest_contour_index, Scalar(255), CV_FILLED, 8, hierarchy ); // Draw the largest contour using previously stored index.
return matImage;
}
If you want to use OpenCV libs, check out OpenCVs SimpleBlobDetector. Here's another stack overflow showing a small tutorial of it: How to use OpenCV SimpleBlobDetector
This only gives you key points though. You could use this as an initial search to find the blob you want, and then possibly use the findContours algorithm around the most likely blobs.
Also the more information you know about your blob, you can provide parameters to filter out the blobs you don't want. You might want to test out the area parameters of the SimpleBlobDetector. Possibly could could compute the area based on the size of the area of the image and then iteratively allow for a smaller blob if the algorithm does not detect any blobs.
Here is the link to the main OpenCV documentation: http://docs.opencv.org/modules/features2d/doc/common_interfaces_of_feature_detectors.html#simpleblobdetector
To find the bounding box of the largest blob, I used findContours, followed by the following code:
double maxArea = 0;
for (MatOfPoint contour : contours) {
double area = Imgproc.contourArea(contour);
if (area > maxArea) {
maxArea = area;
largestContour = contour;
}
}
Rect boundingRect = Imgproc.boundingRect(largestContour);
Since no one has posted a complete OpenCV solution, here's a simple approach using thresholding + contour area filtering
Input image
Largest blob/contour highlighted in green
import cv2
# Load image, grayscale, Gaussian blur, and Otsu's threshold
image = cv2.imread('1.png')
gray = cv2.cvtColor(image, cv2.COLOR_BGR2GRAY)
thresh = cv2.threshold(gray, 0, 255, cv2.THRESH_BINARY_INV + cv2.THRESH_OTSU)[1]
# Find contours and sort using contour area
cnts = cv2.findContours(thresh, cv2.RETR_EXTERNAL, cv2.CHAIN_APPROX_SIMPLE)
cnts = cnts[0] if len(cnts) == 2 else cnts[1]
cnts = sorted(cnts, key=cv2.contourArea, reverse=True)
for c in cnts:
# Highlight largest contour
cv2.drawContours(image, [c], -1, (36,255,12), 3)
break
cv2.imshow('thresh', thresh)
cv2.imshow('image', image)
cv2.waitKey()
TimZaman, your code has a bug but I can't comment so I start a new and correct answer.
Here is my solution based on 1"'s and TimZaman's ideas:
Mat measure::findBiggestBlob(cv::Mat &src){
int largest_area=0;
int largest_contour_index=0;
Mat temp(src.rows,src.cols,CV_8UC1);
Mat dst(src.rows,src.cols,CV_8UC1,Scalar::all(0));
src.copyTo(temp);
vector<vector<Point>> contours; // storing contour
vector<Vec4i> hierarchy;
findContours( temp, contours, hierarchy,CV_RETR_CCOMP, CV_CHAIN_APPROX_SIMPLE );
for( int i = 0; i< contours.size(); i++ ) // iterate
{
double a=contourArea( contours[i],false); //Find the largest area of contour
if(a>largest_area)
{
largest_area=a;
largest_contour_index=i;
}
}
drawContours( dst, contours,largest_contour_index, Scalar(255), CV_FILLED, 8, hierarchy );
// Draw the largest contour
return dst;
}
I have a problem with filling white holes inside a black coin so that I can have only 0-255 binary images with filled black coins. I have used a Median filter to accomplish it but in that case connection bridge between coins grows and it goes impossible to recognize them after several times of erosion... So I need a simple floodFill like method in opencv
Here is my image with holes:
EDIT: floodfill like function must fill holes in big components without prompting X, Y coordinates as a seed...
EDIT: I tried to use the cvDrawContours function but it doesn't fill contours inside bigger ones.
Here is my code:
CvMemStorage mem = cvCreateMemStorage(0);
CvSeq contours = new CvSeq();
CvSeq ptr = new CvSeq();
int sizeofCvContour = Loader.sizeof(CvContour.class);
cvThreshold(gray, gray, 150, 255, CV_THRESH_BINARY_INV);
int numOfContours = cvFindContours(gray, mem, contours, sizeofCvContour, CV_RETR_CCOMP, CV_CHAIN_APPROX_SIMPLE);
System.out.println("The num of contours: "+numOfContours); //prints 87, ok
Random rand = new Random();
for (ptr = contours; ptr != null; ptr = ptr.h_next()) {
Color randomColor = new Color(rand.nextFloat(), rand.nextFloat(), rand.nextFloat());
CvScalar color = CV_RGB( randomColor.getRed(), randomColor.getGreen(), randomColor.getBlue());
cvDrawContours(gray, ptr, color, color, -1, CV_FILLED, 8);
}
CanvasFrame canvas6 = new CanvasFrame("drawContours");
canvas6.showImage(gray);
Result: (you can see black holes inside each coin)
There are two methods to do this:
1) Contour Filling:
First, invert the image, find contours in the image, fill it with black and invert back.
des = cv2.bitwise_not(gray)
contour,hier = cv2.findContours(des,cv2.RETR_CCOMP,cv2.CHAIN_APPROX_SIMPLE)
for cnt in contour:
cv2.drawContours(des,[cnt],0,255,-1)
gray = cv2.bitwise_not(des)
Resulting image:
2) Image Opening:
kernel = cv2.getStructuringElement(cv2.MORPH_ELLIPSE,(3,3))
res = cv2.morphologyEx(gray,cv2.MORPH_OPEN,kernel)
The resulting image is as follows:
You can see, there is not much difference in both cases.
NB: gray - grayscale image, All codes are in OpenCV-Python
Reference. OpenCV Morphological Transformations
A simple dilate and erode would close the gaps fairly well, I imagine. I think maybe this is what you're looking for.
A more robust solution would be to do an edge detect on the whole image, and then a hough transform for circles. A quick google shows there are code samples available in various languages for size invariant detection of circles using a hough transform, so hopefully that will give you something to go on.
The benefit of using the hough transform is that the algorithm will actually give you an estimate of the size and location of every circle, so you can rebuild an ideal image based on that model. It should also be very robust to overlap, especially considering the quality of the input image here (i.e. less worry about false positives, so can lower the threshold for results).
You might be looking for the Fillhole transformation, an application of morphological image reconstruction.
This transformation will fill the holes in your coins, even though at the cost of also filling all holes between groups of adjacent coins. The Hough space or opening-based solutions suggested by the other posters will probably give you better high-level recognition results.
In case someone is looking for the cpp implementation -
std::vector<std::vector<cv::Point> > contours_vector;
cv::findContours(input_image, contours_vector, CV_RETR_LIST, CV_CHAIN_APPROX_NONE);
cv::Mat contourImage(input_image.size(), CV_8UC1, cv::Scalar(0));
for ( ushort contour_index = 0; contour_index < contours_vector.size(); contour_index++) {
cv::drawContours(contourImage, contours_vector, contour_index, cv::Scalar(255), -1);
}
cv::imshow("con", contourImage);
cv::waitKey(0);
Try using cvFindContours() function. You can use it to find connected components. With the right parameters this function returns a list with the contours of each connected components.
Find the contours which represent a hole. Then use cvDrawContours() to fill up the selected contour by the foreground color thereby closing the holes.
I think if the objects are touched or crowded, there will be some problems using the contours and the math morophology opening.
Instead, the following simple solution is found and tested. It is working very well, and not only for this images, but also for any other images.
here is the steps (optimized) as seen in http://blogs.mathworks.com/steve/2008/08/05/filling-small-holes/
let I: the input image
1. filled_I = floodfill(I). // fill every hole in the image.
2. inverted_I = invert(I)`.
3. holes_I = filled_I AND inverted_I. // finds all holes
4. cc_list = connectedcomponent(holes_I) // list of all connected component in holes_I.
5. holes_I = remove(cc_list,holes_I, smallholes_threshold_size) // remove all holes from holes_I having size > smallholes_threshold_size.
6. out_I = I OR holes_I. // fill only the small holes.
In short, the algorithm is just to find all holes, remove the big ones then write the small ones only on the original image.
I've been looking around the internet to find a proper imfill function (as the one in Matlab) but working in C with OpenCV. After some reaserches, I finally came up with a solution :
IplImage* imfill(IplImage* src)
{
CvScalar white = CV_RGB( 255, 255, 255 );
IplImage* dst = cvCreateImage( cvGetSize(src), 8, 3);
CvMemStorage* storage = cvCreateMemStorage(0);
CvSeq* contour = 0;
cvFindContours(src, storage, &contour, sizeof(CvContour), CV_RETR_CCOMP, CV_CHAIN_APPROX_SIMPLE );
cvZero( dst );
for( ; contour != 0; contour = contour->h_next )
{
cvDrawContours( dst, contour, white, white, 0, CV_FILLED);
}
IplImage* bin_imgFilled = cvCreateImage(cvGetSize(src), 8, 1);
cvInRangeS(dst, white, white, bin_imgFilled);
return bin_imgFilled;
}
For this: Original Binary Image
Result is: Final Binary Image
The trick is in the parameters setting of the cvDrawContours function:
cvDrawContours( dst, contour, white, white, 0, CV_FILLED);
dst = destination image
contour = pointer to the first contour
white = color used to fill the contour
0 = Maximal level for drawn contours. If 0, only contour is drawn
CV_FILLED = Thickness of lines the contours are drawn with. If it is negative (For example, =CV_FILLED), the contour interiors are drawn.
More info in the openCV documentation.
There is probably a way to get "dst" directly as a binary image but I couldn't find how to use the cvDrawContours function with binary values.
I'm trying to draw contours around blobs in a binary image, however, sometimes, openCV draws a single contour around two distinct blobs. below is an example. How can i solve this issue?
Here it should draw two bounding boxes for the blob on the right and separately for the one of the left. I agree they are close but enough distance in between them. I'm only drawing External contours instead of the tree or list. I'm also using cvFindNextContour(contourscanner) as this is a easier implementation for my case.
Thanks
EDIT:
Image displayed in the "output" window is from a different function which does just image subtraction. Image displayed in the "contours" window is in the function pplfind(). "output" image is passed to img_con().
IplImage* img_con(IplImage* image){
int ppl;
CvMemStorage* memstr = cvCreateMemStorage();
IplImage* edges = cvCreateImage(cvGetSize(image),8,1);
cvCanny(image,edges,130,255);
CvContourScanner cscan = cvStartFindContours(image,memstr,sizeof(CvContour),CV_RETR_EXTERNAL,CV_CHAIN_APPROX_NONE,cvPoint(0,0));
ppl = pplfind(cscan,cvGetSize(image));
if (ppl !=0 )
printf("Estimated number of people: %d\n",ppl);
cvEndFindContours(&cscan);
cvClearMemStorage(memstr);
return edges;
}
int pplfind(CvContourScanner cscan, CvSize frSize){
ofstream file; char buff[50];
file.open("box.txt",ofstream::app);
int ppl =0;
CvSeq* c;
IplImage *out = cvCreateImage(frSize,8,3);
while (c = cvFindNextContour(cscan)){
CvRect box = cvBoundingRect(c,1);
if ((box.height > int(box.width*1.2))&&(box.height>20)){//&&(box.width<20)){//
ppl++;
cvRectangle(out,cvPoint(box.x,box.y),cvPoint(box.x+box.width,box.y+box.height),CV_RGB(255,0,50),1);
cvShowImage("contours",out);
//cvWaitKey();
}
//printf("Box Height: %d , Box Width: %d ,People: %d\n",box.height,box.width,ppl);
//cvWaitKey(0);
int coord = sprintf_s(buff,"%d,%d,%d\n",box.width,box.height,ppl);
file.write(buff,coord);
}
file.close();
cvReleaseImage(&out);
return ppl;
}
I've never used cvFindNextContour, but running cvFindContours with CV_RETR_EXTERNAL on your image seems to work fine:
I use OpenCV + Python, so this code might not be useful for you, but for the sake of completeness here it goes:
contours = cv.findContours(img, cv.CreateMemStorage(0), mode=cv.CV_RETR_EXTERNAL)
while contours:
(x,y,w,h) = cv.BoundingRect(contours)
cv.Rectangle(colorImg, (x,y), (x+w,y+h), cv.Scalar(0,255,255,255))
contours = contours.h_next()
Edit: you asked how to draw only those contours with certain properties; it would be something like this:
contours = cv.findContours(img, cv.CreateMemStorage(0), mode=cv.CV_RETR_EXTERNAL)
while contours:
(x,y,w,h) = cv.BoundingRect(contours)
if h > w*1.2 and h > 20:
cv.Rectangle(colorImg, (x,y), (x+w,y+h), cv.Scalar(0,255,255,255))
contours = contours.h_next()