I am using the Mat_<float> aque(3,3);
aque << .240 , .640 , .450
,0,0,0
,0,0,0
I want to turn it in to light blue , how I can adjust these values ? I want to know the function of these three values .240 , .640 , .450 in matrix , I know these all are presenting blue color but what are their functionalities what they all 3 values present ?
just go and do your own experiments ?
int f[9] = {24,64,45,0,0,0,0,0,0}; // initial trackbar pos
Mat filt(3,3,CV_32F);
Mat img;
void onTrack(int,void*)
{
float *p = filt.ptr<float>(0);
for ( int i=0; i<9; i++ )
{
p[i] = float(f[i]) / 100; // get it back to [0..1] range for the transform matrix
}
Mat out;
cv::transform(img,out,filt);
imshow("result",out);
}
int main( int argc, const char** argv )
{
img = imread("lena.jpg");
namedWindow("result",0);
namedWindow("sliders",0);
createTrackbar("1","sliders",&f[0],100,onTrack);
createTrackbar("2","sliders",&f[1],100,onTrack);
createTrackbar("3","sliders",&f[2],100,onTrack);
createTrackbar("4","sliders",&f[3],100,onTrack);
createTrackbar("5","sliders",&f[4],100,onTrack);
createTrackbar("6","sliders",&f[5],100,onTrack);
createTrackbar("7","sliders",&f[6],100,onTrack);
createTrackbar("8","sliders",&f[7],100,onTrack);
createTrackbar("9","sliders",&f[8],100,onTrack);
onTrack(0,0);
waitKey();
cerr << filt << endl;
return 0;
}
if you 're happy with the results, just divide each slider value by 100, and compose a filter matrix from that.
Related
I ran the following code for getting code feature for barcode using zbar library and set the properties for the project. I am getting errors such as unresolved external symbol error (LNK2019). How to resolve this error? The code for my program and the errors are attached below
#include <opencv2/opencv.hpp>
#include <C:/Program Files/ZBar/include/zbar.h>
using namespace cv;
using namespace std;
using namespace zbar;
typedef struct
{
string type;
string data;
vector <Point> location;
} decodedObject;
// Find and decode barcodes and QR codes
void decode(Mat& im, vector<decodedObject>& decodedObjects)
{
// Create zbar scanner
ImageScanner scanner;
// Configure scanner
scanner.set_config(ZBAR_NONE, ZBAR_CFG_ENABLE, 1);
// Convert image to grayscale
Mat imGray;
cvtColor(im, imGray, COLOR_BGR2GRAY);
// Wrap image data in a zbar image
Image image(im.cols, im.rows, "Y800", (uchar*)imGray.data, im.cols * im.rows);
// Scan the image for barcodes and QRCodes
int n = scanner.scan(image);
// Print results
for (Image::SymbolIterator symbol = image.symbol_begin(); symbol != image.symbol_end(); ++symbol)
{
decodedObject obj;
obj.type = symbol->get_type_name();
obj.data = symbol->get_data();
// Print type and data
cout << "Type : " << obj.type << endl;`
cout << "Data : " << obj.data << endl << endl;
// Obtain location
for (int i = 0; i < symbol->get_location_size(); i++)
{
obj.location.push_back(Point(symbol->get_location_x(i), symbol->get_location_y(i)));
}
decodedObjects.push_back(obj);
}
}
// Display barcode and QR code location
void display(Mat& im, vector<decodedObject>& decodedObjects)
{
// Loop over all decoded objects
for (int i = 0; i < decodedObjects.size(); i++)
{
vector<Point> points = decodedObjects[i].location;
vector<Point> hull;
// If the points do not form a quad, find convex hull
if (points.size() > 4)
convexHull(points, hull);
else
hull = points;
// Number of points in the convex hull
int n = hull.size();
for (int j = 0; j < n; j++)
{
line(im, hull[j], hull[(j + 1) % n], Scalar(255, 0, 0), 3);
}
}
// Display results
imshow("Results", im);
waitKey(0);
}
int main(int argc, char* argv[])
{
// Read image
Mat im = imread("zbar-test.jpg");
// Variable for decoded objects
vector<decodedObject> decodedObjects;
// Find and decode barcodes and QR codes
decode(im, decodedObjects);
// Display location
display(im, decodedObjects);
return EXIT_SUCCESS;
}
The errors are as follows,
Your code runs OK! You just need to refer the Zbar library on:
Project Properties -> Linker -> Input -> C:\opencv\Zbar\lib\libzbar64-0.lib (for example)
With kind regards,
PFG
I have a classic problem about the output of sobel filter using CUDA.
this is a main class (main.cpp)
/*main class */
int main(int argc, char** argv)
{
IplImage* image_source = cvLoadImage("test.jpg",
CV_LOAD_IMAGE_GRAYSCALE);
IplImage* image_input = cvCreateImage(cvGetSize(image_source),
IPL_DEPTH_8U,image_source->nChannels);
IplImage* image_output = cvCreateImage(cvGetSize(image_source),
IPL_DEPTH_8U,image_source->nChannels);
/* Convert from IplImage tofloat */
cvConvert(image_source,image_input);
unsigned char *h_out = (unsigned char*)image_output->imageData;
unsigned char *h_in = (unsigned char*)image_input->imageData;
width = image_input->width;
height = image_input->height;
widthStep = image_input->widthStep;
sobel_parallel(h_in, h_out, width, height, widthStep);
cvShowImage( "CPU", image_output );
cvReleaseImage( &image_output );
waitKey(0);
}
And this is the CUDA file (kernel_gpu.cu)
__global__ void kernel ( unsigned char *d_in , unsigned char *d_out , int width ,
int height, int widthStep ) {
int col = blockIdx . x * blockDim . x + threadIdx . x ;
int row = blockIdx . y * blockDim . y + threadIdx . y ;
int dx [3][3] = { -1 , 0 , 1 ,
-2 , 0 , 2 ,
-1 , 0 , 1};
int dy [3][3] = {1 ,2 ,1 ,
0 ,0 ,0 ,
-1 , -2 , -1};
int s;
if( col < width && row < height)
{
int i = row;
int j = col;
// apply kernel in X direction
int sum_x=0;
for(int m=-1; m<=1; m++)
for(int n=-1; n<=1; n++)
{
s=d_in[(i+m)*widthStep+j+n]; // get the (i,j) pixel value
sum_x+=s*dx[m+1][n+1];
}
// apply kernel in Y direction
int sum_y=0;
for(int m=-1; m<=1; m++)
for(int n=-1; n<=1; n++)
{
s=d_in[(i+m)*widthStep+j+n]; // get the (i,j) pixel value
sum_y+=s*dy[m+1][n+1];
}
int sum=abs(sum_x)+abs(sum_y);
if (sum>255)
sum=255;
d_out[i*widthStep+j]=sum; // set the (i,j) pixel value
}
}
// Kernel Calling Function
extern "C" void sobel_parallel( unsigned char* h_in, unsigned char* h_out,
int rows, int cols, int widthStep){
unsigned char* d_in;
unsigned char* d_out;
cudaMalloc((void**) &d_in, rows*cols);
cudaMalloc((void**) &d_out, rows*cols);
cudaMemcpy(d_in, h_in, rows*cols*sizeof( unsigned char), cudaMemcpyHostToDevice);
dim3 block (16,16);
dim3 grid ((rows * cols) / 256.0);
kernel<<<grid,block>>>(d_in, d_out, rows, cols, widthStep);
cudaMemcpy(h_out, d_out, rows*cols*sizeof( unsigned char), cudaMemcpyDeviceToHost);
cudaFree(d_in);
cudaFree(d_out);
}
Error :
the result image does not appear in their entirety, only part of the image.
Why is the result(GPU) like this?? (I tried to make CPU computation using the same function and no problem).
You are creating 1 Dimensional grid, while using 2D indexing inside the kernel which will cover only the x direction and only the top 16 rows of the image will be filtered (because the height of the block is 16).
dim3 grid ((rows * cols) / 256.0); //This is incorrect in current case
Consider creating 2 dimensional grid, so that it spans all the rows of the image.
dim3 grid ((cols + 15)/16, (rows + 15)/16);
Check the width and widthStep variables to see if they are actually equal or not because in your sobel_parallel function you are implicitly assuming this (which might not be true since your data is aligned). If this is not true the code
cudaMalloc((void**) &d_in, rows*cols);
will actually allocate less memory than necessary and hence you will only process part of your image. It would be better to use
cudaMalloc((void**) &d_in, rows*widthStep);
And of course adjust the rest of your code as necessary.
You are also calling
void sobel_parallel( unsigned char* h_in, unsigned char* h_out,
int rows, int cols, int widthStep)
with
sobel_parallel(h_in, h_out, width, height, widthStep);
which exchanges rows with cols and this is again exchanged when you are calling your kernel. This will cause a problem when you use the above suggestion.
I have a sample image:
I apply the affine transform with the following warp matrix:
[[ 1.25 0. -128 ]
[ 0. 2. -192 ]]
and crop a 128x128 part from the result to get an output image:
Now, I want to estimate the warp matrix and crop size/location from just comparing the sample and output image. I detect feature points using SURF, and match them by brute force:
There are many matches, of which I'm keeping the best three (by distance), since that is the number required to estimate the affine transform. I then use those 3 keypoints to estimate the affine transform using getAffineTransform. However, the transform it returns is completely wrong:
-0.00 1.87 -6959230028596648489132997794229911552.00
0.00 -1.76 -0.00
What am I doing wrong? Source code is below.
Perform affine transform (Python):
"""Apply an affine transform to an image."""
import cv
import sys
import numpy as np
if len(sys.argv) != 10:
print "usage: %s in.png out.png x1 y1 width height sx sy flip" % __file__
sys.exit(-1)
source = cv.LoadImage(sys.argv[1])
x1, y1, width, height, sx, sy, flip = map(float, sys.argv[3:])
X, Y = cv.GetSize(source)
Xn, Yn = int(sx*(X-1)), int(sy*(Y-1))
if flip:
arr = np.array([[-sx, 0, sx*(X-1)-x1], [0, sy, -y1]])
else:
arr = np.array([[sx, 0, -x1], [0, sy, -y1]])
print arr
warp = cv.fromarray(arr)
cv.ShowImage("source", source)
dest = cv.CreateImage((Xn, Yn), source.depth, source.nChannels)
cv.WarpAffine(source, dest, warp)
cv.SetImageROI(dest, (0, 0, int(width), int(height)))
cv.ShowImage("dest", dest)
cv.SaveImage(sys.argv[2], dest)
cv.WaitKey(0)
Estimate affine transform from two images (C++):
#include <stdio.h>
#include <iostream>
#include <opencv2/core/core.hpp>
#include <opencv2/features2d/features2d.hpp>
#include <opencv2/calib3d/calib3d.hpp>
#include <opencv2/highgui/highgui.hpp>
#include <opencv2/nonfree/nonfree.hpp>
#include <opencv2/imgproc/imgproc.hpp>
#include <algorithm>
using namespace cv;
void readme();
bool cmpfun(DMatch a, DMatch b) { return a.distance < b.distance; }
/** #function main */
int main( int argc, char** argv )
{
if( argc != 3 )
{
return -1;
}
Mat img_1 = imread( argv[1], CV_LOAD_IMAGE_GRAYSCALE );
Mat img_2 = imread( argv[2], CV_LOAD_IMAGE_GRAYSCALE );
if( !img_1.data || !img_2.data )
{
return -1;
}
//-- Step 1: Detect the keypoints using SURF Detector
int minHessian = 400;
SurfFeatureDetector detector( minHessian );
std::vector<KeyPoint> keypoints_1, keypoints_2;
detector.detect( img_1, keypoints_1 );
detector.detect( img_2, keypoints_2 );
//-- Step 2: Calculate descriptors (feature vectors)
SurfDescriptorExtractor extractor;
Mat descriptors_1, descriptors_2;
extractor.compute( img_1, keypoints_1, descriptors_1 );
extractor.compute( img_2, keypoints_2, descriptors_2 );
//-- Step 3: Matching descriptor vectors with a brute force matcher
BFMatcher matcher(NORM_L2, false);
std::vector< DMatch > matches;
matcher.match( descriptors_1, descriptors_2, matches );
double max_dist = 0;
double min_dist = 100;
//-- Quick calculation of max and min distances between keypoints
for( int i = 0; i < descriptors_1.rows; i++ )
{ double dist = matches[i].distance;
if( dist < min_dist ) min_dist = dist;
if( dist > max_dist ) max_dist = dist;
}
printf("-- Max dist : %f \n", max_dist );
printf("-- Min dist : %f \n", min_dist );
//-- Draw only "good" matches (i.e. whose distance is less than 2*min_dist )
//-- PS.- radiusMatch can also be used here.
sort(matches.begin(), matches.end(), cmpfun);
std::vector< DMatch > good_matches;
vector<Point2f> match1, match2;
for (int i = 0; i < 3; ++i)
{
good_matches.push_back( matches[i]);
Point2f pt1 = keypoints_1[matches[i].queryIdx].pt;
Point2f pt2 = keypoints_2[matches[i].trainIdx].pt;
match1.push_back(pt1);
match2.push_back(pt2);
printf("%3d pt1: (%.2f, %.2f) pt2: (%.2f, %.2f)\n", i, pt1.x, pt1.y, pt2.x, pt2.y);
}
//-- Draw matches
Mat img_matches;
drawMatches( img_1, keypoints_1, img_2, keypoints_2, good_matches, img_matches,
Scalar::all(-1), Scalar::all(-1), vector<char>(), DrawMatchesFlags::NOT_DRAW_SINGLE_POINTS);
//-- Show detected matches
imshow("Matches", img_matches );
imwrite("matches.png", img_matches);
waitKey(0);
Mat fun = getAffineTransform(match1, match2);
for (int i = 0; i < fun.rows; ++i)
{
for (int j = 0; j < fun.cols; j++)
{
printf("%.2f ", fun.at<float>(i,j));
}
printf("\n");
}
return 0;
}
/** #function readme */
void readme()
{
std::cout << " Usage: ./SURF_descriptor <img1> <img2>" << std::endl;
}
The cv::Mat getAffineTransform returns is made of doubles, not of floats. The matrix you get probably is fine, you just have to change the printf command in your loops to
printf("%.2f ", fun.at<double>(i,j));
or even easier: Replace this manual output with
std::cout << fun << std::endl;
It's shorter and you don't have to care about data types yourself.
I want to load the image in opencv and split the image into channels(RGB) and i want to increase any one of the colors and getting that corresponding output image.is there any easiest way to do this problem?
Well to add any scalar to an RGB image you can use cvAddS(srcImage, scalarToAdd, dstImage).
Here is an example:
int main(int argc, char** argv)
{
// Create a named window with the name of the file.
cvNamedWindow( argv[1], 1 );
// Load the image from the given file name.
IplImage* img = cvLoadImage( argv[1] );
//Make a scalar to add 30 to Blue Color and 20 to Red (BGR format)
CvScalar colorAdd = cvScalar(30.0, 0, 20.0);
cvAddS(img, colorAdd, img);
// Show the image in the named window
cvShowImage( argv[1], img );
// Idle until the user hits the “Esc” key.
while( 1 ) {
if( cvWaitKey( 100 ) == 27 ) break;
}
cvDestroyWindow( argv[1] );
cvReleaseImage( &img );
exit(0);
}
Haven't tested the code, hope it helps.
#karlphillip: Generally a better solution for RGB images - handles any padding at row ends, also parallelizes nicely with OMP !
for (int i=0; i < height;i++)
{
unsigned char *pRow = pRGBImg->ptr(i);
for (int j=0; j < width;j+=bpp)
// For educational puporses, here is how to print each R G B channel:
std::cout << std::dec << "R:" << (int) pRow->imageData[j] <<
" G:" << (int) pRow->imageData[j+1] <<
" B:" << (int) pRow->imageData[j+2] << " ";
}
}
With the OpenCV C++ interface you can simply add a Scalar to an image with the overloaded arithmetic operators.
int main(int argc, const char * argv[]) {
cv::Mat image;
// read an image
if (argc < 2)
return 2;
image = cv::imread(argv[1]);
if (!image.data) {
std::cout << "Image file not found\n";
return 1;
}
cv::Mat image2 = image.clone(); // Make a deep copy of the image
image2 += cv::Scalar(30,0,20); // Add 30 to blue, 20 to red
cv::namedWindow("original");
cv::imshow("original", image);
cv::namedWindow("addcolors");
cv::imshow("addcolors", image2);
cv::waitKey(0);
return 0;
}
Another option is to manually iterate on the pixels of the image and work on the channel that interests you. This will give you the flexibility to manipulate each channel individually or as a group.
The following code uses the C interface of OpenCV:
IplImage* pRGBImg = cvLoadImage("test.png", CV_LOAD_IMAGE_UNCHANGED);
int width = pRGBImg->width;
int height = pRGBImg->height;
int bpp = pRGBImg->nChannels;
for (int i=0; i < width*height*bpp; i+=bpp)
{
// For educational puporses, here is how to print each R G B channel:
std::cout << std::dec << "R:" << (int) pRGBImg->imageData[i] <<
" G:" << (int) pRGBImg->imageData[i+1] <<
" B:" << (int) pRGBImg->imageData[i+2] << " ";
}
However, if you want to add a fixed value to a certain channel you might want to check #Popovici's answer.
Does anybody know how to find the local maxima in a grayscale IPL_DEPTH_8U image using OpenCV? HarrisCorner mentions something like that but I'm actually not interested in corners ...
Thanks!
A pixel is considered a local maximum if it is equal to the maximum value in a 'local' neighborhood. The function below captures this property in two lines of code.
To deal with pixels on 'plateaus' (value equal to their neighborhood) one can use the local minimum property, since plateaus pixels are equal to their local minimum. The rest of the code filters out those pixels.
void non_maxima_suppression(const cv::Mat& image, cv::Mat& mask, bool remove_plateaus) {
// find pixels that are equal to the local neighborhood not maximum (including 'plateaus')
cv::dilate(image, mask, cv::Mat());
cv::compare(image, mask, mask, cv::CMP_GE);
// optionally filter out pixels that are equal to the local minimum ('plateaus')
if (remove_plateaus) {
cv::Mat non_plateau_mask;
cv::erode(image, non_plateau_mask, cv::Mat());
cv::compare(image, non_plateau_mask, non_plateau_mask, cv::CMP_GT);
cv::bitwise_and(mask, non_plateau_mask, mask);
}
}
Here's a simple trick. The idea is to dilate with a kernel that contains a hole in the center. After the dilate operation, each pixel is replaced with the maximum of it's neighbors (using a 5 by 5 neighborhood in this example), excluding the original pixel.
Mat1b kernelLM(Size(5, 5), 1u);
kernelLM.at<uchar>(2, 2) = 0u;
Mat imageLM;
dilate(image, imageLM, kernelLM);
Mat1b localMaxima = (image > imageLM);
Actually after I posted the code above I wrote a better and very very faster one ..
The code above suffers even for a 640x480 picture..
I optimized it and now it is very very fast even for 1600x1200 pic.
Here is the code :
void localMaxima(cv::Mat src,cv::Mat &dst,int squareSize)
{
if (squareSize==0)
{
dst = src.clone();
return;
}
Mat m0;
dst = src.clone();
Point maxLoc(0,0);
//1.Be sure to have at least 3x3 for at least looking at 1 pixel close neighbours
// Also the window must be <odd>x<odd>
SANITYCHECK(squareSize,3,1);
int sqrCenter = (squareSize-1)/2;
//2.Create the localWindow mask to get things done faster
// When we find a local maxima we will multiply the subwindow with this MASK
// So that we will not search for those 0 values again and again
Mat localWindowMask = Mat::zeros(Size(squareSize,squareSize),CV_8U);//boolean
localWindowMask.at<unsigned char>(sqrCenter,sqrCenter)=1;
//3.Find the threshold value to threshold the image
//this function here returns the peak of histogram of picture
//the picture is a thresholded picture it will have a lot of zero values in it
//so that the second boolean variable says :
// (boolean) ? "return peak even if it is at 0" : "return peak discarding 0"
int thrshld = maxUsedValInHistogramData(dst,false);
threshold(dst,m0,thrshld,1,THRESH_BINARY);
//4.Now delete all thresholded values from picture
dst = dst.mul(m0);
//put the src in the middle of the big array
for (int row=sqrCenter;row<dst.size().height-sqrCenter;row++)
for (int col=sqrCenter;col<dst.size().width-sqrCenter;col++)
{
//1.if the value is zero it can not be a local maxima
if (dst.at<unsigned char>(row,col)==0)
continue;
//2.the value at (row,col) is not 0 so it can be a local maxima point
m0 = dst.colRange(col-sqrCenter,col+sqrCenter+1).rowRange(row-sqrCenter,row+sqrCenter+1);
minMaxLoc(m0,NULL,NULL,NULL,&maxLoc);
//if the maximum location of this subWindow is at center
//it means we found the local maxima
//so we should delete the surrounding values which lies in the subWindow area
//hence we will not try to find if a point is at localMaxima when already found a neighbour was
if ((maxLoc.x==sqrCenter)&&(maxLoc.y==sqrCenter))
{
m0 = m0.mul(localWindowMask);
//we can skip the values that we already made 0 by the above function
col+=sqrCenter;
}
}
}
The following listing is a function similar to Matlab's "imregionalmax". It looks for at most nLocMax local maxima above threshold, where the found local maxima are at least minDistBtwLocMax pixels apart. It returns the actual number of local maxima found. Notice that it uses OpenCV's minMaxLoc to find global maxima. It is "opencv-self-contained" except for the (easy to implement) function vdist, which computes the (euclidian) distance between points (r,c) and (row,col).
input is one-channel CV_32F matrix, and locations is nLocMax (rows) by 2 (columns) CV_32S matrix.
int imregionalmax(Mat input, int nLocMax, float threshold, float minDistBtwLocMax, Mat locations)
{
Mat scratch = input.clone();
int nFoundLocMax = 0;
for (int i = 0; i < nLocMax; i++) {
Point location;
double maxVal;
minMaxLoc(scratch, NULL, &maxVal, NULL, &location);
if (maxVal > threshold) {
nFoundLocMax += 1;
int row = location.y;
int col = location.x;
locations.at<int>(i,0) = row;
locations.at<int>(i,1) = col;
int r0 = (row-minDistBtwLocMax > -1 ? row-minDistBtwLocMax : 0);
int r1 = (row+minDistBtwLocMax < scratch.rows ? row+minDistBtwLocMax : scratch.rows-1);
int c0 = (col-minDistBtwLocMax > -1 ? col-minDistBtwLocMax : 0);
int c1 = (col+minDistBtwLocMax < scratch.cols ? col+minDistBtwLocMax : scratch.cols-1);
for (int r = r0; r <= r1; r++) {
for (int c = c0; c <= c1; c++) {
if (vdist(Point2DMake(r, c),Point2DMake(row, col)) <= minDistBtwLocMax) {
scratch.at<float>(r,c) = 0.0;
}
}
}
} else {
break;
}
}
return nFoundLocMax;
}
The first question to answer would be what is "local" in your opinion. The answer may well be a square window (say 3x3 or 5x5) or circular window of a certain radius. You can then scan over the entire image with the window centered at each pixel and pick the highest value in the window.
See this for how to access pixel values in OpenCV.
This is very fast method. It stored founded maxima in a vector of
Points.
vector <Point> GetLocalMaxima(const cv::Mat Src,int MatchingSize, int Threshold, int GaussKernel )
{
vector <Point> vMaxLoc(0);
if ((MatchingSize % 2 == 0) || (GaussKernel % 2 == 0)) // MatchingSize and GaussKernel have to be "odd" and > 0
{
return vMaxLoc;
}
vMaxLoc.reserve(100); // Reserve place for fast access
Mat ProcessImg = Src.clone();
int W = Src.cols;
int H = Src.rows;
int SearchWidth = W - MatchingSize;
int SearchHeight = H - MatchingSize;
int MatchingSquareCenter = MatchingSize/2;
if(GaussKernel > 1) // If You need a smoothing
{
GaussianBlur(ProcessImg,ProcessImg,Size(GaussKernel,GaussKernel),0,0,4);
}
uchar* pProcess = (uchar *) ProcessImg.data; // The pointer to image Data
int Shift = MatchingSquareCenter * ( W + 1);
int k = 0;
for(int y=0; y < SearchHeight; ++y)
{
int m = k + Shift;
for(int x=0;x < SearchWidth ; ++x)
{
if (pProcess[m++] >= Threshold)
{
Point LocMax;
Mat mROI(ProcessImg, Rect(x,y,MatchingSize,MatchingSize));
minMaxLoc(mROI,NULL,NULL,NULL,&LocMax);
if (LocMax.x == MatchingSquareCenter && LocMax.y == MatchingSquareCenter)
{
vMaxLoc.push_back(Point( x+LocMax.x,y + LocMax.y ));
// imshow("W1",mROI);cvWaitKey(0); //For gebug
}
}
}
k += W;
}
return vMaxLoc;
}
Found a simple solution.
In this example, if you are trying to find 2 results of a matchTemplate function with a minimum distance from each other.
cv::Mat result;
matchTemplate(search, target, result, CV_TM_SQDIFF_NORMED);
float score1;
cv::Point displacement1 = MinMax(result, score1);
cv::circle(result, cv::Point(displacement1.x+result.cols/2 , displacement1.y+result.rows/2), 10, cv::Scalar(0), CV_FILLED, 8, 0);
float score2;
cv::Point displacement2 = MinMax(result, score2);
where
cv::Point MinMax(cv::Mat &result, float &score)
{
double minVal, maxVal;
cv::Point minLoc, maxLoc, matchLoc;
minMaxLoc(result, &minVal, &maxVal, &minLoc, &maxLoc, cv::Mat());
matchLoc.x = minLoc.x - result.cols/2;
matchLoc.y = minLoc.y - result.rows/2;
return minVal;
}
The process is:
Find global Minimum using minMaxLoc
Draw a filled white circle around global minimum using min distance between minima as radius
Find another minimum
The the scores can be compared to each other to determine, for example, the certainty of the match,
To find more than just the global minimum and maximum try using this function from skimage:
http://scikit-image.org/docs/dev/api/skimage.feature.html#skimage.feature.peak_local_max
You can parameterize the minimum distance between peaks, too. And more. To find minima, use negated values (take care of the array type though, 255-image could do the trick).
You can go over each pixel and test if it is a local maxima. Here is how I would do it.
The input is assumed to be type CV_32FC1
#include <vector>//std::vector
#include <algorithm>//std::sort
#include "opencv2/imgproc/imgproc.hpp"
#include "opencv2/core/core.hpp"
//structure for maximal values including position
struct SRegionalMaxPoint
{
SRegionalMaxPoint():
values(-FLT_MAX),
row(-1),
col(-1)
{}
float values;
int row;
int col;
//ascending order
bool operator()(const SRegionalMaxPoint& a, const SRegionalMaxPoint& b)
{
return a.values < b.values;
}
};
//checks if pixel is local max
bool isRegionalMax(const float* im_ptr, const int& cols )
{
float center = *im_ptr;
bool is_regional_max = true;
im_ptr -= (cols + 1);
for (int ii = 0; ii < 3; ++ii, im_ptr+= (cols-3))
{
for (int jj = 0; jj < 3; ++jj, im_ptr++)
{
if (ii != 1 || jj != 1)
{
is_regional_max &= (center > *im_ptr);
}
}
}
return is_regional_max;
}
void imregionalmax(
const cv::Mat& input,
std::vector<SRegionalMaxPoint>& buffer)
{
//find local max - top maxima
static const int margin = 1;
const int rows = input.rows;
const int cols = input.cols;
for (int i = margin; i < rows - margin; ++i)
{
const float* im_ptr = input.ptr<float>(i, margin);
for (int j = margin; j < cols - margin; ++j, im_ptr++)
{
//Check if pixel is local maximum
if ( isRegionalMax(im_ptr, cols ) )
{
cv::Rect roi = cv::Rect(j - margin, i - margin, 3, 3);
cv::Mat subMat = input(roi);
float val = *im_ptr;
//replace smallest value in buffer
if ( val > buffer[0].values )
{
buffer[0].values = val;
buffer[0].row = i;
buffer[0].col = j;
std::sort(buffer.begin(), buffer.end(), SRegionalMaxPoint());
}
}
}
}
}
For testing the code you can try this:
cv::Mat temp = cv::Mat::zeros(15, 15, CV_32FC1);
temp.at<float>(7, 7) = 1;
temp.at<float>(3, 5) = 6;
temp.at<float>(8, 10) = 4;
temp.at<float>(11, 13) = 7;
temp.at<float>(10, 3) = 8;
temp.at<float>(7, 13) = 3;
vector<SRegionalMaxPoint> buffer_(5);
imregionalmax(temp, buffer_);
cv::Mat debug;
cv::cvtColor(temp, debug, cv::COLOR_GRAY2BGR);
for (auto it = buffer_.begin(); it != buffer_.end(); ++it)
{
circle(debug, cv::Point(it->col, it->row), 1, cv::Scalar(0, 255, 0));
}
This solution does not take plateaus into account so it is not exactly the same as matlab's imregionalmax()
I think you want to use the
MinMaxLoc(arr, mask=NULL)-> (minVal, maxVal, minLoc, maxLoc)
Finds global minimum and maximum in array or subarray
function on you image