Related
I'm new in OpenCV, and I want to thresholding the image by myself without using Threshold function in opencv, because the time spend on function threshold is to high for me.
Here is my code:
Mat src = imread("D:\\DataBox\\7.jpg", 0);
for (int i = 0; i < src.cols; i++) {
cout << i << endl;
for (int j = 0; j < src.rows; j++) {
if (src.at<uchar>(i, j) > 70) {
src.at<uchar>(i, j) = 0;
cout << j << endl;
}
else
src.at<uchar>(i, j) = 255;
}
}
but it still says:
"OpenCV Error: Assertion failed (dims <= 2 && data && (unsigned)i0 < (unsigned)size.p[0] && (unsigned)(i1 * DataType<_Tp>::channels) < (unsigned)(size.p[1] * channels()) && ((((sizeof(size_t)<<28)|0x8442211) >> ((DataType<_Tp>::depth) & ((1 << 3) - 1))*4) & 15) == elemSize1()) in cv::Mat::at, file C:\Program Files\opencv\build\include\opencv2/core/mat.inl.hpp, line 894"
I can print j from 0~719(since the size of the image is 720*960), but as long as the parameter i want to become 2 from 1, the error occurs.
You mixed up rows and cols:
Try this:
Mat src = imread("path_to_image", IMREAD_GRAYSCALE);
for (int i = 0; i < src.rows; i++)
{
//cout << i << endl;
for (int j = 0; j < src.cols; j++)
{
if (src.at<uchar>(i, j) > 70) {
src.at<uchar>(i, j) = 0;
//cout << j << endl;
}
else
src.at<uchar>(i, j) = 255;
}
}
This is, however very unlikely to perform better than OpenCV implementation. You can gain a little speed working on raw pointers, with a little trick to work on continuous data when possible:
#include <opencv2\opencv.hpp>
using namespace cv;
int main()
{
Mat src = imread("D:\\SO\\img\\nice.jpg", IMREAD_GRAYSCALE);
int rows = src.rows;
int cols = src.cols;
if (src.isContinuous())
{
cols = rows * cols;
rows = 1;
}
for (int i = 0; i < rows; i++)
{
uchar* pdata = src.ptr<uchar>(i);
int base = i*cols;
for (int j = 0; j < cols; j++)
{
if (pdata[base + j] > 70)
{
pdata[base + j] = 0;
}
else
{
pdata[base + j] = 255;
}
}
}
return 0;
}
Actually, on my PC my version is a little bit faster than OpenCV one:
Time #HenryChen (ms): 2.83266
Time #Miki (ms): 1.09597
Time #OpenCV (ms): 2.10727
You can test on your PC with the following code, since time depends on many factor, e.g. optimizations enabled in OpenCV:
#include <opencv2\opencv.hpp>
#include <iostream>
using namespace cv;
using namespace std;
int main()
{
Mat1b src(720,960);
randu(src, 0, 256);
Mat1b src1 = src.clone();
Mat1b src2 = src.clone();
Mat1b src3 = src.clone();
double tic1 = double(getTickCount());
// Method #HenryChen (corrected)
for (int i = 0; i < src1.rows; i++)
{
//cout << i << endl;
for (int j = 0; j < src1.cols; j++)
{
if (src1.at<uchar>(i, j) > 70) {
src1.at<uchar>(i, j) = 0;
//cout << j << endl;
}
else
src1.at<uchar>(i, j) = 255;
}
}
double toc1 = (double(getTickCount()) - tic1) * 1000.0 / getTickFrequency();
cout << "Time #HenryChen (ms): \t" << toc1 << endl;
//-------------------------------------
double tic2 = double(getTickCount());
// Method #Miki
int rows = src2.rows;
int cols = src2.cols;
if (src2.isContinuous())
{
cols = rows * cols;
rows = 1;
}
for (int i = 0; i < rows; i++)
{
uchar* pdata = src2.ptr<uchar>(0);
int base = i*cols;
for (int j = 0; j < cols; j++)
{
pdata[base + j] = (pdata[base + j] > 70) ? uchar(0) : uchar(255);
}
}
double toc2 = (double(getTickCount()) - tic2) * 1000.0 / getTickFrequency();
cout << "Time #Miki (ms): \t" << toc2 << endl;
//-------------------------------------
double tic3 = double(getTickCount());
// Method #OpenCV
threshold(src3, src3, 70, 255, THRESH_BINARY_INV);
double toc3 = (double(getTickCount()) - tic3) * 1000.0 / getTickFrequency();
cout << "Time #OpenCV (ms): \t" << toc3 << endl;
getchar();
return 0;
}
Use test.at<uchar>(cv::Point(i, j)) instead. I always get lost when accessing cv::Mat directly - cv::Point clears it up a little bit.
Anyway, I agree with Miki - it is very unlikely to create a function that performs better that a library one.
I am trying to train my own detector based on HOG features and i trained a detector with CvSVM utility of opencv. Now to use this detector in HOGDescriptor.SetSVM(myDetector), i need to get trained detector in row-vector (primal) form to feed. For this i am using this code. my implementation is like given below:
vector<float>primal;
void LinearSVM::getSupportVector(std::vector<float>& support_vector) {
CvSVM svm;
svm.load("Classifier.xml");
cin.get();
int sv_count = svm.get_support_vector_count();
const CvSVMDecisionFunc* df = decision_func;
const double* alphas = df[0].alpha;
double rho = df[0].rho;
int var_count = svm.get_var_count();
support_vector.resize(var_count, 0);
for (unsigned int r = 0; r < (unsigned)sv_count; r++) {
float myalpha = alphas[r];
const float* v = svm.get_support_vector(r);
for (int j = 0; j < var_count; j++,v++) {
support_vector[j] += (-myalpha) * (*v);
}
}
support_vector.push_back(rho);
}
int main()
{
LinearSVM s;
s.getSupportVector(primal);
return 0;
}
When i use built-in CvSVM, it shows me SV as 3 bec i have only 3 SV in my saved file but since the decision_func is in protected mode, hence i can not access it. That's why i tried to use that wrapper but still of no use. Perhaps you guys can help me out here... Thanks alot!
Answer with a test harness. I put in new answer as it would add allot of clutter to the original answer, possibly making it a bit confusing.
//dummy features
std:: vector<float>
dummyDerReaderForOneDer(const vector<float> &pattern)
{
int i = std::rand() % pattern.size();
int j = std::rand() % pattern.size();
vector<float> patternPulNoise(pattern);
std::random_shuffle(patternPulNoise.begin()+std::min(i,j),patternPulNoise.begin()+std::max(i,j));
return patternPulNoise;
};
//extend CvSVM to get access to weights
class mySVM : public CvSVM
{
public:
vector<float>
getWeightVector(const int descriptorSize);
};
//get the weights
vector<float>
mySVM::getWeightVector(const int descriptorSize)
{
vector<float> svmWeightsVec(descriptorSize+1);
int numSupportVectors = get_support_vector_count();
//this is protected, but can access due to inheritance rules
const CvSVMDecisionFunc *dec = CvSVM::decision_func;
const float *supportVector;
float* svmWeight = &svmWeightsVec[0];
for (int i = 0; i < numSupportVectors; ++i)
{
float alpha = *(dec[0].alpha + i);
supportVector = get_support_vector(i);
for(int j=0;j<descriptorSize;j++)
{
*(svmWeight + j) += alpha * *(supportVector+j);
}
}
*(svmWeight + descriptorSize) = - dec[0].rho;
return svmWeightsVec;
}
// main harness entry point for detector test
int main (int argc, const char * argv[])
{
//dummy variables for example
int posFiles = 10;
int negFiles = 10;
int dims = 1000;
int randomFactor = 4;
//setup some dummy data
vector<float> dummyPosPattern;
dummyPosPattern.assign(int(dims/randomFactor),1.f);
dummyPosPattern.resize(dims );
random_shuffle(dummyPosPattern.begin(),dummyPosPattern.end());
vector<float> dummyNegPattern;
dummyNegPattern.assign(int(dims/randomFactor),1.f);
dummyNegPattern.resize(dims );
random_shuffle(dummyNegPattern.begin(),dummyNegPattern.end());
// the labels and lables mat
float posLabel = 1.f;
float negLabel = 2.f;
cv::Mat cSvmLabels;
//the data mat
cv::Mat cSvmTrainingData;
//dummy linear svm parmas
SVMParams cSvmParams;
cSvmParams.svm_type = cv::SVM::C_SVC;
cSvmParams.C = 0.0100;
cSvmParams.kernel_type = cv::SVM::LINEAR;
cSvmParams.term_crit = cv::TermCriteria(CV_TERMCRIT_ITER+CV_TERMCRIT_EPS, 1000000, FLT_EPSILON);
cout << "creating training data. please wait" << endl;
int i;
for(i=0;i<posFiles;i++)
{
//your feature for one box from file
vector<float> d = dummyDerReaderForOneDer(dummyPosPattern);
//push back a new mat made from the vectors data, with copy data flag on
//this shows the format of the mat for a single example, (1 (row) X dims(col) ), as training mat has each **row** as an example;
//the push_back works like vector add adds each example to the bottom of the matrix
cSvmTrainingData.push_back(cv::Mat(1,dims,CV_32FC1,d.data(),true));
//push back a pos label to the labels mat
cSvmLabels.push_back(posLabel);
}
//do same with neg files;
for(i=0;i<negFiles;i++)
{
float a = rand();
vector<float> d = dummyDerReaderForOneDer(dummyNegPattern);
cSvmTrainingData.push_back(cv::Mat(1,dims,CV_32FC1,d.data(),true));
cSvmLabels.push_back(negLabel);
}
//have a look
cv::Mat viz;
cSvmTrainingData.convertTo(viz,CV_8UC3);
viz = viz*255;
cv::imshow("svmData", viz);
cv::waitKey(10);
cout << "press any key to continue" << endl;
getchar();
viz.release();
//create the svm;
cout << "training, please wait" << endl;
mySVM svm;
svm.train(cSvmTrainingData,cSvmLabels,cv::Mat(),cv::Mat(),cSvmParams);
cout << "get weights" << endl;
vector<float> svmWeights = svm.getWeightVector(dims);
for(i=0; i<dims+1; i++)
{
cout << svmWeights[i] << ", ";
if(i==dims)
{
cout << endl << "bias: " << svmWeights[i] << endl;
}
}
cout << "press any key to continue" << endl;
getchar();
cout << "testing, please wait" << endl;
//test the svm with a large amount of new unseen fake one at a time
int totExamples = 10;
int k;
for(i=0;i<totExamples; i++)
{
cout << endl << endl;
vector<float> dPos = dummyDerReaderForOneDer(dummyPosPattern);
cv::Mat dMatPos(1,dims,CV_32FC1,dPos.data(),true);
float predScoreFromDual = svm.predict(dMatPos,true);
float predScoreBFromPrimal = svmWeights[dims];
for( k = 0; k <= dims - 4; k += 4 )
predScoreBFromPrimal += dPos[k]*svmWeights[k] + dPos[k+1]*svmWeights[k+1] +
dPos[k+2]*svmWeights[k+2] + dPos[k+3]*svmWeights[k+3];
for( ; k < dims; k++ )
predScoreBFromPrimal += dPos[k]*svmWeights[k];
cout << "Dual Score:\t" << predScoreFromDual << "\tPrimal Score:\t" << predScoreBFromPrimal << endl;
}
cout << "press any key to continue" << endl;
getchar();
return(0);
}
Hello again :) please extend the cvsm class rather than encapsulating it, as you need access to protected member.
//header
class mySVM : public CvSVM
{
public:
vector<float>
getWeightVector(const int descriptorSize);
};
//cpp
vector<float>
mySVM::getWeightVector(const int descriptorSize)
{
vector<float> svmWeightsVec(descriptorSize+1);
int numSupportVectors = get_support_vector_count();
//this is protected, but can access due to inheritance rules
const CvSVMDecisionFunc *dec = CvSVM::decision_func;
const float *supportVector;
float* svmWeight = &svmWeightsVec[0];
for (int i = 0; i < numSupportVectors; ++i)
{
float alpha = *(dec[0].alpha + i);
supportVector = get_support_vector(i);
for(int j=0;j<descriptorSize;j++)
{
*(svmWeight + j) += alpha * *(supportVector+j);
}
}
*(svmWeight + descriptorSize) = - dec[0].rho;
return svmWeightsVec;
}
something like that.
credits:
Obtaining weights in CvSVM, the SVM implementation of OpenCV
I am trying to carry out multi-thresholding with otsu. The method I am using currently is actually via maximising the between class variance, I have managed to get the same threshold value given as that by the OpenCV library. However, that is just via running otsu method once.
Documentation on how to do multi-level thresholding or rather recursive thresholding is rather limited. Where do I do after obtaining the original otsu's value? Would appreciate some hints, I been playing around with the code, adding one external for loop, but the next value calculated is always 254 for any given image:(
My code if need be:
//compute histogram first
cv::Mat imageh; //image edited to grayscale for histogram purpose
//imageh=image; //to delete and uncomment below;
cv::cvtColor(image, imageh, CV_BGR2GRAY);
int histSize[1] = {256}; // number of bins
float hranges[2] = {0.0, 256.0}; // min andax pixel value
const float* ranges[1] = {hranges};
int channels[1] = {0}; // only 1 channel used
cv::MatND hist;
// Compute histogram
calcHist(&imageh, 1, channels, cv::Mat(), hist, 1, histSize, ranges);
IplImage* im = new IplImage(imageh);//assign the image to an IplImage pointer
IplImage* finalIm = cvCreateImage(cvSize(im->width, im->height), IPL_DEPTH_8U, 1);
double otsuThreshold= cvThreshold(im, finalIm, 0, 255, cv::THRESH_BINARY | cv::THRESH_OTSU );
cout<<"opencv otsu gives "<<otsuThreshold<<endl;
int totalNumberOfPixels= imageh.total();
cout<<"total number of Pixels is " <<totalNumberOfPixels<< endl;
float sum = 0;
for (int t=0 ; t<256 ; t++)
{
sum += t * hist.at<float>(t);
}
cout<<"sum is "<<sum<<endl;
float sumB = 0; //sum of background
int wB = 0; // weight of background
int wF = 0; //weight of foreground
float varMax = 0;
int threshold = 0;
//run an iteration to find the maximum value of the between class variance(as between class variance shld be maximise)
for (int t=0 ; t<256 ; t++)
{
wB += hist.at<float>(t); // Weight Background
if (wB == 0) continue;
wF = totalNumberOfPixels - wB; // Weight Foreground
if (wF == 0) break;
sumB += (float) (t * hist.at<float>(t));
float mB = sumB / wB; // Mean Background
float mF = (sum - sumB) / wF; // Mean Foreground
// Calculate Between Class Variance
float varBetween = (float)wB * (float)wF * (mB - mF) * (mB - mF);
// Check if new maximum found
if (varBetween > varMax) {
varMax = varBetween;
threshold = t;
}
}
cout<<"threshold value is: "<<threshold;
To extend Otsu's thresholding method to multi-level thresholding the between class variance equation becomes:
Please check out Deng-Yuan Huang, Ta-Wei Lin, Wu-Chih Hu, Automatic
Multilevel Thresholding Based on Two-Stage Otsu's Method with Cluster
Determination by Valley Estimation, Int. Journal of Innovative
Computing, 2011, 7:5631-5644 for more information.
http://www.ijicic.org/ijicic-10-05033.pdf
Here is my C# implementation of Otsu Multi for 2 thresholds:
/* Otsu (1979) - multi */
Tuple < int, int > otsuMulti(object sender, EventArgs e) {
//image histogram
int[] histogram = new int[256];
//total number of pixels
int N = 0;
//accumulate image histogram and total number of pixels
foreach(int intensity in image.Data) {
if (intensity != 0) {
histogram[intensity] += 1;
N++;
}
}
double W0K, W1K, W2K, M0, M1, M2, currVarB, optimalThresh1, optimalThresh2, maxBetweenVar, M0K, M1K, M2K, MT;
optimalThresh1 = 0;
optimalThresh2 = 0;
W0K = 0;
W1K = 0;
M0K = 0;
M1K = 0;
MT = 0;
maxBetweenVar = 0;
for (int k = 0; k <= 255; k++) {
MT += k * (histogram[k] / (double) N);
}
for (int t1 = 0; t1 <= 255; t1++) {
W0K += histogram[t1] / (double) N; //Pi
M0K += t1 * (histogram[t1] / (double) N); //i * Pi
M0 = M0K / W0K; //(i * Pi)/Pi
W1K = 0;
M1K = 0;
for (int t2 = t1 + 1; t2 <= 255; t2++) {
W1K += histogram[t2] / (double) N; //Pi
M1K += t2 * (histogram[t2] / (double) N); //i * Pi
M1 = M1K / W1K; //(i * Pi)/Pi
W2K = 1 - (W0K + W1K);
M2K = MT - (M0K + M1K);
if (W2K <= 0) break;
M2 = M2K / W2K;
currVarB = W0K * (M0 - MT) * (M0 - MT) + W1K * (M1 - MT) * (M1 - MT) + W2K * (M2 - MT) * (M2 - MT);
if (maxBetweenVar < currVarB) {
maxBetweenVar = currVarB;
optimalThresh1 = t1;
optimalThresh2 = t2;
}
}
}
return new Tuple(optimalThresh1, optimalThresh2);
}
And this is the result I got by thresholding an image scan of soil with the above code:
(T1 = 110, T2 = 147).
Otsu's original paper: "Nobuyuki Otsu, A Threshold Selection Method
from Gray-Level Histogram, IEEE Transactions on Systems, Man, and
Cybernetics, 1979, 9:62-66" also briefly mentions the extension to
Multithresholding.
https://engineering.purdue.edu/kak/computervision/ECE661.08/OTSU_paper.pdf
Hope this helps.
Here is a simple general approach for 'n' thresholds in python (>3.0) :
# developed by- SUJOY KUMAR GOSWAMI
# source paper- https://people.ece.cornell.edu/acharya/papers/mlt_thr_img.pdf
import cv2
import numpy as np
import math
img = cv2.imread('path-to-image')
img = cv2.cvtColor(img, cv2.COLOR_BGR2GRAY)
a = 0
b = 255
n = 6 # number of thresholds (better choose even value)
k = 0.7 # free variable to take any positive value
T = [] # list which will contain 'n' thresholds
def sujoy(img, a, b):
if a>b:
s=-1
m=-1
return m,s
img = np.array(img)
t1 = (img>=a)
t2 = (img<=b)
X = np.multiply(t1,t2)
Y = np.multiply(img,X)
s = np.sum(X)
m = np.sum(Y)/s
return m,s
for i in range(int(n/2-1)):
img = np.array(img)
t1 = (img>=a)
t2 = (img<=b)
X = np.multiply(t1,t2)
Y = np.multiply(img,X)
mu = np.sum(Y)/np.sum(X)
Z = Y - mu
Z = np.multiply(Z,X)
W = np.multiply(Z,Z)
sigma = math.sqrt(np.sum(W)/np.sum(X))
T1 = mu - k*sigma
T2 = mu + k*sigma
x, y = sujoy(img, a, T1)
w, z = sujoy(img, T2, b)
T.append(x)
T.append(w)
a = T1+1
b = T2-1
k = k*(i+1)
T1 = mu
T2 = mu+1
x, y = sujoy(img, a, T1)
w, z = sujoy(img, T2, b)
T.append(x)
T.append(w)
T.sort()
print(T)
For full paper and more informations visit this link.
I've written an example on how otsu thresholding work in python before. You can see the source code here: https://github.com/subokita/Sandbox/blob/master/otsu.py
In the example there's 2 variants, otsu2() which is the optimised version, as seen on Wikipedia page, and otsu() which is more naive implementation based on the algorithm description itself.
If you are okay in reading python codes (in this case, they are pretty simple, almost pseudo code like), you might want to look at otsu() in the example and modify it. Porting it to C++ code is not hard either.
#Antoni4 gives the best answer in my opinion and it's very straight forward to increase the number of levels.
This is for three-level thresholding:
#include "Shadow01-1.cuh"
void multiThresh(double &optimalThresh1, double &optimalThresh2, double &optimalThresh3, cv::Mat &imgHist, cv::Mat &src)
{
double W0K, W1K, W2K, W3K, M0, M1, M2, M3, currVarB, maxBetweenVar, M0K, M1K, M2K, M3K, MT;
unsigned char *histogram = (unsigned char*)(imgHist.data);
int N = src.rows*src.cols;
W0K = 0;
W1K = 0;
M0K = 0;
M1K = 0;
MT = 0;
maxBetweenVar = 0;
for (int k = 0; k <= 255; k++) {
MT += k * (histogram[k] / (double) N);
}
for (int t1 = 0; t1 <= 255; t1++)
{
W0K += histogram[t1] / (double) N; //Pi
M0K += t1 * (histogram[t1] / (double) N); //i * Pi
M0 = M0K / W0K; //(i * Pi)/Pi
W1K = 0;
M1K = 0;
for (int t2 = t1 + 1; t2 <= 255; t2++)
{
W1K += histogram[t2] / (double) N; //Pi
M1K += t2 * (histogram[t2] / (double) N); //i * Pi
M1 = M1K / W1K; //(i * Pi)/Pi
W2K = 1 - (W0K + W1K);
M2K = MT - (M0K + M1K);
if (W2K <= 0) break;
M2 = M2K / W2K;
W3K = 0;
M3K = 0;
for (int t3 = t2 + 1; t3 <= 255; t3++)
{
W2K += histogram[t3] / (double) N; //Pi
M2K += t3 * (histogram[t3] / (double) N); // i*Pi
M2 = M2K / W2K; //(i*Pi)/Pi
W3K = 1 - (W1K + W2K);
M3K = MT - (M1K + M2K);
M3 = M3K / W3K;
currVarB = W0K * (M0 - MT) * (M0 - MT) + W1K * (M1 - MT) * (M1 - MT) + W2K * (M2 - MT) * (M2 - MT) + W3K * (M3 - MT) * (M3 - MT);
if (maxBetweenVar < currVarB)
{
maxBetweenVar = currVarB;
optimalThresh1 = t1;
optimalThresh2 = t2;
optimalThresh3 = t3;
}
}
}
}
}
#Guilherme Silva
Your code has a BUG
You Must Replace:
W3K = 0;
M3K = 0;
with
W2K = 0;
M2K = 0;
and
W3K = 1 - (W1K + W2K);
M3K = MT - (M1K + M2K);
with
W3K = 1 - (W0K + W1K + W2K);
M3K = MT - (M0K + M1K + M2K);
;-)
Regards
EDIT(1): [Toby Speight]
I discovered this bug by applying the effect to the same picture at different resoultions(Sizes) and seeing that the output results were to much different from each others (Even changing resolution a little bit)
W3K and M3K must be the totals minus the Previous WKs and MKs.
(I thought about this for Code-similarity with the one with one level less)
At the moment due to my lacks of English I cannot explain Better How and Why
To be honest I'm still not 100% sure that this way is correct, even thought from my outputs I could tell that it gives better results. (Even with 1 Level more (5 shades of gray))
You could try yourself ;-)
Sorry
My Outputs:
3 Thresholds
4 Thresholds
I found a useful piece of code in this thread. I was looking for a multi-level Otsu implementation for double/float images. So, I tried to generalize example for N-levels with double/float matrix as input. In my code below I am using armadillo library as dependency. But this code can be easily adapted for standard C++ arrays, just replace vec, uvec objects with single dimensional double and integer arrays, mat and umat with two-dimensional. Two other functions from armadillo used here are: vectorise and hist.
// Input parameters:
// map - input image (double matrix)
// mask - region of interest to be thresholded
// nBins - number of bins
// nLevels - number of Otsu thresholds
#include <armadillo>
#include <algorithm>
#include <vector>
mat OtsuFilterMulti(mat map, int nBins, int nLevels) {
mat mapr; // output thresholded image
mapr = zeros<mat>(map.n_rows, map.n_cols);
unsigned int numElem = 0;
vec threshold = zeros<vec>(nLevels);
vec q = zeros<vec>(nLevels + 1);
vec mu = zeros<vec>(nLevels + 1);
vec muk = zeros<vec>(nLevels + 1);
uvec binv = zeros<uvec>(nLevels);
if (nLevels <= 1) return mapr;
numElem = map.n_rows*map.n_cols;
uvec histogram = hist(vectorise(map), nBins);
double maxval = map.max();
double minval = map.min();
double odelta = (maxval - abs(minval)) / nBins; // distance between histogram bins
vec oval = zeros<vec>(nBins);
double mt = 0, variance = 0.0, bestVariance = 0.0;
for (int ii = 0; ii < nBins; ii++) {
oval(ii) = (double)odelta*ii + (double)odelta*0.5; // centers of histogram bins
mt += (double)ii*((double)histogram(ii)) / (double)numElem;
}
for (int ii = 0; ii < nLevels; ii++) {
binv(ii) = ii;
}
double sq, smuk;
int nComb;
nComb = nCombinations(nBins,nLevels);
std::vector<bool> v(nBins);
std::fill(v.begin(), v.begin() + nLevels, true);
umat ibin = zeros<umat>(nComb, nLevels); // indices from combinations will be stored here
int cc = 0;
int ci = 0;
do {
for (int i = 0; i < nBins; ++i) {
if(ci==nLevels) ci=0;
if (v[i]) {
ibin(cc,ci) = i;
ci++;
}
}
cc++;
} while (std::prev_permutation(v.begin(), v.end()));
uvec lastIndex = zeros<uvec>(nLevels);
// Perform operations on pre-calculated indices
for (int ii = 0; ii < nComb; ii++) {
for (int jj = 0; jj < nLevels; jj++) {
smuk = 0;
sq = 0;
if (lastIndex(jj) != ibin(ii, jj) || ii == 0) {
q(jj) += double(histogram(ibin(ii, jj))) / (double)numElem;
muk(jj) += ibin(ii, jj)*(double(histogram(ibin(ii, jj)))) / (double)numElem;
mu(jj) = muk(jj) / q(jj);
q(jj + 1) = 0.0;
muk(jj + 1) = 0.0;
if (jj>0) {
for (int kk = 0; kk <= jj; kk++) {
sq += q(kk);
smuk += muk(kk);
}
q(jj + 1) = 1 - sq;
muk(jj + 1) = mt - smuk;
mu(jj + 1) = muk(jj + 1) / q(jj + 1);
}
if (jj>0 && jj<(nLevels - 1)) {
q(jj + 1) = 0.0;
muk(jj + 1) = 0.0;
}
lastIndex(jj) = ibin(ii, jj);
}
}
variance = 0.0;
for (int jj = 0; jj <= nLevels; jj++) {
variance += q(jj)*(mu(jj) - mt)*(mu(jj) - mt);
}
if (variance > bestVariance) {
bestVariance = variance;
for (int jj = 0; jj<nLevels; jj++) {
threshold(jj) = oval(ibin(ii, jj));
}
}
}
cout << "Optimized thresholds: ";
for (int jj = 0; jj<nLevels; jj++) {
cout << threshold(jj) << " ";
}
cout << endl;
for (unsigned int jj = 0; jj<map.n_rows; jj++) {
for (unsigned int kk = 0; kk<map.n_cols; kk++) {
for (int ll = 0; ll<nLevels; ll++) {
if (map(jj, kk) >= threshold(ll)) {
mapr(jj, kk) = ll+1;
}
}
}
}
return mapr;
}
int nCombinations(int n, int r) {
if (r>n) return 0;
if (r*2 > n) r = n-r;
if (r == 0) return 1;
int ret = n;
for( int i = 2; i <= r; ++i ) {
ret *= (n-i+1);
ret /= i;
}
return ret;
}
I'm using the Hough transform in OpenCV to detect lines. However, I know in advance that I only need lines within a very limited range of angles (about 10 degrees or so). I'm doing this in a very performance sensitive setting, so I'd like to avoid the extra work spent detecting lines at other angles, lines I know in advance I don't care about.
I could extract the Hough source from OpenCV and just hack it to take min_rho and max_rho parameters, but I'd like a less fragile approach (have to manually update my code w/ each OpenCV update, etc.).
What's the best approach here?
Well, i've modified the icvHoughlines function to go for a certain range of angles. I'm sure there's cleaner ways that plays with memory allocation as well, but I got a speed gain going from 100ms to 33ms for a range of angle going from 180deg to 60deg, so i'm happy with that.
Note that this code also outputs the accumulator value. Also, I only output 1 line because that fit my purposes but there was no gain really there.
static void
icvHoughLinesStandard2( const CvMat* img, float rho, float theta,
int threshold, CvSeq *lines, int linesMax )
{
cv::AutoBuffer<int> _accum, _sort_buf;
cv::AutoBuffer<float> _tabSin, _tabCos;
const uchar* image;
int step, width, height;
int numangle, numrho;
int total = 0;
float ang;
int r, n;
int i, j;
float irho = 1 / rho;
double scale;
CV_Assert( CV_IS_MAT(img) && CV_MAT_TYPE(img->type) == CV_8UC1 );
image = img->data.ptr;
step = img->step;
width = img->cols;
height = img->rows;
numangle = cvRound(CV_PI / theta);
numrho = cvRound(((width + height) * 2 + 1) / rho);
_accum.allocate((numangle+2) * (numrho+2));
_sort_buf.allocate(numangle * numrho);
_tabSin.allocate(numangle);
_tabCos.allocate(numangle);
int *accum = _accum, *sort_buf = _sort_buf;
float *tabSin = _tabSin, *tabCos = _tabCos;
memset( accum, 0, sizeof(accum[0]) * (numangle+2) * (numrho+2) );
// find n and ang limits (in our case we want 60 to 120
float limit_min = 60.0/180.0*PI;
float limit_max = 120.0/180.0*PI;
//num_steps = (limit_max - limit_min)/theta;
int start_n = floor(limit_min/theta);
int stop_n = floor(limit_max/theta);
for( ang = limit_min, n = start_n; n < stop_n; ang += theta, n++ )
{
tabSin[n] = (float)(sin(ang) * irho);
tabCos[n] = (float)(cos(ang) * irho);
}
// stage 1. fill accumulator
for( i = 0; i < height; i++ )
for( j = 0; j < width; j++ )
{
if( image[i * step + j] != 0 )
//
for( n = start_n; n < stop_n; n++ )
{
r = cvRound( j * tabCos[n] + i * tabSin[n] );
r += (numrho - 1) / 2;
accum[(n+1) * (numrho+2) + r+1]++;
}
}
int max_accum = 0;
int max_ind = 0;
for( r = 0; r < numrho; r++ )
{
for( n = start_n; n < stop_n; n++ )
{
int base = (n+1) * (numrho+2) + r+1;
if (accum[base] > max_accum)
{
max_accum = accum[base];
max_ind = base;
}
}
}
CvLinePolar2 line;
scale = 1./(numrho+2);
int idx = max_ind;
n = cvFloor(idx*scale) - 1;
r = idx - (n+1)*(numrho+2) - 1;
line.rho = (r - (numrho - 1)*0.5f) * rho;
line.angle = n * theta;
line.votes = accum[idx];
cvSeqPush( lines, &line );
}
If you use the Probabilistic Hough transform then the output is in the form of a cvPoint each for lines[0] and lines[1] parameters. We can get x and y co-ordinated for each of the two points by pt1.x, pt1.y and pt2.x and pt2.y.
Then use the simple formula for finding slope of a line - (y2-y1)/(x2-x1). Taking arctan (tan inverse) of that will yield that angle in radians. Then simply filter out desired angles from the values for each hough line obtained.
I think it's more natural to use standart HoughLines(...) function, which gives collection of lines directly in rho and theta terms and select nessessary angle range from it, rather than recalculate angle from segment end points.
Is it possible to get the accumulator value along with rho and theta from a Hough transform?
I ask because I'd like to differentiate between lines which are "well defined" (ie, which have a high accumulator value) and lines which aren't as well defined.
Thanks!
Ok, so looking at the cvhough.cpp file, the structure CvLinePolar is only defined by rho and angle.
This is all that is passed back as a result of our call to HoughLines. I am in the process of modifying the c++ file and see if i can get the votes out.
Update oct 26: just realized these are not really answers but more like questions. apparently frowned upon. I found some instructions on recompiling OpenCV. I guess we'll have to go in the code and modify it and recompile.
How to install OpenCV 2.0 on win32
update Oct 27: well, i failed at compiling the dlls for OpenCV with my new code so I ended up copy-pasting the specific parts I want to modify into my own files.
I like to add new functions so to avoid overloading the already defined functions.
There are 4 main things you need to copy over:
1- some random defines
#define hough_cmp_gt(l1,l2) (aux[l1] > aux[l2])
static CV_IMPLEMENT_QSORT_EX( icvHoughSortDescent32s, int, hough_cmp_gt, const int* )
2- redefining the struct for line parameters
typedef struct CvLinePolar2
{
float rho;
float angle;
float votes;
}
CvLinePolar2;
3- the main function that was modified
static void
icvHoughLinesStandard2( const CvMat* img, float rho, float theta,
int threshold, CvSeq *lines, int linesMax )
{
cv::AutoBuffer<int> _accum, _sort_buf;
cv::AutoBuffer<float> _tabSin, _tabCos;
const uchar* image;
int step, width, height;
int numangle, numrho;
int total = 0;
float ang;
int r, n;
int i, j;
float irho = 1 / rho;
double scale;
CV_Assert( CV_IS_MAT(img) && CV_MAT_TYPE(img->type) == CV_8UC1 );
image = img->data.ptr;
step = img->step;
width = img->cols;
height = img->rows;
numangle = cvRound(CV_PI / theta);
numrho = cvRound(((width + height) * 2 + 1) / rho);
_accum.allocate((numangle+2) * (numrho+2));
_sort_buf.allocate(numangle * numrho);
_tabSin.allocate(numangle);
_tabCos.allocate(numangle);
int *accum = _accum, *sort_buf = _sort_buf;
float *tabSin = _tabSin, *tabCos = _tabCos;
memset( accum, 0, sizeof(accum[0]) * (numangle+2) * (numrho+2) );
for( ang = 0, n = 0; n < numangle; ang += theta, n++ )
{
tabSin[n] = (float)(sin(ang) * irho);
tabCos[n] = (float)(cos(ang) * irho);
}
// stage 1. fill accumulator
for( i = 0; i < height; i++ )
for( j = 0; j < width; j++ )
{
if( image[i * step + j] != 0 )
for( n = 0; n < numangle; n++ )
{
r = cvRound( j * tabCos[n] + i * tabSin[n] );
r += (numrho - 1) / 2;
accum[(n+1) * (numrho+2) + r+1]++;
}
}
// stage 2. find local maximums
for( r = 0; r < numrho; r++ )
for( n = 0; n < numangle; n++ )
{
int base = (n+1) * (numrho+2) + r+1;
if( accum[base] > threshold &&
accum[base] > accum[base - 1] && accum[base] >= accum[base + 1] &&
accum[base] > accum[base - numrho - 2] && accum[base] >= accum[base + numrho + 2] )
sort_buf[total++] = base;
}
// stage 3. sort the detected lines by accumulator value
icvHoughSortDescent32s( sort_buf, total, accum );
// stage 4. store the first min(total,linesMax) lines to the output buffer
linesMax = MIN(linesMax, total);
scale = 1./(numrho+2);
for( i = 0; i < linesMax; i++ )
{
CvLinePolar2 line;
int idx = sort_buf[i];
int n = cvFloor(idx*scale) - 1;
int r = idx - (n+1)*(numrho+2) - 1;
line.rho = (r - (numrho - 1)*0.5f) * rho;
line.angle = n * theta;
line.votes = accum[idx];
cvSeqPush( lines, &line );
}
cvFree( (void**)&sort_buf );
cvFree( (void**)&accum );
cvFree( (void**)&tabSin );
cvFree( (void**)&tabCos);
}
4- the function that calls that function
CV_IMPL CvSeq*
cvHoughLines3( CvArr* src_image, void* lineStorage, int method,
double rho, double theta, int threshold,
double param1, double param2 )
{
CvSeq* result = 0;
CvMat stub, *img = (CvMat*)src_image;
CvMat* mat = 0;
CvSeq* lines = 0;
CvSeq lines_header;
CvSeqBlock lines_block;
int lineType, elemSize;
int linesMax = INT_MAX;
int iparam1, iparam2;
img = cvGetMat( img, &stub );
if( !CV_IS_MASK_ARR(img))
CV_Error( CV_StsBadArg, "The source image must be 8-bit, single-channel" );
if( !lineStorage )
CV_Error( CV_StsNullPtr, "NULL destination" );
if( rho <= 0 || theta <= 0 || threshold <= 0 )
CV_Error( CV_StsOutOfRange, "rho, theta and threshold must be positive" );
if( method != CV_HOUGH_PROBABILISTIC )
{
lineType = CV_32FC3;
elemSize = sizeof(float)*3;
}
else
{
lineType = CV_32SC4;
elemSize = sizeof(int)*4;
}
if( CV_IS_STORAGE( lineStorage ))
{
lines = cvCreateSeq( lineType, sizeof(CvSeq), elemSize, (CvMemStorage*)lineStorage );
}
else if( CV_IS_MAT( lineStorage ))
{
mat = (CvMat*)lineStorage;
if( !CV_IS_MAT_CONT( mat->type ) || (mat->rows != 1 && mat->cols != 1) )
CV_Error( CV_StsBadArg,
"The destination matrix should be continuous and have a single row or a single column" );
if( CV_MAT_TYPE( mat->type ) != lineType )
CV_Error( CV_StsBadArg,
"The destination matrix data type is inappropriate, see the manual" );
lines = cvMakeSeqHeaderForArray( lineType, sizeof(CvSeq), elemSize, mat->data.ptr,
mat->rows + mat->cols - 1, &lines_header, &lines_block );
linesMax = lines->total;
cvClearSeq( lines );
}
else
CV_Error( CV_StsBadArg, "Destination is not CvMemStorage* nor CvMat*" );
iparam1 = cvRound(param1);
iparam2 = cvRound(param2);
switch( method )
{
case CV_HOUGH_STANDARD:
icvHoughLinesStandard2( img, (float)rho,
(float)theta, threshold, lines, linesMax );
break;
default:
CV_Error( CV_StsBadArg, "Unrecognized method id" );
}
if( mat )
{
if( mat->cols > mat->rows )
mat->cols = lines->total;
else
mat->rows = lines->total;
}
else
result = lines;
return result;
}
And i guess you could uninstall opencv so it takes off all those automatic path setting and recompile it yourself using the CMake method and then the OpenCV is really whatever you make it.
Although this is an old question, I had the same problem, so I might as well put up my solution. The threshold in houghlines() returns 1 for any point that cleared the threshold for votes. The solution is to run houghlines() for every threshold value (until there are no more votes) and add up the votes in another array. In python (maybe with other languages too) when you have no more votes, it throws an error, so use try/except.
Here is an example in python. The array I used was for rho values of -199 to 200 with a max vote of less than 100. You can play around with those constants to suit your needs. You may need to add a line to convert the source image to grayscale.
import matplotlib.pyplot as plt
import cv2
import math
############ make houghspace array ############
houghspace = []
c = 0
height = 400
while c <= height:
houghspace.append([])
cc = 0
while cc <= 180:
houghspace[c].append(0)
cc += 1
c+=1
############ do transform ############
degree_tick = 1 #by how many degrees to check
total_votes = 1 #votes counter
highest_vote = 0 #highest vote in the array
while total_votes < 100:
img = cv2.imread('source.pgm')
edges = cv2.Canny(img,50,150,apertureSize = 3)
lines = cv2.HoughLines(edges,1,math.pi*degree_tick/180,total_votes)
try:
for rho,theta in lines[0]:
a = math.cos(theta)
b = math.sin(theta)
x1 = int((a*rho) + 1000*(-b))
y1 = int((b*rho) + 1000*(a))
x2 = int((a*rho) - 1000*(-b))
y2 = int((b*rho) - 1000*(a))
cv2.line(img,(x1,y1),(x2,y2),(50,200,255),2)
#################add votes into the array################
deradian = 180/math.pi #used to convert to degrees
for rho,theta in lines[0]:
degree = int(round(theta*deradian))
rho_pos = int(rho - 200)
houghspace[rho_pos][degree] += 1
#when lines[0] has no votes, it throws an error which is caught here
except:
total_votes = 999 #exit loop
highest_vote = total_votes
total_votes += 1
del lines
########### loop finished ###############################
print highest_vote
#############################################################
################### plot the houghspace ###################
maxy = 200 #used to offset the y-axis
miny = -200 #used to offset the y-axis
#the main graph
fig = plt.figure(figsize=(10, 5))
ax = fig.add_subplot(111)
ax.set_title('Houghspace')
plt.imshow(houghspace, cmap='gist_stern')
ax.set_aspect('equal')
plt.yticks([0,-miny,maxy-miny], [miny,0,maxy])
#the legend
cax = fig.add_axes([0, 0.1, 0.78, 0.8])
cax.get_xaxis().set_visible(False)
cax.get_yaxis().set_visible(False)
cax.patch.set_alpha(0)
cax.set_frame_on(False)
plt.colorbar(orientation='vertical')
#plot
plt.show()