C++ OPENCV 4.3.0 x64 Why face_cascade throws error? - c++

I am using OpenCV to add a face recognition feature to my C++ program. I have never used it before and I cant seem to get the cascade feature for facial recognition to work. I am wondering if they have made some changes for the FLAGS in the new version. I can display an image but when that comes to the cascade it always throws an error. Can anyone tell me what am I missing?
#include <opencv2/core/core.hpp>
#include <opencv2/highgui/highgui.hpp>
#include <opencv2/imgproc.hpp>
#include <stdio.h>
#include <iostream>
#include <opencv2\objdetect.hpp>
using namespace std;
using namespace cv;
String face_cascade_name = "sources/data/haarcascades/haarcascade_frontalface_default.xml";
String eyes_cascade_name = "sources/data/haarcascades/haarcascade_eye_tree_eyeglasses.xml";
String smile_cascade_name = "sources/data/haarcascades/haarcascade_smile.xml";
CascadeClassifier face_cascade;
CascadeClassifier eyes_cascade;
CascadeClassifier smile_cascade;
string window_name = "Capture - Face detection";
RNG rng(12345);
int main()
{
//-- 1. Load the cascades
if (!face_cascade.load(face_cascade_name)) { printf("--(!)Error loading file 1\n"); return -1; };
if (!eyes_cascade.load(eyes_cascade_name)) { printf("--(!)Error loading file 2\n"); return -1; };
if (!smile_cascade.load(smile_cascade_name)) { printf("--(!)Error loading file 3\n"); return -1; };
std::string image_path = samples::findFile("test.jpg");
Mat img = imread(image_path, IMREAD_COLOR);
Mat img_gry;
if (img.empty())
{
std::cout << "Could not read the image: " << image_path << std::endl;
return 1;
}
imshow("Display window", img);
// Detect faces
std::vector<Rect> faces;
cvtColor(img, img_gry, COLOR_BGR2GRAY);
equalizeHist(img, img_gry);
//I GET ERROR HERE
face_cascade.detectMultiScale(img_gry, faces, 1.1, 2, CASCADE_SCALE_IMAGE, Size(30, 30), Size(130, 130)); //I GET ERROR HERE
/*...REST WILL BE PARSING faces...*/
int g_key = waitKey(0); // Wait for a keystroke in the window
if (g_key == 's')
{
imwrite("starry_night.png", img); //save image in same path
}
return 0;
}

I modified the code as:
/*...
OTHER CODE
...*/
std::vector<Rect> faces;
cvtColor(img, img_gry, COLOR_BGR2GRAY);
equalizeHist(img_gry, img_gry);
face_cascade.detectMultiScale(img_gry, faces);
for (size_t i = 0; i < faces.size(); i++)
{
/*...PARSE...*/
}
imshow("Display window", img);
As #SourceCode mentioned :
equalizeHist( smallImg, smallImg); //my variable is img_gry instead.
But also, I modified :
face_cascade.detectMultiScale(img_gry, faces, 1.1, 2, CASCADE_SCALE_IMAGE, Size(30, 30), Size(130, 130));
To
face_cascade.detectMultiScale(img_gry, faces);
Otherwise it does not work in my case.
Source if that helps: https://docs.opencv.org/3.4/db/d28/tutorial_cascade_classifier.html

Have you tried using something like:
face_cascade.detectMultiScale(img_gry, faces, 1.1, 2, 0|CASCADE_SCALE_IMAGE, Size(30, 30));

Related

How can I use Blob Detector

I'm trying to use SimpleBlobDetector in OpenCV 3 to detect blobs of heat in thermal images, for example people. Any simple code or example will be appreciated.
i tried`
#include <opencv2/core/core.hpp>
#include <opencv2/highgui/highgui.hpp>
#include <iostream>
#include "opencv2\features2d.hpp"
using namespace cv;
using namespace std;
int main(int argc, char** argv)
{
if (argc != 2)
{
cout << " Usage: display_image ImageToLoadAndDisplay" << endl;
return 0;
}
Mat image;
image = imread(argv[1], CV_LOAD_IMAGE_GRAYSCALE); // Read the file
if (!image.data) // Check for invalid input
{
cout << "Could not open or find the image" << std::endl;
return 0;
}
// Set up the detector with default parameters.
//SimpleBlobDetector detector;
// Setup SimpleBlobDetector parameters.
SimpleBlobDetector::Params params;
// Change thresholds
params.minThreshold = 50;
params.maxThreshold = 200;
// Filter by Area.
params.filterByArea = true;
params.minArea = 1500;
// Filter by Circularity
params.filterByCircularity = true;
params.minCircularity = 0.1;
// Filter by Convexity
params.filterByConvexity = true;
params.minConvexity = 0.87;
// Filter by Inertia
params.filterByInertia = true;
params.minInertiaRatio = 0.01;
// Detect blobs.
std::vector<KeyPoint> keypoints;
cv::Ptr<cv::SimpleBlobDetector> detector = cv::SimpleBlobDetector::create(params);
//detector->detect(img, keypoints);
detector->detect(image, keypoints);
//params.detect(image, keypoints);
// Draw detected blobs as red circles.
//DrawMatchesFlags::DRAW_RICH_KEYPOINTS flag ensures the size of the circle corresponds to the size of blob
Mat im_with_keypoints;
drawKeypoints(image, keypoints, im_with_keypoints, Scalar(0, 0, 255), DrawMatchesFlags::DRAW_RICH_KEYPOINTS);
// Show blobs
imshow("keypoints", im_with_keypoints);
waitKey(0);
//namedWindow("Display window", WINDOW_AUTOSIZE);// Create a window for display.
//imshow("Display window", image); // Show our image inside it.
//waitKey(0); // Wait for a keystroke in the window
//return 0;
}
` but it just returns the gray image unchanged.
To detect blobs with OpenCV you need to:
Instantiate a SimpleBlobDetector type
Declare a vector of type KeyPoints
Call SimpleBlobDetector::detect()
There is a brilliant tutorial online here (where I nicked the code from): https://www.learnopencv.com/blob-detection-using-opencv-python-c/
using namespace cv;
Mat im = imread( "blob.jpg", IMREAD_GRAYSCALE );
SimpleBlobDetector detector;
std::vector<KeyPoint> keypoints;
detector.detect( im, keypoints);
drawKeypoints( im, keypoints, im_with_keypoints, Scalar(0,0,255), DrawMatchesFlags::DRAW_RICH_KEYPOINTS );
imshow("keypoints", im_with_keypoints );// Show blobs
waitKey(0);
You can also adjust parameters to select blobs with specific attributes, it's all listed in the tutorial. I'd suggest having a play, to get a feel for how it works.

Debug Assertion failed ! in detectAndDisplay function of face recognition openCv

I am trying to run the program and is building well but not able to debug. Capturing first frame and then giving below error.
I tried to check in debug mode and could figure out that
imshow(window_name, frame);
Error !!!
Here is the working code that is copied from OpenCV blog.
#include "opencv2/objdetect/objdetect.hpp"
#include "opencv2/video/video.hpp"
#include "opencv2/highgui/highgui.hpp"
#include "opencv2/imgproc/imgproc.hpp"
#include <iostream>
#include <stdio.h>
using namespace std;
using namespace cv;
/** Function Headers */
void detectAndDisplay(Mat frame);
/** Global variables */
String face_cascade_name = "haarcascade_frontalface_alt.xml";
String eyes_cascade_name = "haarcascade_eye_tree_eyeglasses.xml";
CascadeClassifier face_cascade;
CascadeClassifier eyes_cascade;
string window_name = "Capture - Face detection";
RNG rng(12345);
/** #function main */
int main(int argc, const char** argv)
{
CvCapture* capture;
Mat frame;
//-- 1. Load the cascades
if (!face_cascade.load(face_cascade_name)) { printf("--(!)Error loading\n"); return -1; };
if (!eyes_cascade.load(eyes_cascade_name)) { printf("--(!)Error loading\n"); return -1; };
//-- 2. Read the video stream
capture = cvCaptureFromCAM(CV_CAP_ANY);
if (capture)
{
while (true)
{
frame = cvQueryFrame(capture);
//-- 3. Apply the classifier to the frame
if (!frame.empty())
{
detectAndDisplay(frame);
}
else
{
printf(" --(!) No captured frame -- Break!");
break;
}
int c = waitKey(10);
if ((char)c == 'c') { break; }
}
}
return 0;
}
/** #function detectAndDisplay */
void detectAndDisplay(Mat frame)
{
std::vector<Rect> faces;
Mat frame_gray;
cvtColor(frame, frame_gray, CV_BGR2GRAY);
equalizeHist(frame_gray, frame_gray);
//-- Detect faces
face_cascade.detectMultiScale(frame_gray, faces, 1.1, 2, 0 | CV_HAAR_SCALE_IMAGE, Size(30, 30));
for (size_t i = 0; i < faces.size(); i++)
{
Point center(faces[i].x + faces[i].width*0.5, faces[i].y + faces[i].height*0.5);
ellipse(frame, center, Size(faces[i].width*0.5, faces[i].height*0.5), 0, 0, 360, Scalar(255, 0, 255), 4, 8, 0);
Mat faceROI = frame_gray(faces[i]);
std::vector<Rect> eyes;
//-- In each face, detect eyes
eyes_cascade.detectMultiScale(faceROI, eyes, 1.1, 2, 0 | CV_HAAR_SCALE_IMAGE, Size(30, 30));
for (size_t j = 0; j < eyes.size(); j++)
{
Point center(faces[i].x + eyes[j].x + eyes[j].width*0.5, faces[i].y + eyes[j].y + eyes[j].height*0.5);
int radius = cvRound((eyes[j].width + eyes[j].height)*0.25);
circle(frame, center, radius, Scalar(255, 0, 0), 4, 8, 0);
}
}
//-- Show what you got
imshow(window_name, frame);
}
Error when value chosen in
capture = cvCaptureFromCAM(-1)
is -1.
I am getting GRey window with no Error.
imshow with Grey Window, No Error
I changed the Platform Toolset from Visual Studio 2015(v140) to Visual Studio 2013(v120) as in the figure attached. I do not know why but it worked.
Visual Studio 2015(v140)
Visual Studio 2013(v120)
It may happen, if your face ROI, out of frame bounds.
Because you trying to copy this region you getting memory error.
if(faces[i].x>=0 && faces[i].y >= 0 && faces[i].x+faces[i].width<frame_gray.cols && faces[i].y+faces[i].height < frame_gray.rows)
{
faceROI=frame_gray(faces[i]);
}

opencv detectMultiScale

Im trying to learn opencv and object detection. I used objecdetection.cpp in opencv samples and when I run it I get this error
The cascade loads perfectly fine and also the camera the only problem is detectmultiscale because whenever i commented it out the program doesn't crash
here is the code of objectdecetion2.cpp
#include "opencv2/objdetect.hpp"
#include "opencv2/videoio.hpp"
#include "opencv2/highgui.hpp"
#include "opencv2/imgproc.hpp"
#include <iostream>
#include <stdio.h>
using namespace std;
using namespace cv;
/** Function Headers */
void detectAndDisplay(Mat frame);
/** Global variables */
String face_cascade_name = "..\\Debug\\haarcascade_frontalface_alt.xml";
String eyes_cascade_name = "..\\Debug\\haarcascade_eye_tree_eyeglasses.xml";
CascadeClassifier face_cascade;
CascadeClassifier eyes_cascade;
String window_name = "Capture - Face detection";
/**
* #function main
*/
int main(void)
{
VideoCapture capture;
Mat frame;
//-- 1. Load the cascade
if (!face_cascade.load(face_cascade_name)){ printf("--(!)Error loading face cascade\n"); return -1; };
if (!eyes_cascade.load(eyes_cascade_name)){ printf("--(!)Error loading eyes cascade\n"); return -1; };
//-- 2. Read the video stream
capture.open(0);
if (!capture.isOpened()) { printf("--(!)Error opening video capture\n"); return -1; }
while (capture.read(frame))
{
if (frame.empty())
{
printf(" --(!) No captured frame -- Break!");
break;
}
//-- 3. Apply the classifier to the frame
detectAndDisplay(frame);
//-- bail out if escape was pressed
int c = waitKey(10);
if ((char)c == 27) { break; }
}
return 0;
}
/**
* #function detectAndDisplay
*/
void detectAndDisplay(Mat frame)
{
std::vector<Rect> faces;
Mat frame_gray;
cvtColor(frame, frame_gray, COLOR_BGR2GRAY);
equalizeHist(frame_gray, frame_gray);
face_cascade.detectMultiScale(frame_gray, faces, 1.1, 2, 0, Size(80, 80));
imshow(window_name, frame);
}
You are likely experiencing an OpenCV bug, described here: http://code.opencv.org/issues/3710
The code you posted looks OK to me, otherwise.
The code you posted is right! But I doubt that your opencv configuration is not right! If you work on windows, Please check your .dll files and lib files!

OpenCV: record footage in one window and Display the same video in 2nd window but with contours only

I want to capture a video and display it on one window and have second window in which contours are displayed simultaneous. I am struggling with how to have the processed video displayed in the second window. Please analyze my code and suggest a solution or indicate where am going wrong maybe give me some directions to an online tutorial or sources. Thanks.
#include "iostream"
#include<opencv\cv.h>
#include<opencv\highgui.h>
#include<opencv\ml.h>
#include<opencv\cxcore.h>
#include <iostream>
#include <vector>
#include <string>
#include <opencv2/core/core.hpp> // Basic OpenCV structures (cv::Mat)
#include <opencv2/highgui/highgui.hpp> // Video write
using namespace cv;
using namespace std;
Mat image; Mat image_gray; Mat image_gray2; Mat threshold_output;
Mat frame;
int thresh=100, max_thresh=255;
int main(int argc, char** argv) {
//Capture Video
VideoCapture capCam(1);
if (!capCam.isOpened()){
cout<<"ERROR: Failed to Initialize Camera"<<endl;
return 1;
}
else{
cout<<"Camera Initialized"<<endl;
}
//Create Window
char* ImputFootage = "Source";
namedWindow(ImputFootage, CV_WINDOW_AUTOSIZE);
imshow(ImputFootage, frame);
char* OutputFootage = "Processed";
namedWindow(OutputFootage, CV_WINDOW_AUTOSIZE);
imshow(OutputFootage, frame);
while(1){
capCam>> frame;
imshow("Source", frame);
return(1);
if(capCam.read(ImputFootage)){
//Convert Image to gray & blur it
cvtColor( image,
image_gray,
CV_BGR2GRAY );
blur( image_gray,
image_gray2,
Size(3,3) );
//Threshold Gray&Blur Image
threshold(image_gray2,
threshold_output,
thresh,
max_thresh,
THRESH_BINARY);
//2D Container
vector<vector<Point>> contours;
//Fnd Countours Points, (Imput Image, Storage, Mode1, Mode2, Offset??)
findContours(threshold_output,
contours, // a vector of contours
CV_RETR_EXTERNAL,// retrieve the external contours
CV_CHAIN_APPROX_NONE,
Point(0, 0)); // all pixels of each contours
// Draw black contours on a white image
Mat result(threshold_output.size(),CV_8U,Scalar(255));
drawContours(result,contours,
-1, // draw all contours
Scalar(0), // in black
2); // with a thickness of 2
}
}
char CheckForEscKey = waitKey(10);
return 1;
}
You should call imshow("Processed", result); after calling drawContours
You were trying to show frames even before they were captured with camera. Compiler was not giving you error because Mat were declared ,but they were without value (null), Moreover you were trying to display Mat image, but what you capture from camera is Mat frame. Also, you lack exit (esc sequence, and your wait key was OUT of camera loop.
Anyway, here is your code (rewritten), I hope this is what you wanted.
#include <opencv2/core/core.hpp>
#include <opencv2/highgui/highgui.hpp>
#include <opencv2/imgproc/imgproc.hpp>
#include <cstdio>
#include <iostream>
#include <stdlib.h>
#include <stdio.h>
using namespace std;
using namespace cv;
Mat image;
Mat image_gray;
Mat image_gray2;
Mat threshold_output;
Mat frame;
int thresh = 100, max_thresh = 255;
int main(int argc, char** argv)
{
//Capture Video
VideoCapture capCam(0);
if (!capCam.isOpened())
{
cout << "ERROR: Failed to Initialize Camera" << endl;
return 1;
}
else
{
cout << "Camera Initialized" << endl;
}
//Create Window
char* ImputFootage = "Source";
namedWindow(ImputFootage, CV_WINDOW_AUTOSIZE);
char* OutputFootage = "Processed";
namedWindow(OutputFootage, CV_WINDOW_AUTOSIZE);
while (1)
{
capCam >> frame;
imshow(ImputFootage, frame);
if (capCam.read(frame))
{
//Convert Image to gray & blur it
cvtColor(frame, image_gray, CV_BGR2GRAY);
blur(image_gray, image_gray2, Size(3, 3));
//Threshold Gray&Blur Image
threshold(image_gray2, threshold_output, thresh, max_thresh, THRESH_BINARY);
//2D Container
vector<vector<Point> > contours;
//Fnd Countours Points, (Imput Image, Storage, Mode1, Mode2, Offset??)
findContours(threshold_output, contours, // a vector of contours
CV_RETR_EXTERNAL, // retrieve the external contours
CV_CHAIN_APPROX_NONE, Point(0, 0)); // all pixels of each contours
// Draw black contours on a white image
Mat result(threshold_output.size(), CV_8U, Scalar(255));
drawContours(result, contours, -1, // draw all contours
Scalar(0), // in black
2); // with a thickness of 2
imshow(OutputFootage, result);
char CheckForEscKey = waitKey(10);
//If the key pressed by user is Esc(ASCII is 27) then break out of the loop
if (CheckForEscKey == 27)
{
break;
}
}
}
return 0;
}

How can I convert a cv::Mat to a gray scale in OpenCv?

How can I convert a cv::Mat to a gray scale?
I am trying to run drawKeyPoints func from opencv, however I have been getting an Assertion Filed error. My guess is that it needs to receive a gray scale image rather than a color image in the parameter.
void SurfDetector(cv::Mat img){
vector<cv::KeyPoint> keypoints;
cv::Mat featureImage;
cv::drawKeypoints(img, keypoints, featureImage, cv::Scalar(255,255,255) ,cv::DrawMatchesFlags::DRAW_RICH_KEYPOINTS);
cv::namedWindow("Picture");
cv::imshow("Picture", featureImage);
}
Using the C++ API, the function name has slightly changed and it writes now:
#include <opencv2/imgproc/imgproc.hpp>
cv::Mat greyMat, colorMat;
cv::cvtColor(colorMat, greyMat, CV_BGR2GRAY);
The main difficulties are that the function is in the imgproc module (not in the core), and by default cv::Mat are in the Blue Green Red (BGR) order instead of the more common RGB.
OpenCV 3
Starting with OpenCV 3.0, there is yet another convention.
Conversion codes are embedded in the namespace cv:: and are prefixed with COLOR.
So, the example becomes then:
#include <opencv2/imgproc/imgproc.hpp>
cv::Mat greyMat, colorMat;
cv::cvtColor(colorMat, greyMat, cv::COLOR_BGR2GRAY);
As far as I have seen, the included file path hasn't changed (this is not a typo).
May be helpful for late comers.
#include "stdafx.h"
#include "cv.h"
#include "highgui.h"
using namespace cv;
using namespace std;
int main(int argc, char *argv[])
{
if (argc != 2) {
cout << "Usage: display_Image ImageToLoadandDisplay" << endl;
return -1;
}else{
Mat image;
Mat grayImage;
image = imread(argv[1], IMREAD_COLOR);
if (!image.data) {
cout << "Could not open the image file" << endl;
return -1;
}
else {
int height = image.rows;
int width = image.cols;
cvtColor(image, grayImage, CV_BGR2GRAY);
namedWindow("Display window", WINDOW_AUTOSIZE);
imshow("Display window", image);
namedWindow("Gray Image", WINDOW_AUTOSIZE);
imshow("Gray Image", grayImage);
cvWaitKey(0);
image.release();
grayImage.release();
return 0;
}
}
}