以下代码用于识别我从以下链接获得的面孔
http://docs.opencv.org/3.0-beta/modules/face/doc/facerec/tutorial/facerec_video_recognition.html
我所做的唯一修改是：我没有使用命令行参数来提供CSV和Cascade分类器路径，而是直接在代码中给出了它们。
问题 facerecognization.exe中的0x00007FFDD0C0E09B（opencv_core310.dll）抛出异常：0xC0000005：访问冲突读取位置0xFFFFFFFFFFFFFFFF。
我遇到了访问冲突问题，如图所示。
解决问题我试图
1）逐步调试我在代码到达此行时得到异常 CascadeClassifier haar_cascade;在模型 - >训练之后
2）我重新安装了两次所有的东西，即opencv_contru，但我又一次重复问题
3）我最初在＆amp; t数据库中用作at.txt，因为它使用.pgm文件（windows无法识别，当我遇到同样的问题时），所以我用.jpg创建了我自己的数据库，即facecsv.txt（我的数据库有10套）但同样的问题仍然存在
4）我将haarcascade_frontalface_default.xml更改为其他.xml文件，但仍然存在同样的问题
5）dll不是配置两次的问题
码
#include "opencv2/core.hpp"
#include "opencv2/face.hpp"
#include "opencv2/highgui.hpp"
#include "opencv2/imgproc.hpp"
#include "opencv2/objdetect.hpp"
#include <iostream>
#include <fstream>
#include <sstream>
using namespace cv;
using namespace cv::face;
using namespace std;
int abc;
static void read_csv(const string& filename, vector<Mat>& images, vector<int>& labels, char separator = ';') {
std::ifstream file(filename.c_str(), ifstream::in);
if (!file) {
string error_message = "No valid input file was given, please check the given filename.";
CV_Error(CV_StsBadArg, error_message);
}
string line, path, classlabel;
while (getline(file, line)) {
stringstream liness(line);
getline(liness, path, separator);
getline(liness, classlabel);
if (!path.empty() && !classlabel.empty()) {
images.push_back(imread(path, 0));
labels.push_back(atoi(classlabel.c_str()));
}
}
}
int main(int argc, const char *argv[]) {
// Get the path to your CSV:
string fn_haar = "C:\\OpenCV-3.1.0\\opencv\\build2\\install\\etc\\haarcascades\\haarcascade_frontalface_default.xml";
string fn_csv = "C:\\OpenCV-3.1.0\\facedata\\facecsv.txt";
int deviceId = 0;
// These vectors hold the images and corresponding labels:
vector<Mat> images;
vector<int> labels;
// Read in the data (fails if no valid input filename is given, but you'll get an error message):
try {
read_csv(fn_csv, images, labels);
}
catch (cv::Exception& e) {
cerr << "Error opening file \"" << fn_csv << "\". Reason: " << e.msg << endl;
// nothing more we can do
cin >> abc;
exit(1);
}
// Get the height from the first image. We'll need this
// later in code to reshape the images to their original
// size AND we need to reshape incoming faces to this size:
int im_width = images[0].cols;
int im_height = images[0].rows;
// Create a FaceRecognizer and train it on the given images:
Ptr<FaceRecognizer> model = createFisherFaceRecognizer();
model->train(images, labels);
// That's it for learning the Face Recognition model. You now
// need to create the classifier for the task of Face Detection.
// We are going to use the haar cascade you have specified in the
// command line arguments:
//
CascadeClassifier haar_cascade;
haar_cascade.load(fn_haar);
// Get a handle to the Video device:
VideoCapture cap(deviceId);
// Check if we can use this device at all:
if (!cap.isOpened()) {
cerr << "Capture Device ID " << deviceId << "cannot be opened." << endl;
return -1;
}
// Holds the current frame from the Video device:
Mat frame;
for (;;) {
cap >> frame;
// Clone the current frame:
Mat original = frame.clone();
// Convert the current frame to grayscale:
Mat gray;
cvtColor(original, gray, CV_BGR2GRAY);
// Find the faces in the frame:
vector< Rect_<int> > faces;
haar_cascade.detectMultiScale(gray, faces);
// At this point you have the position of the faces in
// faces. Now we'll get the faces, make a prediction and
// annotate it in the video. Cool or what?
for (int i = 0; i < faces.size(); i++) {
// Process face by face:
Rect face_i = faces[i];
// Crop the face from the image. So simple with OpenCV C++:
Mat face = gray(face_i);
// Resizing the face is necessary for Eigenfaces and Fisherfaces. You can easily
// verify this, by reading through the face recognition tutorial coming with OpenCV.
// Resizing IS NOT NEEDED for Local Binary Patterns Histograms, so preparing the
// input data really depends on the algorithm used.
//
// I strongly encourage you to play around with the algorithms. See which work best
// in your scenario, LBPH should always be a contender for robust face recognition.
//
// Since I am showing the Fisherfaces algorithm here, I also show how to resize the
// face you have just found:
Mat face_resized;
cv::resize(face, face_resized, Size(im_width, im_height), 1.0, 1.0, INTER_CUBIC);
// Now perform the prediction, see how easy that is:
int prediction = model->predict(face_resized);
// And finally write all we've found out to the original image!
// First of all draw a green rectangle around the detected face:
rectangle(original, face_i, CV_RGB(0, 255, 0), 1);
// Create the text we will annotate the box with:
string box_text = format("Prediction = %d", prediction);
// Calculate the position for annotated text (make sure we don't
// put illegal values in there):
int pos_x = std::max(face_i.tl().x - 10, 0);
int pos_y = std::max(face_i.tl().y - 10, 0);
// And now put it into the image:
putText(original, box_text, Point(pos_x, pos_y), FONT_HERSHEY_PLAIN, 1.0, CV_RGB(0, 255, 0), 2.0);
}
// Show the result:
imshow("face_recognizer", original);
// And display it:
char key = (char)waitKey(20);
// Exit this loop on escape:
if (key == 27)
break;
}
return 0;
}
我的数据库看起来像 的 facecsv.txt
C:\OpenCV-3.1.0\facedata\Angelina Jolie/Angelina_1.jpg;0
C:\OpenCV-3.1.0\facedata\Angelina Jolie/Angelina_2.jpg;0
C:\OpenCV-3.1.0\facedata\Angelina Jolie/angelina_3.jpg;0
C:\OpenCV-3.1.0\facedata\Arnold Schwarzenegger/Arnold_1.jpg;1
C:\OpenCV-3.1.0\facedata\Arnold Schwarzenegger/Arnold_2.jpg;1
C:\OpenCV-3.1.0\facedata\Arnold Schwarzenegger/Arnold_3.jpg;1
C:\OpenCV-3.1.0\facedata\Brad Pitt/Brad_1.jpg;2
C:\OpenCV-3.1.0\facedata\Brad Pitt/Brad_2.jpg;2
C:\OpenCV-3.1.0\facedata\Brad Pitt/Brad_3.jpg;2
C:\OpenCV-3.1.0\facedata\Emma Watson/Emma_1.jpg;3
C:\OpenCV-3.1.0\facedata\Emma Watson/Emma_2.jpg;3
C:\OpenCV-3.1.0\facedata\Emma Watson/Emma_3.jpg;3
C:\OpenCV-3.1.0\facedata\Justin Timberlake/Justin_1.jpg;4
C:\OpenCV-3.1.0\facedata\Justin Timberlake/Justin_2.jpg;4
C:\OpenCV-3.1.0\facedata\Justin Timberlake/Justin_3.jpg;4
C:\OpenCV-3.1.0\facedata\Katy Perry/Katy_1.jpg;5
C:\OpenCV-3.1.0\facedata\Katy Perry/Katy_2.jpg;5
C:\OpenCV-3.1.0\facedata\Katy Perry/Katy_3.jpg;5
C:\OpenCV-3.1.0\facedata\Keanu Reeves/Keanu_1.jpg;6
C:\OpenCV-3.1.0\facedata\Keanu Reeves/Keanu_2.jpg;6
C:\OpenCV-3.1.0\facedata\Keanu Reeves/Keanu_3.jpg;6
C:\OpenCV-3.1.0\facedata\Nisarg/Nisarg_1.jpg;7
C:\OpenCV-3.1.0\facedata\Nisarg/Nisarg_2.jpg;7
C:\OpenCV-3.1.0\facedata\Nisarg/Nisarg_3.jpg;7
C:\OpenCV-3.1.0\facedata\Nisarg/Nisarg_4.jpg;7
C:\OpenCV-3.1.0\facedata\Nisarg/Nisarg_5.jpg;7
C:\OpenCV-3.1.0\facedata\Tom Cruise/Tom_1.jpg;8
C:\OpenCV-3.1.0\facedata\Tom Cruise/Tom_2.jpg;8
C:\OpenCV-3.1.0\facedata\Tom Cruise/Tom_3.jpg;8
和＆amp; t数据库
C:\OpenCV-3.1.0\att_faces (1)\database\s1/1.pgm;0
C:\OpenCV-3.1.0\att_faces (1)\database\s1/10.pgm;0
C:\OpenCV-3.1.0\att_faces (1)\database\s1/2.pgm;0
C:\OpenCV-3.1.0\att_faces (1)\database\s1/3.pgm;0
C:\OpenCV-3.1.0\att_faces (1)\database\s1/4.pgm;0
C:\OpenCV-3.1.0\att_faces (1)\database\s1/5.pgm;0
C:\OpenCV-3.1.0\att_faces (1)\database\s1/6.pgm;0
C:\OpenCV-3.1.0\att_faces (1)\database\s1/7.pgm;0
C:\OpenCV-3.1.0\att_faces (1)\database\s1/8.pgm;0
C:\OpenCV-3.1.0\att_faces (1)\database\s1/9.pgm;0
C:\OpenCV-3.1.0\att_faces (1)\database\s10/1.pgm;1
C:\OpenCV-3.1.0\att_faces (1)\database\s10/10.pgm;1
C:\OpenCV-3.1.0\att_faces (1)\database\s10/2.pgm;1
C:\OpenCV-3.1.0\att_faces (1)\database\s10/3.pgm;1
C:\OpenCV-3.1.0\att_faces (1)\database\s10/4.pgm;1
C:\OpenCV-3.1.0\att_faces (1)\database\s10/5.pgm;1
C:\OpenCV-3.1.0\att_faces (1)\database\s10/6.pgm;1
C:\OpenCV-3.1.0\att_faces (1)\database\s10/7.pgm;1
C:\OpenCV-3.1.0\att_faces (1)\database\s10/8.pgm;1
C:\OpenCV-3.1.0\att_faces (1)\database\s10/9.pgm;1
C:\OpenCV-3.1.0\att_faces (1)\database\s11/1.pgm;2
C:\OpenCV-3.1.0\att_faces (1)\database\s11/10.pgm;2
C:\OpenCV-3.1.0\att_faces (1)\database\s11/2.pgm;2
C:\OpenCV-3.1.0\att_faces (1)\database\s11/3.pgm;2
C:\OpenCV-3.1.0\att_faces (1)\database\s11/4.pgm;2
C:\OpenCV-3.1.0\att_faces (1)\database\s11/5.pgm;2
C:\OpenCV-3.1.0\att_faces (1)\database\s11/6.pgm;2
C:\OpenCV-3.1.0\att_faces (1)\database\s11/7.pgm;2
C:\OpenCV-3.1.0\att_faces (1)\database\s11/8.pgm;2
C:\OpenCV-3.1.0\att_faces (1)\database\s11/9.pgm;2
C:\OpenCV-3.1.0\att_faces (1)\database\s12/1.pgm;3
C:\OpenCV-3.1.0\att_faces (1)\database\s12/10.pgm;3
C:\OpenCV-3.1.0\att_faces (1)\database\s12/2.pgm;3
C:\OpenCV-3.1.0\att_faces (1)\database\s12/3.pgm;3
C:\OpenCV-3.1.0\att_faces (1)\database\s12/4.pgm;3
C:\OpenCV-3.1.0\att_faces (1)\database\s12/5.pgm;3
C:\OpenCV-3.1.0\att_faces (1)\database\s12/6.pgm;3
C:\OpenCV-3.1.0\att_faces (1)\database\s12/7.pgm;3
C:\OpenCV-3.1.0\att_faces (1)\database\s12/8.pgm;3
C:\OpenCV-3.1.0\att_faces (1)\database\s12/9.pgm;3
C:\OpenCV-3.1.0\att_faces (1)\database\s13/1.pgm;4
C:\OpenCV-3.1.0\att_faces (1)\database\s13/10.pgm;4
C:\OpenCV-3.1.0\att_faces (1)\database\s13/2.pgm;4
C:\OpenCV-3.1.0\att_faces (1)\database\s13/3.pgm;4
C:\OpenCV-3.1.0\att_faces (1)\database\s13/4.pgm;4
C:\OpenCV-3.1.0\att_faces (1)\database\s13/5.pgm;4
C:\OpenCV-3.1.0\att_faces (1)\database\s13/6.pgm;4
C:\OpenCV-3.1.0\att_faces (1)\database\s13/7.pgm;4
C:\OpenCV-3.1.0\att_faces (1)\database\s13/8.pgm;4
C:\OpenCV-3.1.0\att_faces (1)\database\s13/9.pgm;4
and it goes upto 40 test sample s1 to s40
问题
Exception thrown at 0x00007FFDD0C0E09B (opencv_core310.dll) in facerecognization.exe: 0xC0000005: Access violation reading location 0xFFFFFFFFFFFFFFFF.
我正在使用Windows 10 64位与Visual Studio 2015和OpenCV 3.1.0以及opencv_contrib-master（构建配置：x64-Debug）
他们在这里是类似的问题Face Recognition in Video using OpenCV gives unhandled exception 但他只使用了一个标签，但我使用了超过8个没有解决我问题的标签
答案 0 :(得分：0)
我正在使用Windows 10 64位与Visual Studio 2015和OpenCV 3.1.0以及opencv_contrib-master（构建配置：x64- 调试）
您已链接到发布库，但您处于调试模式。
在调试中，您需要使用尾随＆＃34; d＆＃34;：opencv_<module><version>d.lib链接到OpenCV库。
所以在你的情况下：opencv_core310d.lib等......