2017-08-19 10:59:37 -0600
| received badge | ● Popular Question
(source)
|
2015-06-28 02:31:40 -0600
| commented question | Image captured by opencv is not good as normal. I will try. Thank you so much. |
2015-06-27 22:30:55 -0600
| commented question | Image captured by opencv is not good as normal. But the quality image captured by VideoCapture before using imwrite, it is also like that. It is not good at the one captured by v4l2-ctl. |
2015-06-27 12:54:39 -0600
| asked a question | Image captured by opencv is not good as normal. I have captured two images,
one by opencv
another one by these command lines, v4l2-ctl --set-fmt-video=width=640,height=480,pixelformat=3
v4l2-ctl --stream-mmap=3 --stream-count=1 --stream-to=somefile.jpg
As the result, image captured by opencv is not good as the remaining. The size of image captured by opencv is just 50kB and the remaining size is 110kb. Why are they different?
How can I set the setting of VideoCapture to get the good image? Please help me, thanks. |
2015-05-14 10:18:53 -0600
| asked a question | Sign Language Recogintion I have a project about sign language recoginition.
Please show me the way to recognize a paticular hand sign (hand shape).
Which algorithm has the highest accuracy?
As I know, we have some algortithm such as SVM Trainning, CascadeClassifier.
Please help me. |
2014-11-24 10:55:41 -0600
| asked a question | Opencv in Raspberry pi. Error when capturing video I have posted my problem in stackoverflow.
Please read and help me. How can i resolve it. |
2014-11-24 10:50:42 -0600
| asked a question | OpenCV in Raspberry Pi - Error when capturing video. I have posted my problem in stackoverflow.
Please read and help me. How can i resolve it. |
2014-11-09 06:50:01 -0600
| received badge | ● Editor
(source)
|
2014-11-08 05:21:45 -0600
| commented answer | Opencv 3.0.0 alpha build error with library opencv_contrib |
2014-11-08 05:19:16 -0600
| asked a question | Face Recoginition - Process is very slow if images from camera doesn't contain face. I have used face cascade to tracking face through webcame. And loop function is very fast if image from camera contains face. However, if not, it is very slow. Please help. My source: void camera() {
String face_cascade_name = "haarcascade_frontalface_alt.xml";
String eye_cascade_name = "haarcascade_eye.xml";
CascadeClassifier face_cascade;
CascadeClassifier eyes_cascade;
String window_name = "Capture - Face detection";
VideoCapture cap(0);
if (!face_cascade.load(face_cascade_name)) {
printf("--(!)Error loading\n");
};
if (!eyes_cascade.load(eye_cascade_name)) {
printf("--(!)Error loading\n");
};
if (!cap.isOpened()) {
cerr << "Capture Device ID " << 0 << "cannot be opened." << endl;
} else {
Mat frame;
vector<Rect> faces;
vector<Rect> eyes;
for (;;) {
cap.read(frame);
Mat original = frame.clone();
Mat frame_gray;
cvtColor(original, frame_gray, CV_BGR2GRAY);
equalizeHist(frame_gray, frame_gray);
face_cascade.detectMultiScale(frame_gray, faces, 1.1, 2,
CASCADE_FIND_BIGGEST_OBJECT | CASCADE_DO_ROUGH_SEARCH,
Size(30, 30));
if (faces.size() > 0) {
rectangle(original, faces[0], Scalar(0, 0, 255), 2, 8, 0);
Mat face = frame_gray(faces[0]);
eyes_cascade.detectMultiScale(face, eyes, 1.1, 2,
0 | CASCADE_SCALE_IMAGE, Size(30, 30));
Mat veFace = original(faces[0]);
for (int i = 0; i < eyes.size(); i++) {
rectangle(veFace, eyes[i], Scalar(255, 0, 255), 2, 8, 0);
}
namedWindow(window_name, CV_WINDOW_AUTOSIZE);
imshow(window_name, original);
}
if (waitKey(30) == 27) {
cout << "esc key is pressed by user" << endl;
break;
}
}
}}
How can i produce that time, please help me. |
2014-11-02 04:45:07 -0600
| asked a question | Opencv 3.0.0 alpha build error with library opencv_contrib I'm developing a project about face recognition. And i know the library for face recognition is opencv_contrib. And this is my source code. #include "opencv2/objdetect.hpp"
#include "opencv2/highgui.hpp"
#include "opencv2/imgproc.hpp"
#include "opencv2/core.hpp"
#include "opencv2/contrib/contrib.hpp"
#include <iostream>
#include <fstream>
#include <sstream>
#include <stdio.h>
using namespace std;
using namespace cv;
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() {
String face_cascade_name = "face.xml";
String csvPath = "/home/longnhkse60984/csv.ext";
String eye_cascade_name = "haarcascade_eye.xml";
CascadeClassifier face_cascade;
CascadeClassifier eyes_cascade;
String window_name = "Capture - Face detection";
vector<Mat> images;
vector<int> labels;
try {
read_csv(csvPath, images, labels);
} catch (cv::Exception& e) {
cerr << "Error opening file \"" << csvPath << "\". Reason: " << e.msg
<< endl;
// nothing more we can do
exit(1);
}
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);
//CascadeClassifier haar_cascade;
face_cascade.load(face_cascade_name);
Mat frame = imread("aaa.jpg");
Mat original = frame.clone();
vector<Rect> faces;
Mat frame_gray;
cvtColor(original, frame_gray, COLOR_BGR2GRAY);
equalizeHist(frame_gray, frame_gray);
//-- Detect faces
face_cascade.detectMultiScale(frame_gray, faces, 1.1, 2,
CASCADE_FIND_BIGGEST_OBJECT | CASCADE_DO_ROUGH_SEARCH,
Size(30, 30));
Mat face = frame_gray(faces[0]);
Mat face_resized;
resize(face, face_resized, Size(im_width,im_height),1.0,1.0,INTER_CUBIC);
int prediction = model->predict(face_resized);
cout << prediction;
// 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:
//
waitKey(0);
return 0;}
When i build this i have received errors of opencv_contrib. Please help me. |
2014-11-02 04:23:51 -0600
| commented question | Don't see library opencv_contrib in opencv 3.0.0-alpha i don't understand clearly. i'm looking for the facerecoginition, what i must download and install. please, help. |
2014-11-02 00:48:38 -0600
| commented answer | Don't see library opencv_contrib in opencv 3.0.0-alpha Thank you, can you help me how to install it and how to tell ubuntu where lib. :) |
2014-11-01 23:39:38 -0600
| asked a question | Don't see library opencv_contrib in opencv 3.0.0-alpha I have installed opencv 3.0.0 follow this site Install opencv 3.0.0 on ubuntu. After that, everything is good except library opencv_contrib, i don't see it in folder "usr/local/lib" of ubuntu.
So i find it folder "modules" in folder "build" of opencv 3.0.0 and i still don't see it. And folder "lib" in folder "build" Error when i built my project with opencv_contrib |