OpenCV 人脸检测（HAAR/DNN）

1、HAAR级联检测

#include <opencv2/opencv.hpp>
#include <iostream>

using namespace cv;

#include <iostream>
#include <cstdlib>
using namespace std;

int main(int artc, char** argv) {
	face_detect_haar();
	waitKey(0);
	return 0;
}

void face_detect_haar() {
	CascadeClassifier faceDetector;
	std::string haar_data_file = "./models/haarcascades/haarcascade_frontalface_alt_tree.xml";
	faceDetector.load(haar_data_file);	
	vector<Rect> faces;
	//VideoCapture capture(0);
	VideoCapture capture("./video/test.mp4");
	Mat frame, gray;
	int count=0;
	while (capture.read(frame)) {
		int64 start = getTickCount();
		if (frame.empty())
		{
			break;
		}
		// 水平镜像调整
		// flip(frame, frame, 1);
		imshow("input", frame);
		if (frame.channels() == 4)
			cvtColor(frame, frame, COLOR_BGRA2BGR);
		cvtColor(frame, gray, COLOR_BGR2GRAY);
		equalizeHist(gray, gray);
		faceDetector.detectMultiScale(gray, faces, 1.2, 1, 0, Size(30, 30), Size(400, 400));
		for (size_t t = 0; t < faces.size(); t++) {
			count++;
			rectangle(frame, faces[t], Scalar(0, 255, 0), 2, 8, 0);
		}
		float fps = getTickFrequency() / (getTickCount() - start);
		ostringstream ss;ss.str("");
		ss << "FPS: " << fps << " ; inference time: " << time << " ms";
		putText(frame, ss.str(), Point(20, 20), 0, 0.75, Scalar(0, 0, 255), 2, 8);
		imshow("haar_face_detection", frame);
		if (waitKey(1) >= 0) break;
	}

    printf("total face: %d\n", count);
}

2、 DNN人脸检测

#include <opencv2/dnn.hpp>
#include <opencv2/opencv.hpp>

using namespace cv;
using namespace cv::dnn;

#include <iostream>
#include <cstdlib>
using namespace std;

const size_t inWidth = 300;
const size_t inHeight = 300;
const double inScaleFactor = 1.0;
const Scalar meanVal(104.0, 177.0, 123.0);
const float confidenceThreshold = 0.7;
void face_detect_dnn();
int main(int argc, char** argv)
{
    face_detect_dnn();
    waitKey(0);
    return 0;
}

void face_detect_dnn() {
    //这里采用tensorflow模型
    std::string modelBinary = "./models/dnn/face_detector/opencv_face_detector_uint8.pb";
    std::string modelDesc = "./models/dnn/face_detector/opencv_face_detector.pbtxt";
    // 初始化网络
    dnn::Net net = readNetFromTensorflow(modelBinary, modelDesc);

    net.setPreferableBackend(DNN_BACKEND_OPENCV);
    net.setPreferableTarget(DNN_TARGET_CPU);
    if (net.empty())
    {
        printf("Load models fail...\n");
        return;
    }

    // 打开摄像头
    // VideoCapture capture(0);
    VideoCapture capture("./video/test.mp4");
    if (!capture.isOpened()) {
        printf("Don't find video...\n");
        return;
    }

    Mat frame;
    int count=0;
    while (capture.read(frame)) {
        int64 start = getTickCount();
        if (frame.empty())
        {
            break;
        }
        // 水平镜像调整
        // flip(frame, frame, 1);
        imshow("input", frame);
        if (frame.channels() == 4)
            cvtColor(frame, frame, COLOR_BGRA2BGR);

        // 输入数据调整
        Mat inputBlob = blobFromImage(frame, inScaleFactor,
            Size(inWidth, inHeight), meanVal, false, false);
        net.setInput(inputBlob, "data");

        // 人脸检测
        Mat detection = net.forward("detection_out");
        vector<double> layersTimings;
        double freq = getTickFrequency() / 1000;
        double time = net.getPerfProfile(layersTimings) / freq;
        Mat detectionMat(detection.size[2], detection.size[3], CV_32F, detection.ptr<float>());

        ostringstream ss;
        for (int i = 0; i < detectionMat.rows; i++)
        {
            // 置信度 0～1之间
            float confidence = detectionMat.at<float>(i, 2);
            if (confidence > confidenceThreshold)
            {
                count++;
                int xLeftBottom = static_cast<int>(detectionMat.at<float>(i, 3) * frame.cols);
                int yLeftBottom = static_cast<int>(detectionMat.at<float>(i, 4) * frame.rows);
                int xRightTop = static_cast<int>(detectionMat.at<float>(i, 5) * frame.cols);
                int yRightTop = static_cast<int>(detectionMat.at<float>(i, 6) * frame.rows);

                Rect object((int)xLeftBottom, (int)yLeftBottom,
                    (int)(xRightTop - xLeftBottom),
                    (int)(yRightTop - yLeftBottom));

                rectangle(frame, object, Scalar(0, 255, 0));

                ss << confidence;
                std::string conf(ss.str());
                std::string label = "Face: " + conf;
                int baseLine = 0;
                Size labelSize = getTextSize(label, FONT_HERSHEY_SIMPLEX, 0.5, 1, &baseLine);
                rectangle(frame, Rect(Point(xLeftBottom, yLeftBottom - labelSize.height),
                    Size(labelSize.width, labelSize.height + baseLine)),
                    Scalar(255, 255, 255), FILLED);
                putText(frame, label, Point(xLeftBottom, yLeftBottom),
                    FONT_HERSHEY_SIMPLEX, 0.5, Scalar(0, 0, 0));
            }
        }
        float fps = getTickFrequency() / (getTickCount() - start);
        ss.str("");
        ss << "FPS: " << fps << " ; inference time: " << time << " ms";
        putText(frame, ss.str(), Point(20, 20), 0, 0.75, Scalar(0, 0, 255), 2, 8);
        imshow("dnn_face_detection", frame);
        if (waitKey(1) >= 0) break;
    }
    printf("total face: %d\n", count);
}