opencv -dnn人脸识别
来源:互联网 发布:网络基站都是华为的吗 编辑:程序博客网 时间:2024/05/17 15:06
随着深度学习的发展,opencv3.1也可以直接调用caffe或者torch。下面是使用opencv的dnn模块来进行人脸识别:
1:编译opencv3.1
首先下载opencv源码https://github.com/opencv/opencv
下载Cmake https://cmake.org/download/
下载opencv的
具体的camke过程可以参考这篇博客:
http://www.cnblogs.com/jliangqiu2016/p/5597501.html
编译完成后可以把不需要的文件删除仅保留include bin lib 文件即可。
编译好的opencv3.1和普通opencv的配置过程一样:
opencv_aruco310.libopencv_bgsegm310.libopencv_bioinspired310.libopencv_calib3d310.libopencv_ccalib310.libopencv_core310.libopencv_cudaarithm310.libopencv_cudabgsegm310.libopencv_cudacodec310.libopencv_cudafeatures2d310.libopencv_cudafilters310.libopencv_cudaimgproc310.libopencv_cudalegacy310.libopencv_cudaobjdetect310.libopencv_cudaoptflow310.libopencv_cudastereo310.libopencv_cudawarping310.libopencv_cudev310.libopencv_datasets310.libopencv_dnn310.libopencv_dpm310.libopencv_face310.libopencv_features2d310.libopencv_flann310.libopencv_fuzzy310.libopencv_highgui310.libopencv_imgcodecs310.libopencv_imgproc310.libopencv_line_descriptor310.libopencv_ml310.libopencv_objdetect310.libopencv_optflow310.libopencv_photo310.libopencv_plot310.libopencv_reg310.libopencv_rgbd310.libopencv_saliency310.libopencv_shape310.libopencv_stereo310.libopencv_stitching310.libopencv_structured_light310.libopencv_superres310.libopencv_surface_matching310.libopencv_text310.libopencv_tracking310.libopencv_ts310.libopencv_video310.libopencv_videoio310.libopencv_videostab310.libopencv_viz310.libopencv_xfeatures2d310.libopencv_ximgproc310.libopencv_xobjdetect310.libopencv_xphoto310.lib
在opencv的源码中提供了dnn的test.cpp
下面具体分析代码:
/* Find best class for the blob (i. e. class with maximal probability) */
获取prob层的输出:实际意义为测试图片所对应与标签的概率值。resize成一个列向量,然后排序,输出最大值和最大值所对应的位置。
void getMaxClass(dnn::Blob &probBlob, int *classId, double *classProb){ Mat probMat = probBlob.matRefConst().reshape(1, 1); //reshape the blob to 1x1000 matrix Point classNumber; minMaxLoc(probMat, NULL, classProb, NULL, &classNumber); *classId = classNumber.x;}
相关系数函数:一种相似性度量用于判断两个人的相似性距离。
float mean(const std::vector<float>& v){ assert(v.size() != 0); float ret = 0.0; for (std::vector<float>::size_type i = 0; i != v.size(); ++i) { ret += v[i]; } return ret / v.size();}float cov(const std::vector<float>& v1, const std::vector<float>& v2){ assert(v1.size() == v2.size() && v1.size() > 1); float ret = 0.0; float v1a = mean(v1), v2a = mean(v2); for (std::vector<float>::size_type i = 0; i != v1.size(); ++i) { ret += (v1[i] - v1a) * (v2[i] - v2a); } return ret / (v1.size() - 1);}// 相关系数float coefficient(const std::vector<float>& v1, const std::vector<float>& v2){ assert(v1.size() == v2.size()); return cov(v1, v2) / sqrt(cov(v1, v1) * cov(v2, v2));}
cos相似性距离函数:
//cos 相似性度量float cos_distance(const std::vector<float>& vecfeature1, vector<float>& vecfeature2){ float cos_dis=0; float dotmal=0, norm1=0, norm2=0; for (int i = 0; i < vecfeature1.size(); i++) { dotmal += vecfeature1[i] * vecfeature2[i]; norm1 += vecfeature1[i] * vecfeature1[i]; norm2 += vecfeature2[i] * vecfeature2[i]; } norm1 = sqrt(norm1); norm2 = sqrt(norm2); cos_dis = dotmal / (norm1*norm2); return cos_dis;}
下面是主函数:
/**/////#include <opencv2/dnn.hpp>#include <opencv2/imgproc.hpp>#include <opencv2/highgui.hpp>using namespace cv;using namespace cv::dnn;#include <fstream>#include <iostream>#include <cstdlib>#include <time.h>#include<math.h>using namespace std;/* Find best class for the blob (i. e. class with maximal probability) */void getMaxClass(dnn::Blob &probBlob, int *classId, double *classProb){ Mat probMat = probBlob.matRefConst().reshape(1, 1); //reshape the blob to 1x1000 matrix Point classNumber; minMaxLoc(probMat, NULL, classProb, NULL, &classNumber); *classId = classNumber.x;}std::vector<String> readClassNames(const char *filename = "synset_words.txt"){ std::vector<String> classNames; std::ifstream fp(filename); if (!fp.is_open()) { std::cerr << "File with classes labels not found: " << filename << std::endl; exit(-1); } std::string name; while (!fp.eof()) { std::getline(fp, name); if (name.length()) classNames.push_back(name.substr(name.find(' ') + 1)); } fp.close(); return classNames;}string Int_String(int a){ std::stringstream ss; std::string str; ss << a; ss >> str; return str;}float mean(const std::vector<float>& v){ assert(v.size() != 0); float ret = 0.0; for (std::vector<float>::size_type i = 0; i != v.size(); ++i) { ret += v[i]; } return ret / v.size();}float cov(const std::vector<float>& v1, const std::vector<float>& v2){ assert(v1.size() == v2.size() && v1.size() > 1); float ret = 0.0; float v1a = mean(v1), v2a = mean(v2); for (std::vector<float>::size_type i = 0; i != v1.size(); ++i) { ret += (v1[i] - v1a) * (v2[i] - v2a); } return ret / (v1.size() - 1);}// 相关系数float coefficient(const std::vector<float>& v1, const std::vector<float>& v2){ assert(v1.size() == v2.size()); return cov(v1, v2) / sqrt(cov(v1, v1) * cov(v2, v2));}//cos 相似性度量float cos_distance(const std::vector<float>& vecfeature1, vector<float>& vecfeature2){ float cos_dis=0; float dotmal=0, norm1=0, norm2=0; for (int i = 0; i < vecfeature1.size(); i++) { dotmal += vecfeature1[i] * vecfeature2[i]; norm1 += vecfeature1[i] * vecfeature1[i]; norm2 += vecfeature2[i] * vecfeature2[i]; } norm1 = sqrt(norm1); norm2 = sqrt(norm2); cos_dis = dotmal / (norm1*norm2); return cos_dis;}int main(){ String modelTxt = "VGG_FACE_deploy.prototxt"; String modelBin = "VGG_FACE.caffemodel"; //String imageFile = (argc > 1) ? argv[1] : "ak.png"; /*String modelTxt = "bvlc_googlenet.prototxt"; String modelBin = "bvlc_googlenet.caffemodel"; String imageFile = (argc > 1) ? argv[1] : "1.jpg";*/ //! [Create the importer of Caffe model] Ptr<dnn::Importer> importer; try //Try to import Caffe GoogleNet model { importer = dnn::createCaffeImporter(modelTxt, modelBin); } catch (const cv::Exception &err) //Importer can throw errors, we will catch them { std::cerr << err.msg << std::endl; } //! [Create the importer of Caffe model] if (!importer) { std::cerr << "Can't load network by using the following files: " << std::endl; std::cerr << "prototxt: " << modelTxt << std::endl; std::cerr << "caffemodel: " << modelBin << std::endl; std::cerr << "bvlc_googlenet.caffemodel can be downloaded here:" << std::endl; std::cerr << "http://dl.caffe.berkeleyvision.org/bvlc_googlenet.caffemodel" << std::endl; exit(-1); } //! [Initialize network] dnn::Net net; importer->populateNet(net); importer.release(); //We don't need importer anymore //! [Initialize network] //! [Prepare blob] //===============进行训练样本提取=======================可修改==================== //========================五个人,每人一张照片==================================== std::vector<Mat> train; std::vector<int> train_label; int train_man = 1, train_num = 1;//训练的人的种类、人的个数 for (train_man = 1; train_man <= 4; train_man++) { for (train_num = 1; train_num <= 1; train_num++) { string train_road = "VGG_train/" + Int_String(train_man) + "-" + Int_String(train_num) + ".jpg"; cv::Mat train_Sample = imread(train_road); // cv::imshow("train_1",train_Sample); // waitKey(1); if (!train_Sample.empty()) { train.push_back(train_Sample); train_label.push_back(train_man); cout << "There is train pic!!" << train_man << "" << train_num << endl; } else { cout << "There is no pic!!" << train_man << "" << train_num; getchar(); exit(-1); } } } clock_t start, finish; double totaltime; start = clock(); dnn::Blob train_blob = dnn::Blob(train); net.setBlob(".data", train_blob); cout << "Please wait..." << endl; net.forward(); dnn::Blob prob = net.getBlob("fc7");//提取哪一层 Mat probMat = prob.matRefConst().reshape(1, 1); //reshape the blob to 1x4096 matrix finish = clock(); totaltime = (double)(finish - start) / CLOCKS_PER_SEC; totaltime = totaltime / 4; std::cout << "extract feature the train image is :" << totaltime << "sec" << std::endl; vector < vector <float> > feature_vector; feature_vector.clear(); int train_man_num = 0;//第几个人 clock_t start2, finish2; double totaltime2; start2 = clock(); for (train_man_num = 0; train_man_num <= 3; train_man_num++) { vector<float> feature_one;//单个人的feature int channel = 0; while (channel < 4096)//看网络相应层的output { feature_one.push_back(*prob.ptrf(train_man_num, channel, 1, 1)); channel++; string train_txt = Int_String(train_man_num) + ".txt"; ofstream myfile(train_txt, ios::app); //example.txt是你要输出的文件的名字,这里把向量都分开保存为txt,以便于后面可以直接读取 myfile << *prob.ptrf(train_man_num, channel, 1, 1) << endl; } feature_vector.push_back(feature_one);//把它赋给二维数组 feature_one.clear(); } finish2 = clock(); totaltime2 = (double)(finish2 - start2) / CLOCKS_PER_SEC; totaltime2 = totaltime2 / 4; std::cout << "save the train image feature is :" << totaltime2 << "sec" << std::endl; cout << "Successful extract!!!" << endl; train_blob.offset(); //===============================================================================// // // // Test // // // //===============================================================================// //string test_fileroad = "C://wamp//www//pic//" + Int_String(x) + ".jpg";//图片的地方,改成摄像头也可以。 Mat testSample = imread("C:\\Users\\naslab\\Desktop\\opencv_dnn _face_train\\opencv_dnn\\VGG_test\\1.jpg"); if (testSample.empty()) cout << "There is no testSample ..." << endl; else { //testSample = Facedetect(testSample); vector<Mat> test; vector<int> test_label; test.push_back(testSample); test_label.push_back(0); //then dnn::Blob test_blob = dnn::Blob(test);//如果用原来的似乎会报错。。。 net.setBlob(".data", test_blob); cout << "extracting features..." << endl; clock_t start1, finish1; double totaltime1; start1 = clock(); net.forward(); dnn::Blob prob_test = net.getBlob("fc7"); vector<float> test_feature;//第8层的特征 int channel = 0; while (channel < 4096) { test_feature.push_back(*prob_test.ptrf(0, channel, 1, 1)); channel++; } finish1 = clock(); totaltime1 = (double)(finish1 - start1) / CLOCKS_PER_SEC; std::cout << "extract feature the train image is :" << totaltime1 << "sec" << std::endl; cout << "we got it.." << endl; float higher_score = 0;//相似度 int T_number = 0; for (int test_num_vector = 0; test_num_vector <= 3; test_num_vector++) { float score1 = coefficient(feature_vector[test_num_vector], test_feature); float score = cos_distance(feature_vector[test_num_vector], test_feature); cout << "The coefficient" << test_num_vector << "----------to--------" << score1 << endl; cout << "The cos_distance" << test_num_vector << "----------to--------" << score << endl; if (score > higher_score) { higher_score = score; T_number = test_num_vector; } } cv::imshow("trainSample", train[T_number]);//可以直接把和测试样本最相近的一张图亮出来 cv::waitKey(1); } cv::imshow("testSample", testSample); cv::waitKey(0);} //main
里面我有所修改,本来提取的是fc8层的,后来改成fc7层4096维特征。
这速度真喜人!!!!!!!!提取个特征就要8秒!!!!!!!
1:程序的改进方向:
1:保存提取的特征为dat文件,这样可以预先训练,直接测试即可
2:程序输出的是Bolb格式的数据,保存数据占用的时间比较长,可以修改一下。
3:还是使用caffe for windows吧!
下面是一些参考链接:
http://blog.csdn.net/mr_curry/article/details/52183263
http://docs.opencv.org/trunk/d5/de7/tutorial_dnn_googlenet.html
http://docs.opencv.org/trunk/de/d25/tutorial_dnn_build.html
- opencv -dnn人脸识别
- opencv -dnn人脸识别(2016-10-27)
- 使用Opencv的dnn模块进行深度学习人脸识别(速度较慢)
- Opencv如何使用dnn读取caffemodel进行识别
- OpenCV人脸识别
- opencv人脸识别
- openCV人脸识别
- Opencv 人脸识别
- opencv人脸识别
- Opencv 人脸识别
- opencv 人脸识别
- OpenCv人脸识别
- openCV人脸识别
- OpenCV人脸识别
- 人脸识别opencv
- openCV人脸识别
- opencv人脸识别
- OpenCV的行人识别&人脸识别
- 【VOLTE】SPS 半持续调度
- 【VOLTE】ROHC 健壮性包头压缩
- 【VOLTE】Early Offer VS Later Offer
- 布局管理(分割窗口QSplitter类、停靠窗口QDockWidget类、堆栈窗体QStackedWidget类、基本布局(QLayout))
- google的语音搜索工具
- opencv -dnn人脸识别
- 【VOLTE】Early media VS Later Media
- 【OpenCV】人脸旋转角度计算
- 【VOLTE】VOLTE中的Precondition
- HTML之<input>标签
- 【VOLTE】100rel
- 单点登录
- 【VOLTE】MAX-FORWARD 最大跳转数
- 【VOLTE】P-Access-Network-Info 私有报头-接入网络信心