生活随笔
收集整理的這篇文章主要介紹了
opencv 人脸识别 （二）训练和识别
小編覺得挺不錯的,現(xiàn)在分享給大家,幫大家做個參考.
上一篇中我們對訓(xùn)練數(shù)據(jù)做了一些預(yù)處理，檢測出人臉并保存在\pic\color\x文件夾下（x=1,2,3,...類別號），本文做訓(xùn)練和識別。為了識別，首先將人臉訓(xùn)練數(shù)據(jù) 轉(zhuǎn)為灰度、對齊、歸一化，再放入分類器（EigenFaceRecognizer）,最后用訓(xùn)練出的model進行predict。
-----------------------------------------
環(huán)境：vs2010+opencv 2.4.6.0
特征：eigenface
Input：一個人臉數(shù)據(jù)庫，15個人，每人20個樣本（左右）。
Output：人臉檢測，并識別出每張檢測到的人臉。
-----------------------------------------
1. 為訓(xùn)練數(shù)據(jù)預(yù)處理（?轉(zhuǎn)為灰度、對齊、歸一化?）
- 轉(zhuǎn)為灰度和對齊是后面做訓(xùn)練時EigenFaceRecognizer的要求；
- 歸一化是防止光照帶來的影響
在上一篇的?2.2 Prehelper.cpp文件中加入函數(shù)
void resizeandtogray(char* dir,int k,? vector<Mat> &images, vector<int> &labels,
vector<Mat> &testimages, vector<int> &testlabels);
[cpp]?view plaincopy
void?resizeandtogray(char*?dir,int?K,?vector<Mat>?&images,?vector<int>?&labels,?? ????vector<Mat>?&testimages,?vector<int>?&testlabels)?? {?? ????IplImage*?standard?=?cvLoadImage("D:\\privacy\\picture\\photo\\2.jpg",CV_LOAD_IMAGE_GRAYSCALE);?? ????string?cur_dir;?? ????char?id[5];?? ????int?i,j;?? ????for(int?i=1;?i<=K;?i++)?? ????{?? ????????cur_dir?=?dir;?? ????????cur_dir.append("gray\\");????? ????????_itoa(i,id,10);?? ????????cur_dir.append(id);?? ????????const?char*?dd?=?cur_dir.c_str();?? ????????CStatDir?statdir;?? ????????if?(!statdir.SetInitDir(dd))?? ????????{?? ????????????puts("Dir?not?exist");?? ????????????return;?? ????????}?? ????????cout<<"Processing?samples?in?Class?"<<i<<endl;?? ????????vector<char*>file_vec?=?statdir.BeginBrowseFilenames("*.*");?? ????????for?(j=0;j<file_vec.size();j++)?? ????????{?? ????????????IplImage*?cur_img?=?cvLoadImage(file_vec[j],CV_LOAD_IMAGE_GRAYSCALE);?? ????????????cvResize(cur_img,standard,CV_INTER_AREA);?? ????????????Mat?cur_mat?=?cvarrToMat(standard,true),des_mat;?? ????????????cv::normalize(cur_mat,des_mat,0,?255,?NORM_MINMAX,?CV_8UC1);?? ????????????cvSaveImage(file_vec[j],cvCloneImage(&(IplImage)?des_mat));?? ????????????if(j!=file_vec.size())?? ????????????{?? ????????????????????images.push_back(des_mat);?? ????????????????????labels.push_back(i);?? ????????????}?? ????????????else?? ????????????{?? ????????????????testimages.push_back(des_mat);?? ????????????????testlabels.push_back(i);?? ????????????}?? ????????}?? ????????cout<<file_vec.size()<<"?images."<<endl;?? ????}?? }??
并在main中調(diào)用：
[cpp]?view plaincopy
int?main(?)?? {?? ????CvCapture*?capture?=?0;?? ????Mat?frame,?frameCopy,?image;?? ????string?inputName;????? ????int?mode;?? ?? ????char?dir[256]?=?"D:\\Courses\\CV\\Face_recognition\\pic\\";??? ?????? ????vector<Mat>?images,testimages;?? ????vector<int>?labels,testlabels;?? ????resizeandtogray(dir,K,images,labels,testimages,testlabels);??? ?????? ????system("pause");?? ????return?0;?? }??
2. 訓(xùn)練
有了vector<Mat> images,testimages; vector<int> labels,testlabels; 可以開始訓(xùn)練了，我們采用EigenFaceRecognizer建模。
在Prehelper.cpp中加入函數(shù)
Ptr<FaceRecognizer> Recognition(vector<Mat> images, vector<int> labels,vector<Mat> testimages, vector<int> testlabels)；
[cpp]?view plaincopy
Ptr<FaceRecognizer>?Recognition(vector<Mat>?images,?vector<int>?labels,?? ????vector<Mat>?testimages,?vector<int>?testlabels)?? {?? ????Ptr<FaceRecognizer>?model?=?createEigenFaceRecognizer(10);?? ????cout<<"train"<<endl;?? ????model->train(images,labels);?? ????int?i,acc=0,predict_l;?? ????for?(i=0;i<testimages.size();i++)?? ????{?? ????????predict_l?=?model->predict(testimages[i]);?? ????????if(predict_l?!=?testlabels[i])?? ????????{?? ????????????cout<<"An?error?in?recognition:?sample?"<<i+1<<",?predict?"<<?? ????????????????predict_l<<",?groundtruth?"<<testlabels[i]<<endl;?? ????????????imshow("error?1",testimages[i]);?? ????????????waitKey();?? ????????}?? ????????else?? ????????????acc++;?? ????}?? ????cout<<"Recognition?Rate:?"<<acc*1.0/testimages.size()<<endl;?? ????return?model;?? }??
Recognization()輸出分錯的樣本和正確率，最后返回建模結(jié)果Ptr<FaceRecognizer> model
主函數(shù)改為：
[cpp]?view plaincopy
int?main(?)?? {?? ????CvCapture*?capture?=?0;?? ????Mat?frame,?frameCopy,?image;?? ????string?inputName;????? ????int?mode;?? ?? ????char?dir[256]?=?"D:\\Courses\\CV\\Face_recognition\\pic\\";??? ?????? ????vector<Mat>?images,testimages;?? ????vector<int>?labels,testlabels;?? ?????? ????resizeandtogray(dir,K,images,labels,testimages,testlabels);??? ?????? ????Ptr<FaceRecognizer>?model?=?Recognition(images,labels,testimages,testlabels);?? ????char*?dirmodel?=?new?char?[256];?? ????strcpy(dirmodel,dir);?strcat(dirmodel,"model.out");?? ????FILE*?f?=?fopen(dirmodel,"w");?? ????fwrite(model,sizeof(model),1,f);?? ????system("pause");?? ????return?0;?? }??
最終結(jié)果：一個錯分樣本，正確率93.3%
文章所用代碼打包鏈接：http://download.csdn.net/detail/abcjennifer/7047853
from:?http://blog.csdn.net/abcjennifer/article/details/20446077
總結(jié)
以上是生活随笔為你收集整理的opencv 人脸识别 （二）训练和识别的全部內(nèi)容，希望文章能夠幫你解決所遇到的問題。
如果覺得生活随笔網(wǎng)站內(nèi)容還不錯，歡迎將生活随笔推薦給好友。
