SVM人脸识别

来源：互联网发布：远程教育软件哪家好编辑：程序博客网时间：2024/06/05 16:05

SVM在中等维度的分类问题中，有较好的表现，其在某种程度上构建了一个简单的网络结构，类似于神经网络中的RBF神经网络。

人脸数据集是经典的分类和聚类问题中经常使用的数据集，维度相对不高，灰度图像，这里选用64*64的人脸图像，将其reshape从1*64^2的一维数组，共40类样本，每组10个。

通常在SVM解决较高维度问题时，需要将其适度降维，这里选用传统的线性降维方法PCA（KPCA同样适用，只是人脸数据集PCA已经够用，不用换成更复杂的非线性降维）。

导入相关模块；
获取数据；
标准化（这里可以不用，图像数据一般已经是标准的）
比较降维到不同的维度下，各自的效果对比（这时SVM的参数不变，选用RBF核函数）
用网格搜索最佳的pca参数和SVM参数，效果演示。

以下为实验代码模块

（1）导入模块

# -*-encoding:utf-8-*-'''created by zwg in 2017-03-01'''import numpy,timefrom sklearn import datasetsfrom sklearn import svmfrom sklearn import decompositionfrom sklearn import manifoldfrom sklearn.cross_validation import train_test_split as ttsfrom sklearn import svm,neural_networkfrom sklearn.metrics import classification_report,precision_score,recall_score,f1_scorefrom sklearn import pipelinefrom sklearn.preprocessing import StandardScaler,MinMaxScalerfrom sklearn.grid_search import GridSearchCVfrom matplotlib import pyplotimport matplotlib.colors as colors

（2）获取数据

def get_data():    face_data=datasets.fetch_olivetti_faces()    #face_data=datasets.load_iris()    data=face_data.data    target=face_data.target    return data,target

（3）PCA函数

def pca(x,n):    pca_learner=decomposition.PCA(n_components=n)    x=pca_learner.fit_transform(x)    return x

（4）PCA & SVM（返回得分系数）

def pca_svm(pca_n=10,svm_C=1):    t1=time.time()    data,target=get_data()    #scale_learner=StandardScaler()    #data=scale_learner.fit_transform(data)    x_train,x_test,y_train,y_test=tts(data,target,random_state=33)    pca_learner=decomposition.PCA(n_components=pca_n)    x_train=pca_learner.fit_transform(x_train)    svm_learner=svm.SVC(C=svm_C)    svm_learner.fit(x_train,y_train)    x_test_pre=pca_learner.transform(x_test)    y_test_pre=svm_learner.predict(x_test_pre)    # report=classification_report(y_test,y_test_pre)    # print 'The Main Explanied: ',numpy.sum(pca_learner.explained_variance_ratio_)    # print report    # print x_test_pre.shape,y_test_pre.shape,y_test.shape    ac=svm_learner.score(x_test_pre,y_test)    p=precision_score(y_test,y_test_pre,average='weighted')    r=recall_score(y_test,y_test_pre,average='weighted')    f1=2.0/(1.0/p+1.0/r)    t=time.time()-t1    return ac,p,r,f1,t

（5）PCA降维到不同维度下效果比较

def pca_svm_time_score_compare():    ac_score=[]    p_score=[]    r_score=[]    f1_score=[]    tt=[]    stand=MinMaxScaler((20,30))    steps=numpy.arange(10,410,10)    for n in steps:        ac,p,r,f1,t=pca_svm(pca_n=n)        p_score.append(p)        f1_score.append(f1)        r_score.append(r)        ac_score.append(ac)        tt.append(t)    p_score_stand=stand.fit_transform(numpy.array(p_score).reshape((-1,1)))    r_score_stand=stand.fit_transform(numpy.array(r_score).reshape((-1,1)))    f1_score_stand=stand.fit_transform(numpy.array(f1_score).reshape((-1,1)))    ac_score_stand=stand.fit_transform(numpy.array(ac_score).reshape((-1,1)))    figure=pyplot.figure()            pyplot.subplot(2,1,1)    pyplot.scatter(steps,f1_score,label='f1-score',color='red',s=p_score_stand,alpha=0.7)    pyplot.scatter(steps,r_score,label='recall-score',color='blue',s=r_score_stand,alpha=0.7)    pyplot.scatter(steps,p_score,label='precision-score',color='yellow',s=f1_score_stand,alpha=0.7)    pyplot.scatter(steps,ac_score,label='accuracy-score',color='purple',s=ac_score_stand,alpha=0.7)    pyplot.xlabel('n-components')    pyplot.ylabel('score')    pyplot.legend()    pyplot.title('The Score Of SVM After PCA To N_components')    pyplot.subplot(2,1,2)    pyplot.plot(steps,tt,label='cost-time',color='black',marker='o')    # for i in range(len(tt)):        # pyplot.text(steps[i],ac_score[i],str(round(tt[i],1))+'s',fontdict=dict(size=10,weight='normal'))        # pyplot.plot([steps[i],steps[i]],[0,ac_score[i]],'--b')    pyplot.legend()    pyplot.xlabel('n-components')    pyplot.ylabel('time')    pyplot.show()

（6）网格搜索pca和SVM最佳参数，并进行可视化

# pca before svm fitting is betterdef pca_svm_pipeline():    #svm_C=numpy.linspace(0.5,10,10)    svm_C=[1]    pca_n_components=numpy.arange(5,200,10)    data,target=get_data()    x_train,x_test,y_train,y_test=tts(data,target,random_state=33)    #scale_learner=StandardScaler()    pca_learner=decomposition.PCA()    svm_learner=svm.SVC()    pipe=pipeline.Pipeline([('pca',pca_learner),('svm',svm_learner)])    gscv=GridSearchCV(pipe,                      {'pca__n_components':pca_n_components,'svm__C':svm_C},n_jobs=-1)    gscv.fit(x_train,y_train)    y_test_pre=gscv.predict(x_test)    report=classification_report(y_test,y_test_pre)    print gscv.best_params_    print report    target_pre=gscv.predict(data)    n1,n2=data.shape    figure=pyplot.figure()    L=numpy.zeros((40,))    xx=numpy.linspace(0,1,64)+13    yy=numpy.linspace(1,0,64)+13    xx,yy=numpy.meshgrid(xx,yy)    for i in xrange(n1):        k=target_pre[i]        g=L[k]        L[k]+=1        xx1=xx-k        yy1=yy-g        pyplot.contourf(xx1,yy1,data[i].reshape((64,64)),cmap='gray')        if target[i]!=target_pre[i]:            pyplot.scatter(numpy.mean(xx1),numpy.mean(yy1),marker='x',c='red',s=40)    pyplot.axis('off')    pyplot.grid('off')    pyplot.title('PCA & SVM Recongnize Faces')    pyplot.show()

（7）调用

if __name__=='__main__':    pca_svm_pipeline()  #Grid Search and show the results    pca_svm_time_score_compare()  #Direct Search

结果：（1）降维至10~60多维时，效果最好。

结果：（2）最佳参数以及分类结果，pca降至35维，SCM参数C=1，

{'pca__n_components': 35, 'svm__C': 1}
precision recall f1-score support

0 1.00 0.80 0.89 5
1 1.00 1.00 1.00 1
3 1.00 0.67 0.80 3
4 1.00 1.00 1.00 1
5 1.00 1.00 1.00 1
6 1.00 1.00 1.00 3
7 0.75 1.00 0.86 3
8 1.00 1.00 1.00 1
9 0.67 1.00 0.80 2
10 1.00 1.00 1.00 1
11 1.00 1.00 1.00 1
12 0.50 0.50 0.50 2
13 1.00 1.00 1.00 1
14 1.00 1.00 1.00 3
15 1.00 0.50 0.67 2
17 1.00 1.00 1.00 2
18 1.00 1.00 1.00 2
19 1.00 1.00 1.00 3
20 1.00 1.00 1.00 2
21 1.00 1.00 1.00 2
22 0.67 1.00 0.80 2
23 1.00 0.50 0.67 2
24 1.00 1.00 1.00 4
25 1.00 1.00 1.00 1
26 1.00 1.00 1.00 4
27 1.00 1.00 1.00 4
28 1.00 1.00 1.00 2
29 1.00 1.00 1.00 4
30 1.00 1.00 1.00 6
31 1.00 1.00 1.00 1
32 1.00 1.00 1.00 4
33 1.00 1.00 1.00 4
34 1.00 1.00 1.00 4
35 1.00 1.00 1.00 3
36 1.00 1.00 1.00 5
37 1.00 1.00 1.00 2
38 1.00 1.00 1.00 4
39 0.75 1.00 0.86 3

avg / total 0.96 0.95 0.95 100

0 0