I have been using OpenCV for a quite time. I decided to check its power for Machine Learning lately. So I ended up with implementing a neural network for face recognition. To summarize my strategy for face recognition :
- Read images from a csv of some face database.
- Roll images to a Mat array row wise.
- Apply PCA for dimensionality reduction.
- Use projections of PCA to train the network.
- Predict the test data using the trained network.
So everything was OK until the prediction stage. I was using the max responsed output unit to classify the face. So normally OpenCV's sigmoid implementation should give values in range of -1 to 1 which is stated at the docs. 1 is the max closure to class. After I got nearly 0 accuracy I checked the output responses for each class for each test data. I was suprised with the values : 14.53, -1.7 , #IND . If sigmoid was applied, how could i get these values ? Where am i doing wrong ?
To help you understand the matter and for the ones wondering how to apply PCA and use it with NN I m sharing my code :
Reading csv:
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(1, 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()) { Mat im = imread(path, 0); images.push_back(im); labels.push_back(atoi(classlabel.c_str())); } } }
Rolling images row by row :
Mat rollVectortoMat(const vector<Mat> &data)
{
Mat dst(static_cast<int>(data.size()), data[0].rows*data[0].cols, CV_32FC1);
for(unsigned int i = 0; i < data.size(); i++)
{
Mat image_row = data[i].clone().reshape(1,1);
Mat row_i = dst.row(i);
image_row.convertTo(row_i,CV_32FC1, 1/255.);
}
return dst;
}
Converting vector of labels to Mat of labels
Mat getLabels(const vector<int> &data,int classes = 20)
{
Mat labels(data.size(),classes,CV_32FC1);
for(int i = 0; i <data.size() ; i++)
{
int cls = data[i] - 1;
labels.at<float>(i,cls) = 1.0;
}
return labels;
}
MAIN
int main()
{
PCA pca;
vector<Mat> images_train;
vector<Mat> images_test;
vector<int> labels_train;
vector<int> labels_test;
read_csv("train1k.txt",images_train,labels_train);
read_csv("test1k.txt",images_test,labels_test);
Mat rawTrainData = rollVectortoMat(images_train);
Mat rawTestData = rollVectortoMat(images_test);
Mat trainLabels = getLabels(labels_train);
Mat testLabels = getLabels(labels_test);
int pca_size = 500;
Mat trainData(rawTrainData.rows, pca_size,rawTrainData.type());
Mat testData(rawTestData.rows,pca_size,rawTestData.type());
pca(rawTrainData,Mat(),CV_PCA_DATA_AS_ROW,pca_size);
for(int i = 0; i < rawTrainData.rows ; i++)
pca.project(rawTrainData.row(i),trainData.row(i));
for(int i = 0; i < rawTestData.rows ; i++)
pca.project(rawTestData.row(i),testData.row(i));
Mat layers = Mat(3,1,CV_32SC1);
int sz = trainData.cols ;
layers.row(0) = Scalar(sz);
layers.row(1) = Scalar(1000);
layers.row(2) = Scalar(20);
CvANN_MLP mlp;
CvANN_MLP_TrainParams params;
CvTermCriteria criteria;
criteria.max_iter = 1000;
criteria.epsilon = 0.00001f;
criteria.type = CV_TERMCRIT_ITER | CV_TERMCRIT_EPS;
params.train_method = CvANN_MLP_TrainParams::BACKPROP;
params.bp_dw_scale = 0.1f;
params.bp_moment_scale = 0.1f;
params.term_crit = criteria;
mlp.create(layers,CvANN_MLP::SIGMOID_SYM);
int i = mlp.train(trainData,trainLabels,Mat(),Mat(),params);
int t = 0, f = 0;
for(int i = 0; i < testData.rows ; i++)
{
Mat response(1,20,CV_32FC1);
Mat sample = testData.row(i);
mlp.predict(sample,response);
float max = -1000000000000.0f;
int cls = -1;
for(int j = 0 ; j < 20 ; j++)
{
float value = response.at<float>(0,j);
if(value > max)
{
max = value;
cls = j + 1;
}
}
if(cls == labels_test[i])
t++;
else
f++;
}
return 0;
}
NOTE: I used AT&T 's first 20 class for my dataset.