I realized my mistake - it wasn't connected with pre-processing at all (thanks to @DavidBrown and @John). I used handwritten dataset of digits instead of printed (capitalized). I didn't find such database in the web so I decided to create it by myself. I have uploaded my database to the Google Drive.
And here's how you can use it (train and classify):
int digitSize = 16;
//returns list of files in specific directory
static vector<string> getListFiles(const string& dirPath)
{
vector<string> result;
DIR *dir;
struct dirent *ent;
if ((dir = opendir(dirPath.c_str())) != NULL)
{
while ((ent = readdir (dir)) != NULL)
{
if (strcmp(ent->d_name, ".") != 0 && strcmp(ent->d_name, "..") != 0 )
{
result.push_back(ent->d_name);
}
}
closedir(dir);
}
return result;
}
void DigitClassifier::train(const string& imagesPath)
{
int num = 510;
int size = digitSize * digitSize;
Mat trainData = Mat(Size(size, num), CV_32FC1);
Mat responces = Mat(Size(1, num), CV_32FC1);
int counter = 0;
for (int i=1; i<=9; i++)
{
char digit[2];
sprintf(digit, "%d/", i);
string digitPath(digit);
digitPath = imagesPath + digitPath;
vector<string> images = getListFiles(digitPath);
for (int j=0; j<images.size(); j++)
{
Mat mat = imread(digitPath+images[j], 0);
resize(mat, mat, Size(digitSize, digitSize));
mat.convertTo(mat, CV_32FC1);
mat = mat.reshape(1,1);
for (int k=0; k<size; k++)
{
trainData.at<float>(counter*size+k) = mat.at<float>(k);
}
responces.at<float>(counter) = i;
counter++;
}
}
knn.train(trainData, responces);
}
int DigitClassifier::classify(const Mat& img) const
{
Mat tmp = img.clone();
resize(tmp, tmp, Size(digitSize, digitSize));
tmp.convertTo(tmp, CV_32FC1);
return knn.find_nearest(tmp.reshape(1, 1), 5);
}