How to input sample images in libsvm train code - c++

Question

I have downloaded the libsvm code for object detection. I am having problems in using the train svm code. I can't input the sample files properly. Anyone please help me how to input positive and negative images.Here is the train code.
#include <stdio.h>
#include <stdlib.h>
#include <string.h>
#include <ctype.h>
#include <errno.h>
#include "svm.h"
#define Malloc(type,n) (type *)malloc((n)*sizeof(type))
void print_null(const char *s) {}
void exit_with_help()
{
printf(
"Usage: svm-train [options] training_set_file [model_file]\n"
"options:\n"
"-s svm_type : set type of SVM (default 0)\n"
" 0 -- C-SVC (multi-class classification)\n"
" 1 -- nu-SVC (multi-class classification)\n"
" 2 -- one-class SVM\n"
" 3 -- epsilon-SVR (regression)\n"
" 4 -- nu-SVR (regression)\n"
"-t kernel_type : set type of kernel function (default 2)\n"
" 0 -- linear: u'*v\n"
" 1 -- polynomial: (gamma*u'*v + coef0)^degree\n"
" 2 -- radial basis function: exp(-gamma*|u-v|^2)\n"
" 3 -- sigmoid: tanh(gamma*u'*v + coef0)\n"
" 4 -- precomputed kernel (kernel values in training_set_file)\n"
"-d degree : set degree in kernel function (default 3)\n"
"-g gamma : set gamma in kernel function (default 1/num_features)\n"
"-r coef0 : set coef0 in kernel function (default 0)\n"
"-c cost : set the parameter C of C-SVC, epsilon-SVR, and nu-SVR (default 1)\n"
"-n nu : set the parameter nu of nu-SVC, one-class SVM, and nu-SVR (default 0.5)\n"
"-p epsilon : set the epsilon in loss function of epsilon-SVR (default 0.1)\n"
"-m cachesize : set cache memory size in MB (default 100)\n"
"-e epsilon : set tolerance of termination criterion (default 0.001)\n"
"-h shrinking : whether to use the shrinking heuristics, 0 or 1 (default 1)\n"
"-b probability_estimates : whether to train a SVC or SVR model for probability estimates, 0 or 1 (default 0)\n"
"-wi weight : set the parameter C of class i to weight*C, for C-SVC (default 1)\n"
"-v n: n-fold cross validation mode\n"
"-q : quiet mode (no outputs)\n"
);
exit(1);
}
void exit_input_error(int line_num)
{
fprintf(stderr,"Wrong input format at line %d\n", line_num);
exit(1);
}
void parse_command_line(int argc, char **argv, char *input_file_name, char *model_file_name);
void read_problem(const char *filename);
void do_cross_validation();
struct svm_parameter param; // set by parse_command_line
struct svm_problem prob; // set by read_problem
struct svm_model *model;
struct svm_node *x_space;
int cross_validation;
int nr_fold;
static char *line = NULL;
static int max_line_len;
static char* readline(FILE *input)
{
int len;
if(fgets(line,max_line_len,input) == NULL)
return NULL;
while(strrchr(line,'\n') == NULL)
{
max_line_len *= 2;
line = (char *) realloc(line,max_line_len);
len = (int) strlen(line);
if(fgets(line+len,max_line_len-len,input) == NULL)
break;
}
return line;
}
int main(int argc, char **argv)
{
char input_file_name[1024];
char model_file_name[1024];
const char *error_msg;
parse_command_line(argc, argv, input_file_name, model_file_name);
read_problem(input_file_name);
error_msg = svm_check_parameter(&prob,&param);
if(error_msg)
{
fprintf(stderr,"ERROR: %s\n",error_msg);
exit(1);
}
if(cross_validation)
{
do_cross_validation();
}
else
{
model = svm_train(&prob,&param);
if(svm_save_model(model_file_name,model))
{
fprintf(stderr, "can't save model to file %s\n", model_file_name);
exit(1);
}
svm_free_and_destroy_model(&model);
}
svm_destroy_param(&param);
free(prob.y);
free(prob.x);
free(x_space);
free(line);
return 0;
}
void do_cross_validation()
{
int i;
int total_correct = 0;
double total_error = 0;
double sumv = 0, sumy = 0, sumvv = 0, sumyy = 0, sumvy = 0;
double *target = Malloc(double,prob.l);
svm_cross_validation(&prob,&param,nr_fold,target);
if(param.svm_type == EPSILON_SVR ||
param.svm_type == NU_SVR)
{
for(i=0;i<prob.l;i++)
{
double y = prob.y[i];
double v = target[i];
total_error += (v-y)*(v-y);
sumv += v;
sumy += y;
sumvv += v*v;
sumyy += y*y;
sumvy += v*y;
}
printf("Cross Validation Mean squared error = %g\n",total_error/prob.l);
printf("Cross Validation Squared correlation coefficient = %g\n",
((prob.l*sumvy-sumv*sumy)*(prob.l*sumvy-sumv*sumy))/
((prob.l*sumvv-sumv*sumv)*(prob.l*sumyy-sumy*sumy))
);
}
else
{
for(i=0;i<prob.l;i++)
if(target[i] == prob.y[i])
++total_correct;
printf("Cross Validation Accuracy = %g%%\n",100.0*total_correct/prob.l);
}
free(target);
}
void parse_command_line(int argc, char **argv, char *input_file_name, char *model_file_name)
{
int i;
void (*print_func)(const char*) = NULL; // default printing to stdout
// default values
param.svm_type = C_SVC;
param.kernel_type = RBF;
param.degree = 3;
param.gamma = 0; // 1/num_features
param.coef0 = 0;
param.nu = 0.5;
param.cache_size = 100;
param.C = 1;
param.eps = 1e-3;
param.p = 0.1;
param.shrinking = 1;
param.probability = 0;
param.nr_weight = 0;
param.weight_label = NULL;
param.weight = NULL;
cross_validation = 0;
// parse options
for(i=1;i<argc;i++)
{
if(argv[i][0] != '-') break;
if(++i>=argc)
exit_with_help();
switch(argv[i-1][1])
{
case 's':
param.svm_type = atoi(argv[i]);
break;
case 't':
param.kernel_type = atoi(argv[i]);
break;
case 'd':
param.degree = atoi(argv[i]);
break;
case 'g':
param.gamma = atof(argv[i]);
break;
case 'r':
param.coef0 = atof(argv[i]);
break;
case 'n':
param.nu = atof(argv[i]);
break;
case 'm':
param.cache_size = atof(argv[i]);
break;
case 'c':
param.C = atof(argv[i]);
break;
case 'e':
param.eps = atof(argv[i]);
break;
case 'p':
param.p = atof(argv[i]);
break;
case 'h':
param.shrinking = atoi(argv[i]);
break;
case 'b':
param.probability = atoi(argv[i]);
break;
case 'q':
print_func = &print_null;
i--;
break;
case 'v':
cross_validation = 1;
nr_fold = atoi(argv[i]);
if(nr_fold < 2)
{
fprintf(stderr,"n-fold cross validation: n must >= 2\n");
exit_with_help();
}
break;
case 'w':
++param.nr_weight;
param.weight_label = (int *)realloc(param.weight_label,sizeof(int)*param.nr_weight);
param.weight = (double *)realloc(param.weight,sizeof(double)*param.nr_weight);
param.weight_label[param.nr_weight-1] = atoi(&argv[i-1][2]);
param.weight[param.nr_weight-1] = atof(argv[i]);
break;
default:
fprintf(stderr,"Unknown option: -%c\n", argv[i-1][1]);
exit_with_help();
}
}
svm_set_print_string_function(print_func);
// determine filenames
if(i>=argc)
exit_with_help();
strcpy(input_file_name, argv[i]);
if(i<argc-1)
strcpy(model_file_name,argv[i+1]);
else
{
char *p = strrchr(argv[i],'/');
if(p==NULL)
p = argv[i];
else
++p;
sprintf(model_file_name,"%s.model",p);
}
}
// read in a problem (in svmlight format)
void read_problem(const char *filename)
{
int max_index, inst_max_index, i;
size_t elements, j;
FILE *fp = fopen(filename,"r");
char *endptr;
char *idx, *val, *label;
if(fp == NULL)
{
fprintf(stderr,"can't open input file %s\n",filename);
exit(1);
}
prob.l = 0;
elements = 0;
max_line_len = 1024;
line = Malloc(char,max_line_len);
while(readline(fp)!=NULL)
{
char *p = strtok(line," \t"); // label
// features
while(1)
{
p = strtok(NULL," \t");
if(p == NULL || *p == '\n') // check '\n' as ' ' may be after the last feature
break;
++elements;
}
++elements;
++prob.l;
}
rewind(fp);
prob.y = Malloc(double,prob.l);
prob.x = Malloc(struct svm_node *,prob.l);
x_space = Malloc(struct svm_node,elements);
max_index = 0;
j=0;
for(i=0;i<prob.l;i++)
{
inst_max_index = -1; // strtol gives 0 if wrong format, and precomputed kernel has <index> start from 0
readline(fp);
prob.x[i] = &x_space[j];
label = strtok(line," \t\n");
if(label == NULL) // empty line
exit_input_error(i+1);
prob.y[i] = strtod(label,&endptr);
if(endptr == label || *endptr != '\0')
exit_input_error(i+1);
while(1)
{
idx = strtok(NULL,":");
val = strtok(NULL," \t");
if(val == NULL)
break;
errno = 0;
x_space[j].index = (int) strtol(idx,&endptr,10);
if(endptr == idx || errno != 0 || *endptr != '\0' || x_space[j].index <= inst_max_index)
exit_input_error(i+1);
else
inst_max_index = x_space[j].index;
errno = 0;
x_space[j].value = strtod(val,&endptr);
if(endptr == val || errno != 0 || (*endptr != '\0' && !isspace(*endptr)))
exit_input_error(i+1);
++j;
}
if(inst_max_index > max_index)
max_index = inst_max_index;
x_space[j++].index = -1;
}
if(param.gamma == 0 && max_index > 0)
param.gamma = 1.0/max_index;
if(param.kernel_type == PRECOMPUTED)
for(i=0;i<prob.l;i++)
{
if (prob.x[i][0].index != 0)
{
fprintf(stderr,"Wrong input format: first column must be 0:sample_serial_number\n");
exit(1);
}
if ((int)prob.x[i][0].value <= 0 || (int)prob.x[i][0].value > max_index)
{
fprintf(stderr,"Wrong input format: sample_serial_number out of range\n");
exit(1);
}
}
fclose(fp);
}
UPDATE
can i convert to numerical representation using this code?
#include <opencv2/core/core.hpp>
#include <opencv2/imgproc/imgproc.hpp>
#include <opencv2/highgui/highgui.hpp>
#include <cv.h>
#include <highgui.h>
#include <cvaux.h>
#include <iostream>
#include <vector>
#include<string.h>
using namespace std;
using namespace cv;
int main ( int argc, char** argv )
{
cout << "OpenCV Training SVM Automatic Number Plate Recognition\n";
cout << "\n";
char* path_Plates;
char* path_NoPlates;
int numPlates;
int numNoPlates;
int imageWidth=150;
int imageHeight=150;
//Check if user specify image to process
if(1)
{
numPlates= 12;
numNoPlates= 67 ;
path_Plates= "/home/kaushik/opencv_work/Manas6/Pics/Positive_Images/";
path_NoPlates= "/home/kaushik/opencv_work/Manas6/Pics/Negative_Images/i";
}else{
cout << "Usage:\n" << argv[0] << " <num Plate Files> <num Non Plate Files> <path to plate folder files> <path to non plate files> \n";
return 0;
}
Mat classes;//(numPlates+numNoPlates, 1, CV_32FC1);
Mat trainingData;//(numPlates+numNoPlates, imageWidth*imageHeight, CV_32FC1 );
Mat trainingImages;
vector<int> trainingLabels;
for(int i=1; i<= numPlates; i++)
{
stringstream ss(stringstream::in | stringstream::out);
ss<<path_Plates<<i<<".jpg";
try{
const char* a = ss.str().c_str();
printf("\n%s\n",a);
Mat img = imread(ss.str(), CV_LOAD_IMAGE_UNCHANGED);
img= img.clone().reshape(1, 1);
//imshow("Window",img);
//cout<<ss.str();
trainingImages.push_back(img);
trainingLabels.push_back(1);
}
catch(Exception e){;}
}
for(int i=0; i< numNoPlates; i++)
{
stringstream ss(stringstream::in | stringstream::out);
ss << path_NoPlates<<i << ".jpg";
try
{
const char* a = ss.str().c_str();
printf("\n%s\n",a);
Mat img=imread(ss.str(),CV_LOAD_IMAGE_UNCHANGED);
//imshow("Win",img);
img= img.clone().reshape(1, 1);
trainingImages.push_back(img);
trainingLabels.push_back(0);
//cout<<ss.str();
}
catch(Exception e){;}
}
Mat(trainingImages).copyTo(trainingData);
//trainingData = trainingData.reshape(1,trainingData.rows);
trainingData.convertTo(trainingData, CV_32FC1);
Mat(trainingLabels).copyTo(classes);
FileStorage fs("SVM.xml", FileStorage::WRITE);
fs << "TrainingData" << trainingData;
fs << "classes" << classes;
fs.release();
return 0;
}

Answer 1

What I can see from your code is, that you are mixing OpenCV and LIBSVM.
Basically you can follow one of the following ways. Personally I would suggest to use OpenCV only.
OpenCV
OpenCV is a very powerfull library for working with images. Hence they implement their own machine learning algorithms including SVMs.
As described in a very good way here it is very easy to perform classification with images via OpenCV since the algorithms use a common interface for this purpose.
LIBSVM
LIBSVM a standalone library for SVM classification in various form (e.g. multiclass, two-class, with probability estimates, etc). If you go this way, you have to perform the following steps in order to do successful classification:
Think about how many different classes you want to differentiate (e.g. + / -)
Maybe preprocess your images (filters, ...)
Extract so called "features" rom your images using a feature selection method (for example: Mutual Information). Those methods will tell you, which points are significant for your given classes since we follow the basic assumption, that not every singel pixel in an image is important.
According to your extracted features you transform your images to an vectorial representation.
Write it into an file according to the LIBSVM data format:
label feature_id1:feature_value1 feature_id2:feature_value2
+1 1:0.53265 2:0.5232
-1 1:0.78543 2:0.64326
Proceed with "svm_train" according to its description. Classification would be a combination of 2.) 4.) 5.) and a run of "svm_predict".