Visual Servoing Platform version 3.6.0
Loading...
Searching...
No Matches
Tutorial: Automatic thresholding

Introduction

This tutorial will show you how to automatically threshold, binarize an image using different methods:

  • Huang [Huang_imagethresholding]
  • Intermodes [NYAS:NYAS1035]
  • Isodata [article4310039]
  • Mean [Glasbey:1993:AHT:167725.167747]
  • Otsu [article4310076]
  • Triangle [doi:10.1177/25.7.70454]

These functions have been ported from the Auto Threshold ImageJ plugin and you can refer to the corresponding documentation for more information.

Example code

The following example also available in tutorial-autothreshold.cpp will demonstrate on a sample image the result of each of these methods:

#include <cstdlib>
#include <iostream>
#include <visp3/core/vpImage.h>
#include <visp3/gui/vpDisplayGDI.h>
#include <visp3/gui/vpDisplayOpenCV.h>
#include <visp3/gui/vpDisplayX.h>
#include <visp3/io/vpImageIo.h>
#if defined(VISP_HAVE_MODULE_IMGPROC)
#include <visp3/imgproc/vpImgproc.h>
#endif
int main(int argc, const char **argv)
{
#if defined(VISP_HAVE_MODULE_IMGPROC) && (defined(VISP_HAVE_X11) || defined(VISP_HAVE_GDI) || defined(VISP_HAVE_OPENCV))
std::string input_filename = "grid36-03.pgm";
for (int i = 1; i < argc; i++) {
if (std::string(argv[i]) == "--input" && i + 1 < argc) {
input_filename = std::string(argv[i + 1]);
} else if (std::string(argv[i]) == "--help" || std::string(argv[i]) == "-h") {
std::cout << "Usage: " << argv[0] << " [--input <input image>] [--help]" << std::endl;
return EXIT_SUCCESS;
}
}
vpImageIo::read(I, input_filename);
vpImage<unsigned char> I_res(3 * I.getHeight(), 3 * I.getWidth());
I_res.insert(I, vpImagePoint(I.getHeight(), I.getWidth()));
#ifdef VISP_HAVE_X11
#elif defined(VISP_HAVE_GDI)
#elif defined(HAVE_OPENCV_HIGHGUI)
#endif
d.init(I_res);
I_res.insert(I_huang, vpImagePoint());
vpImage<unsigned char> I_intermodes = I;
I_res.insert(I_intermodes, vpImagePoint(0, I.getWidth()));
vpImage<unsigned char> I_isodata = I;
I_res.insert(I_isodata, vpImagePoint(0, 2 * I.getWidth()));
I_res.insert(I_mean, vpImagePoint(I.getHeight(), 0));
I_res.insert(I_otsu, vpImagePoint(I.getHeight(), 2 * I.getWidth()));
vpImage<unsigned char> I_triangle = I;
I_res.insert(I_triangle, vpImagePoint(2 * I.getHeight(), 0));
vpDisplay::displayText(I_res, 30, 20, "Huang", vpColor::red);
vpDisplay::displayText(I_res, 30, 20 + I.getWidth(), "Intermodes", vpColor::red);
vpDisplay::displayText(I_res, 30, 20 + 2 * I.getWidth(), "IsoData", vpColor::red);
vpDisplay::displayText(I_res, 30 + I.getHeight(), 20, "Mean", vpColor::red);
vpDisplay::displayText(I_res, 30 + I.getHeight(), 20 + I.getWidth(), "Original", vpColor::red);
vpDisplay::displayText(I_res, 30 + I.getHeight(), 20 + 2 * I.getWidth(), "Otsu", vpColor::red);
vpDisplay::displayText(I_res, 30 + 2 * I.getHeight(), 20, "Triangle", vpColor::red);
#else
(void)argc;
(void)argv;
#endif
return EXIT_SUCCESS;
}
static const vpColor red
Definition vpColor.h:211
Display for windows using GDI (available on any windows 32 platform).
The vpDisplayOpenCV allows to display image using the OpenCV library. Thus to enable this class OpenC...
Use the X11 console to display images on unix-like OS. Thus to enable this class X11 should be instal...
Definition vpDisplayX.h:132
void init(vpImage< unsigned char > &I, int win_x=-1, int win_y=-1, const std::string &win_title="")
static bool getClick(const vpImage< unsigned char > &I, bool blocking=true)
virtual void setDownScalingFactor(unsigned int scale)
static void display(const vpImage< unsigned char > &I)
static void flush(const vpImage< unsigned char > &I)
static void displayText(const vpImage< unsigned char > &I, const vpImagePoint &ip, const std::string &s, const vpColor &color)
static void read(vpImage< unsigned char > &I, const std::string &filename, int backend=IO_DEFAULT_BACKEND)
Class that defines a 2D point in an image. This class is useful for image processing and stores only ...
Definition of the vpImage class member functions.
Definition vpImage.h:135
unsigned int getWidth() const
Definition vpImage.h:242
unsigned int getHeight() const
Definition vpImage.h:184
VISP_EXPORT unsigned char autoThreshold(vpImage< unsigned char > &I, const vp::vpAutoThresholdMethod &method, const unsigned char backgroundValue=0, const unsigned char foregroundValue=255)
@ AUTO_THRESHOLD_ISODATA
Definition vpImgproc.h:75
@ AUTO_THRESHOLD_HUANG
Definition vpImgproc.h:67
@ AUTO_THRESHOLD_INTERMODES
Definition vpImgproc.h:71
@ AUTO_THRESHOLD_TRIANGLE
Definition vpImgproc.h:87
@ AUTO_THRESHOLD_MEAN
Definition vpImgproc.h:79
@ AUTO_THRESHOLD_OTSU
Definition vpImgproc.h:83

These functions are provided in a vp:: namespace and accessible using this include:

#include <visp3/imgproc/vpImgproc.h>

The code to use is pretty straightword:

The following image presents the results for each method:

Comparison of different binarizations using the threshold value returned by each method

The function vp::autoThreshold(vpImage<unsigned char> &, const vp::vpAutoThresholdMethod &, const unsigned char, const unsigned char) has two parameters to specify the pixel values to use for the background and the foreground. By default, it is (see vpImageTools::binarise(vpImage<Type> &, Type, Type, Type, Type, Type, const bool)):

\[
  I_{bin}\left ( i,j \right ) = 
  \left \{ \begin{matrix}
  0 \text{ if } I_{src}\left ( i,j \right ) < \text{threshold} \\ 
  255 \text{ otherwise}
  \end{matrix} \right.
\]

Next tutorial

You can now read the Tutorial: Contours extraction from a binary image, to learn how to extract the contours from a binary image.