Something More for Research

Explorer of Research #HEMBAD

Posts Tagged ‘Median filter’

Hybrid median filter

Posted by Hemprasad Y. Badgujar on October 12, 2014


Hybrid median filter

Category. Digital image processing (DIP) software development.

Abstract. The article is a practical tutorial for hybrid median filter understanding and implementation. Article contains theory, C++ source code, programming instructions and sample applications.

Download hybrid median filter for Win32 (zip, 1.03 Mb)

Download hybrid median filter C++ source code (zip, 2 Kb)

Corrupted and restored images

1. Introduction to hybrid median filter

Hybrid median filter is windowed filter of nonlinear class, that easily removes impulse noise while preserving edges. In comparison with basic version of the median filter hybrid one has better corner preserving characteristics. The basic idea behind filter is for any element of the signal (image) apply median technique several times varying window shape and then take the median of the got median values.

To get acquainted with filter window idea in signal and image processing read our “Filter window, or filter mask” article.

2. Understanding hybrid median filter

Now let us see, how hybrid version of the median filter works. In one phrase idea is like “apply median filter with cross-mask, apply median filter with x-mask and take the median of got results and element itself”. Hybrid median filter workflow depicted below in fig. 1.

Fig. 1. Hybrid median filter workflow.Fig. 1. Hybrid median filter workflow.

Due to the nature of the workflow the filter dimension is not less than 2D.

Now let us write down step-by-step instructions for processing by hybrid median filter.

Hybrid median filter algorithm:

  1. Place a cross-window over element;
  2. Pick up elements;
  3. Order elements;
  4. Take the middle element;
  5. Place a x-window over element;
  6. Pick up elements;
  7. Order elements;
  8. Take the middle element;
  9. Pick up result in point 4, 8 and element itself;
  10. Order elements;
  11. Take the middle element.

Now, when we have the algorithm, it is time to write some code — let us come down to programming.

3. Hybrid median filter programming

We can see that operation of taking median — “order elements” and “take the middle element” — repeated three times in the list. So it is good idea to put those steps into separate function:

//   MEDIAN calculation
//     elements - input elements
//     N        - number of input elements
element median(element* elements, int N)
{
   //   Order elements (only half of them)
   for (int i = 0; i < (N >> 1) + 1; ++i)
   {
      //   Find position of minimum element
      int min = i;
      for (int j = i + 1; j < N; ++j)
         if (elements[j] < elements[min])
            min = j;
      //   Put found minimum element in its place
      const element temp = elements[i];
      elements[i] = elements[min];
      elements[min] = temp;
   }
   //   Get result - the middle element
   return elements[N >> 1];
}

In the function above we are using a code optimization trick. Since everything we need is middle element, it is enough to order just a half of elements.

Let us have 2D signal or image of length N×M as input and let we choose filter window of 3×3 size. The first step is window placing — we do that by changing index of the leading element:

//   Move window through all elements of the image
for (int m = 1; m < M - 1; ++m)
   for (int n = 1; n < N - 1; ++n)

Pay attention, that we are not processing first and last rows and columns. The problem is we cannot process elements at edges, because in this case the part of the filter window is empty. We will discuss below, how to solve that problem.

The second step is picking up elements around with cross-window, ok:

//   Pick up cross-window elements
window[0] = image[(m - 1) * N + n];
window[1] = image[m * N + n - 1];
window[2] = image[m * N + n];
window[3] = image[m * N + n + 1];
window[4] = image[(m + 1) * N + n];

The third and fourth steps are done by our auxiliary function:

//   Get median
results[0] = median(window, 5);

Fifth and sixth steps are picking up elements with x-window:

//   Pick up x-window elements
window[0] = image[(m - 1) * N + n - 1];
window[1] = image[(m - 1) * N + n + 1];
window[2] = image[m * N + n];
window[3] = image[(m + 1) * N + n - 1];
window[4] = image[(m + 1) * N + n + 1];

Seventh and eighth steps are made again by our auxiliary function:

//   Get median
results[1] = median(window, 5);

To complete ninth step enough to pick up our leading element itself:

//   Pick up leading element
results[2] = image[m * N + n];

Final steps are performed by our useful function:

//   Get result
result[(m - 1) * (N - 2) + n - 1] = median(results, 3);

At last, let us write down the entire algorithm as function:

//   2D HYBRID MEDIAN FILTER implementation
//     image  - input image
//     result - output image
//     N      - width of the image
//     M      - height of the image
void _hybridmedianfilter(const element* image, element* result, int N, int M)
{
   //   Move window through all elements of the image
   for (int m = 1; m < M - 1; ++m)
      for (int n = 1; n < N - 1; ++n)
      {
         element window[5];
         element results[3];
         //   Pick up cross-window elements
         window[0] = image[(m - 1) * N + n];
         window[1] = image[m * N + n - 1];
         window[2] = image[m * N + n];
         window[3] = image[m * N + n + 1];
         window[4] = image[(m + 1) * N + n];
         //   Get median
         results[0] = median(window, 5);
         //   Pick up x-window elements
         window[0] = image[(m - 1) * N + n - 1];
         window[1] = image[(m - 1) * N + n + 1];
         window[2] = image[m * N + n];
         window[3] = image[(m + 1) * N + n - 1];
         window[4] = image[(m + 1) * N + n + 1];
         //   Get median
         results[1] = median(window, 5);
         //   Pick up leading element
         results[2] = image[m * N + n];
         //   Get result
         result[(m - 1) * (N - 2) + n - 1] = median(results, 3);
      }
}

Looks very straightforward.

Type element could be defined as:

typedef double element;

4. Treating edges

For all window filters there is some problem. That is edge treating. If you place window over an element at the edge, some part of the window will be empty. To fill the gap, signal should be extended. For hybrid median filter there is good idea to extend image symmetrically, like this:

Fig. 2. Image extension.Fig. 2. Image extension.

In other words we are adding lines at the top and at the bottom of the image and add columns to the left and to the right of it.

So, before passing signal to our median filter function the signal should be extended. Let us write down the wrapper, that makes all preparations.

//   2D HYBRID MEDIAN FILTER wrapper
//     image  - input image
//     result - output image
//     N      - width of the image
//     M      - height of the image
void hybridmedianfilter(element* image, element* result, int N, int M)
{
   //   Check arguments
   if (!image || N < 1 || M < 1)
      return;
   //   Allocate memory for signal extension
   element* extension = new element[(N + 2) * (M + 2)];
   //   Check memory allocation
   if (!extension)
      return;
   //   Create image extension
   for (int i = 0; i < M; ++i)
   {
      memcpy(extension + (N + 2) * (i + 1) + 1,
         image + N * i,
         N * sizeof(element));
      extension[(N + 2) * (i + 1)] = image[N * i];
      extension[(N + 2) * (i + 2) - 1] = image[N * (i + 1) - 1];
   }
   //   Fill first line of image extension
   memcpy(extension,
      extension + N + 2,
      (N + 2) * sizeof(element));
   //   Fill last line of image extension
   memcpy(extension + (N + 2) * (M + 1),
      extension + (N + 2) * M,
      (N + 2) * sizeof(element));
   //   Call hybrid median filter implementation
   _hybridmedianfilter(extension, result ? result : image, N + 2, M + 2);
   //   Free memory
   delete[] extension;
}

As you can see, our code takes into account some practical issues. First of all we check our input parameters — image should not be NULL, and image sizes should be positive:

//   Check arguments
if (!image || N < 1 || M < 1)
   return;

Now let us allocate memory for signal extension.

//   Allocate memory for signal extension
element* extension = new element[(N + 2) * (M + 2)];

And check memory allocation.

//   Check memory allocation
if (!extension)
   return;

Now we are building extension.

//   Create signal extension
for (int i = 0; i < M; ++i)
{
   memcpy(extension + (N + 2) * (i + 1) + 1,
      image + N * i,
      N * sizeof(element));
   extension[(N + 2) * (i + 1)] = image[N * i];
   extension[(N + 2) * (i + 2) - 1] = image[N * (i + 1) - 1];
}
//   Fill first line of image extension
memcpy(extension,
   extension + N + 2,
   (N + 2) * sizeof(element));
//   Fill last line of image extension
memcpy(extension + (N + 2) * (M + 1),
   extension + (N + 2) * M,
   (N + 2) * sizeof(element));

Finally, everything is ready — filtering!

//   Call hybrid median filter implementation
_hybridmedianfilter(extension, result ? result : image, N + 2, M + 2);

And to complete the job — free memory.

//   Free memory
delete[] extension;

Since we are using memory management function from standard library, we should include its header.

#include <memory.h>

5. Hybrid median filter declaration file

Now we have three functions: helper function, hybrid median filter and entry point that makes preparations. Let us write code for header file.

#ifndef _HYBRIDMEDIANFILTER_H_
#define _HYBRIDMEDIANFILTER_H_

//   Image element type
typedef double element;

//   2D HYBRID MEDIAN FILTER, window size 3x3
//     image  - input image
//     result - output image, NULL for inplace processing
//     N      - width of the image
//     M      - height of the image
void hybridmedianfilter(element* image, element* result, int N, int M);

#endif

Now all is ready. The code we have written is good both for Linux/Unix and Windows platforms. You can download full hybrid median filter source code here:

Download hybrid median filter C++ source code (zip, 2 Kb)

Full file listings are available online as well:

And now — a couple of applications to play around!

6. Color median filter: image restoration

Download hybrid median filter for Win32 (zip, 1.03 Mb)

We have created a couple of applications to show hybrid median filter capabilities in restoration images corrupted by impulse noise. The sample package includes 4 files — two applications, sample image and description:

  • hybridmedian.exe — median filter,
  • corrupter.exe — destructive noise generator,
  • sample.bmp — 24-bit sample image,
  • readme.txt — description.

Be aware of the fact, that this sample uses OpenGL, so it should be supported by your system (usually that is the case).

7. Step 1: prepare corrupted image

We have created impulse noise generator that will help us to prepare corrupted image. Start up corrupter.exe application and load image to be corrupted. Choose Set >> Corruption… or click N button in toolbar and set noise level at 5–15%. Click OK. Then save corrupted image.

Fig. 3. Corruption by impulse noise. Screenshot.Fig. 3. Corruption by impulse noise.

8. Step 2: restore corrupted image

Start up hybridmedian.exe application. Load the saved corrupted image. Apply hybrid median filter by choosing Set >> Filter or clickingF-button in toolbar. See the result. If necessary, filter the image one more time.

Fig. 4. Image restored by hybrid median filter. Screenshot.Fig. 4. Image restored by hybrid median filter.

 

Posted in Image / Video Filters | Tagged: | Leave a Comment »

Median filter Category. Digital signal and image

Posted by Hemprasad Y. Badgujar on October 12, 2014


Median filter

Category. Digital signal and image processing (DSP and DIP) software development.

Abstract. The article is a practical guide for median filter understanding and implementation. Article contains theory, C++ source code, programming instructions and sample applications.

Reference. Case study: 3D median filter — ultrasound image despeckling.

Download median filter for Win32 (zip, 603 Kb)

Download median filter C++ source code (zip, 2 Kb)

Corrupted and restored images

1. Introduction to median filter

Median filter is windowed filter of nonlinear class, which easily removes destructive noise while preserving edges. The basic idea behind filter is for any element of the signal (image) look at its neighborhood and pick up the element most similar to others. Median filter in its properties resembles mean filter, or average filter, but much better in treating “salt and pepper” noise and edge preserving. On the other hand median filter is often used for speckle noise reduction but there are more effective techniques like diffusion filter though more complicated. To understand how to implement median filter in practice, let us start with window idea.

2. Filter window or mask

Let us imagine, you should read a letter and what you see in text restricted by hole in special stencil like this.

First stencilFig. 1. First stencil.

So, the result of reading is sound [t]. Ok, let us read the letter again, but with the help of another stencil:

Second stencilFig. 2. Second stencil.

Now the result of reading t is sound [ð]. Let us make the third try:

Third stencilFig. 3. Third stencil.

Now you are reading letter t as sound [θ].

What happens here? To say that in mathematical language, you are making an operation (reading) over element (letter t). And the result (sound) depends on the element neighborhood (letters next to t).

And that stencil, which helps to pick up element neighborhood, is window! Yes, window is just a stencil or pattern, by means of which you are selecting the element neighborhood — a set of elements around the given one — to help you make decision. Another name for filter window is mask — mask is a stencil, which hides elements we are not paying attention to.

In our example the element we are operating on positioned at leftmost of the window, in practice however its usual position is the center of the window.

Let us see some window examples. In one dimension.

Window or mask of size 5 in 1DFig. 4. Window or mask of size 5 in 1D.

In two dimensions.

Window or mask of size 3x3 in 2DFig. 5. Window or mask of size 3×3 in 2D.

In three dimensions… Think about building. And now — about room in that building. The room is like 3D window, which cuts out some subspace from the entire space of the building. You can find 3D window in volume (voxel) image processing.

Window of mask of size 3x3x3 in 3DFig. 6. Window or mask of size 3×3×3 in 3D.

3. Understanding median filter

Now let us see, how to “pick up element most similar to others”. The basic idea is simple — order elements and take the middle one. For instance, let us find the median for the case, depicted in fig. 7.

Taking the medianFig. 7. Taking the median.

And that is all. Yes, we just have filtered 1D signal by median filter! Let us make resume and write down step-by-step instructions for processing by median filter.

Median filter algorithm:

  1. Place a window over element;
  2. Pick up elements;
  3. Order elements;
  4. Take the middle element.

Now, when we have the algorithm, it is time to write some code — let us come down to programming.

4. 1D median filter programming

In this section we develop 1D median filter with window of size 5. Let us have 1D signal of length N as input. The first step is window placing — we do that by changing index of the leading element:

//   Move window through all elements of the signal
for (int i = 2; i < N - 2; ++i)

Pay attention, that we are starting with the third element and finishing with the last but two. The problem is we cannot start with the first element, because in this case the left part of the filter window is empty. We will discuss below, how to solve that problem.

The second step is picking up elements around, ok:

//   Pick up window elements
for (int j = 0; j < 5; ++j)
   window[j] = signal[i - 2 + j];

The third step is putting window elements in order. But we will use a code optimization trick here. Everything we need is middle element. So, it is enough to order just a half of elements. Great:

//   Order elements (only half of them)
for (int j = 0; j < 3; ++j)
{
   //   Find position of minimum element
   int min = j;
   for (int k = j + 1; k < 5; ++k)
      if (window[k] < window[min])
         min = k;
   //   Put found minimum element in its place
   const element temp = window[j];
   window[j] = window[min];
   window[min] = temp;
}

The final step — take the middle:

//   Get result - the middle element
result[i - 2] = window[2];

At last, let us write down the entire algorithm as function:

//   1D MEDIAN FILTER implementation
//     signal - input signal
//     result - output signal
//     N      - length of the signal
void _medianfilter(const element* signal, element* result, int N)
{
   //   Move window through all elements of the signal
   for (int i = 2; i < N - 2; ++i)
   {
      //   Pick up window elements
      element window[5];
      for (int j = 0; j < 5; ++j)
         window[j] = signal[i - 2 + j];
      //   Order elements (only half of them)
      for (int j = 0; j < 3; ++j)
      {
         //   Find position of minimum element
         int min = j;
         for (int k = j + 1; k < 5; ++k)
            if (window[k] < window[min])
               min = k;
         //   Put found minimum element in its place
         const element temp = window[j];
         window[j] = window[min];
         window[min] = temp;
      }
      //   Get result - the middle element
      result[i - 2] = window[2];
   }
}

Type element could be defined as:

typedef double element;

5. Treating edges

For all window filters there is some problem. That is edge treating. If you place window over first (last) element, the left (right) part of the window will be empty. To fill the gap, signal should be extended. For median filter there is good idea to extend signal or image symmetrically, like this:

Signal extensionFig. 8. Signal extension.

So, before passing signal to our median filter function the signal should be extended. Let us write down the wrapper, which makes all preparations.

//   1D MEDIAN FILTER wrapper
//     signal - input signal
//     result - output signal
//     N      - length of the signal
void medianfilter(element* signal, element* result, int N)
{
   //   Check arguments
   if (!signal || N < 1)
      return;
   //   Treat special case N = 1
   if (N == 1)
   {
      if (result)
         result[0] = signal[0];
      return;
   }
   //   Allocate memory for signal extension
   element* extension = new element[N + 4];
   //   Check memory allocation
   if (!extension)
      return;
   //   Create signal extension
   memcpy(extension + 2, signal, N * sizeof(element));
   for (int i = 0; i < 2; ++i)
   {
      extension[i] = signal[1 - i];
      extension[N + 2 + i] = signal[N - 1 - i];
   }
   //   Call median filter implementation
   _medianfilter(extension, result ? result : signal, N + 4);
   //   Free memory
   delete[] extension;
}

As you can see, our code takes into account some practical issues. First of all we check our input parameters — signal should not be NULL, and signal length should be positive:

//   Check arguments
if (!signal || N < 1)
   return;

Second step — we check case N=1. This case is special one, because to build extension we need at least two elements. For the signal of 1 element length the result is the signal itself. As well pay attention, our median filter works in-place, if output parameter result is NULL.

//   Treat special case N = 1
if (N == 1)
{
   if (result)
      result[0] = signal[0];
   return;
}

Now let us allocate memory for signal extension.

//   Allocate memory for signal extension
element* extension = new element[N + 4];

And check memory allocation.

//   Check memory allocation
if (!extension)
   return;

Now we are building extension.

//   Create signal extension
memcpy(extension + 2, signal, N * sizeof(element));
for (int i = 0; i < 2; ++i)
{
   extension[i] = signal[1 - i];
   extension[N + 2 + i] = signal[N - 1 - i];
}

Finally, everything is ready — filtering!

//   Call median filter implementation
_medianfilter(extension, result ? result : signal, N + 4);

And to complete the job — free memory.

//   Free memory
delete[] extension;

Since we are using memory management function from standard library, we should include its header.

#include <memory.h>

6. 2D median filter programming

In 2D case we have 2D signal, or image. The idea is the same, just now median filter has 2D window. Window influences only the elements selection. All the rest is the same: ordering elements and picking up the middle one. So, let us have a look at 2D median filter programming. For 2D case we choose window of 3×3 size.

//   2D MEDIAN FILTER implementation
//     image  - input image
//     result - output image
//     N      - width of the image
//     M      - height of the image
void _medianfilter(const element* image, element* result, int N, int M)
{
   //   Move window through all elements of the image
   for (int m = 1; m < M - 1; ++m)
      for (int n = 1; n < N - 1; ++n)
      {
         //   Pick up window elements
         int k = 0;
         element window[9];
         for (int j = m - 1; j < m + 2; ++j)
            for (int i = n - 1; i < n + 2; ++i)
               window[k++] = image[j * N + i];
         //   Order elements (only half of them)
         for (int j = 0; j < 5; ++j)
         {
            //   Find position of minimum element
            int min = j;
            for (int l = j + 1; l < 9; ++l)
            if (window[l] < window[min])
               min = l;
            //   Put found minimum element in its place
            const element temp = window[j];
            window[j] = window[min];
            window[min] = temp;
         }
         //   Get result - the middle element
         result[(m - 1) * (N - 2) + n - 1] = window[4];
      }
}

7. Treating edges in 2D case

As in 1D case in 2D case we should extend our input image as well. To do that we are to add lines at the top and at the bottom of the image and add columns to the left and to the right.

Image extensionFig. 9. Image extension.

Here is our wrapper function, which does that job.

//   2D MEDIAN FILTER wrapper
//     image  - input image
//     result - output image
//     N      - width of the image
//     M      - height of the image
void medianfilter(element* image, element* result, int N, int M)
{
   //   Check arguments
   if (!image || N < 1 || M < 1)
      return;
   //   Allocate memory for signal extension
   element* extension = new element[(N + 2) * (M + 2)];
   //   Check memory allocation
   if (!extension)
      return;
   //   Create image extension
   for (int i = 0; i < M; ++i)
   {
      memcpy(extension + (N + 2) * (i + 1) + 1,
         image + N * i,
         N * sizeof(element));
      extension[(N + 2) * (i + 1)] = image[N * i];
      extension[(N + 2) * (i + 2) - 1] = image[N * (i + 1) - 1];
   }
   //   Fill first line of image extension
   memcpy(extension,
      extension + N + 2,
      (N + 2) * sizeof(element));
   //   Fill last line of image extension
   memcpy(extension + (N + 2) * (M + 1),
      extension + (N + 2) * M,
      (N + 2) * sizeof(element));
   //   Call median filter implementation
   _medianfilter(extension, result ? result : image, N + 2, M + 2);
   //   Free memory
   delete[] extension;
}

8. Median filter library

Now we have four functions, two of them are for processing 1D signals by median filter, and other two are for filtering 2D images. It is time to put everything together and create small median filter library. Let us write code for header file.

#ifndef _MEDIANFILTER_H_
#define _MEDIANFILTER_H_

//   Signal/image element type
typedef double element;

//   1D MEDIAN FILTER, window size 5
//     signal - input signal
//     result - output signal, NULL for inplace processing
//     N      - length of the signal
void medianfilter(element* signal, element* result, int N);

//   2D MEDIAN FILTER, window size 3x3
//     image  - input image
//     result - output image, NULL for inplace processing
//     N      - width of the image
//     M      - height of the image
void medianfilter(element* image, element* result, int N, int M);

#endif

Our library is ready. The code we have written is good both for Linux/Unix and Windows platforms. You can download full median filter library source code here:

Download median filter C++ source code (zip, 2 Kb)

Full listings of library files are available online as well:

And now — a couple of applications to play around!

9. Color median filter: image restoration

Download median filter for Win32 (zip, 603 Kb)

We have created a couple of applications to show median filter capabilities in restoration images corrupted by destructive noise. The sample package includes 4 files — two applications, sample image and description:

  • restorer.exe — median filter,
  • corrupter.exe — destructive noise generator,
  • sample.bmp — 24-bit sample image,
  • readme.txt — description.

Be aware of the fact, that this sample uses OpenGL, so it should be installed on your computer.

10. Step 1: prepare corrupted image

To prepare corrupted image you have two choices. First choice is you can corrupt the image with destructive noise. Start up corrupter.exeapplication and load image to be corrupted. Choose Set >> Corruption… or click N button in toolbar and set noise level at 5–15%. Click OK. Then save corrupted image.

Corruption by destructive noise - screenshotFig. 10. Corruption by destructive noise.

Median filter can filter out not only destructive noise but scratches as well. This is the second choice. Open MS Paint: Start >> Programs >> Accessories >> Paint, load some .bmp file. Pick up pencil, choose white color and scratch the image. Save corrupted image.

Corruption by scratches - screenshotFig. 11. Corruption by scratches.

11. Step 2: restore corrupted image

Start up restorer.exe application. Load the saved corrupted image. Apply median filter by choosing Set >> Filter or clicking F-button in toolbar. See the result. If necessary, filter the image once more.

Image restored by median filter - screenshotFig. 12. Image restored by median filter.

 

Posted in Image / Video Filters | Tagged: | Leave a Comment »

Computer Vision Algorithm Implementations

Posted by Hemprasad Y. Badgujar on May 6, 2014


Participate in Reproducible Research

General Image Processing

OpenCV
(C/C++ code, BSD lic) Image manipulation, matrix manipulation, transforms
Torch3Vision
(C/C++ code, BSD lic) Basic image processing, matrix manipulation and feature extraction algorithms: rotation, flip, photometric normalisations (Histogram Equalization, Multiscale Retinex, Self-Quotient Image or Gross-Brajovic), edge detection, 2D DCT, 2D FFT, 2D Gabor, PCA to do Eigen-Faces, LDA to do Fisher-Faces. Various metrics (Euclidean, Mahanalobis, ChiSquare, NormalizeCorrelation, TangentDistance, …)
ImLab
(C/C++ code, MIT lic) A Free Experimental System for Image Processing (loading, transforms, filters, histogram, morphology, …)
CIMG
(C/C++ code, GPL and LGPL lic) CImg Library is an open source C++ toolkit for image processing
Generic Image Library (GIL)boost integration
(C/C++ code, MIT lic) Adobe open source C++ Generic Image Library (GIL)
SimpleCV a kinder, gentler machine vision library
(python code, MIT lic) SimpleCV is a Python interface to several powerful open source computer vision libraries in a single convenient package
PCL, The Point Cloud Library
(C/C++ code, BSD lic) The Point Cloud Library (or PCL) is a large scale, open project for point cloud processing. The PCL framework contains numerous state-of-the art algorithms including filtering, feature estimation, surface reconstruction, registration, model fitting and segmentation.
Population, imaging library in C++ for processing, analysing, modelling and visualising
(C/C++ code, CeCill lic) Population is an open-source imaging library in C++ for processing, analysing, modelling and visualising including more than 200 algorithms designed by V. Tariel.
qcv
(C/C++ code, LGPL 3) A computer vision framework based on Qt and OpenCV that provides an easy to use interface to display, analyze and run computer vision algorithms. The library is provided with multiple application examples including stereo, SURF, Sobel and and Hough transform.
Machine Vision Toolbox
(MATLAB/C, LGPL lic) image processing, segmentation, blob/line/point features, multiview geometry, camera models, colorimetry.
BoofCV
(Java code, Apache lic) BoofCV is an open source Java library for real-time computer vision and robotics applications. BoofCV is organized into several packages: image processing, features, geometric vision, calibration, visualize, and IO.
Simd
(C++ code, MIT lic) Simd is free open source library in C++. It includes high performance image processing algorithms. The algorithms are optimized with using of SIMD CPU extensions such as SSE2, SSSE3, SSE4.2 and AVX2.
Free but not open source – ArrayFire (formely LibJacket) is a matrix library for CUDA
(CUDA/C++, free lic) ArrayFire offers hundreds of general matrix and image processing functions, all running on the GPU. The syntax is very Matlab-like, with the goal of offering easy porting of Matlab code to C++/ArrayFire.

Image Acquisition, Decoding & encoding

FFMPEG
(C/C++ code, LGPL or GPL lic) Record, convert and stream audio and video (lot of codec)
OpenCV
(C/C++ code, BSD lic) PNG, JPEG,… images, avi video files, USB webcam,…
Torch3Vision
(C/C++ code, BSD lic) Video file decoding/encoding (ffmpeg integration), image capture from a frame grabber or from USB, Sony pan/tilt/zoom camera control using VISCA interface
lib VLC
(C/C++ code, GPL lic) Used by VLC player: record, convert and stream audio and video
Live555
(C/C++ code, LGPL lic) RTSP streams
ImageMagick
(C/C++ code, GPL lic) Loading & saving DPX, EXR, GIF, JPEG, JPEG-2000, PDF, PhotoCD, PNG, Postscript, SVG, TIFF, and more
DevIL
(C/C++ code, LGPL lic) Loading & saving various image format
FreeImage
(C/C++ code, GPL & FPL lic) PNG, BMP, JPEG, TIFF loading
VideoMan
(C/C++ code, LGPL lic) VideoMan is trying to make the image capturing process from cameras, video files or image sequences easier.

Segmentation

OpenCV
(C/C++ code, BSD lic) Pyramid image segmentation
Branch-and-Mincut
(C/C++ code, Microsoft Research Lic) Branch-and-Mincut Algorithm for Image Segmentation
Efficiently solving multi-label MRFs (Readme)
(C/C++ code) Segmentation, object category labelling, stereo

Machine Learning

Torch
(C/C++ code, BSD lic) Gradient machines ( multi-layered perceptrons, radial basis functions, mixtures of experts, convolutional networks and even time-delay neural networks), Support vector machines, Ensemble models (bagging, adaboost), Non-parametric models (K-nearest-neighbors, Parzen regression and Parzen density estimator), distributions (Kmeans, Gaussian mixture models, hidden Markov models, input-output hidden Markov models, and Bayes classifier), speech recognition tools

Object Detection

OpenCV
(C/C++ code, BSD lic) Viola-jones face detection (Haar features)
Torch3Vision
(C/C++ code, BSD lic) MLP & cascade of Haar-like classifiers face detection
Hough Forests
(C/C++ code, Microsoft Research Lic) Class-Specific Hough Forests for Object Detection
Efficient Subwindow Object Detection
(C/C++ code, Apache Lic) Christoph Lampert “Efficient Subwindow” algorithms for Object Detection
INRIA Object Detection and Localization Toolkit
(C/C++ code, Custom Lic) Histograms of Oriented Gradients library for Object Detection

Object Category Labelling

Efficiently solving multi-label MRFs (Readme)
(C/C++ code) Segmentation, object category labelling, stereo
Multi-label optimization
(C/C++/MATLAB code) The gco-v3.0 library is for optimizing multi-label energies. It supports energies with any combination of unary, pairwise, and label cost terms.

Optical flow

OpenCV
(C/C++ code, BSD lic) Horn & Schunck algorithm, Lucas & Kanade algorithm, Lucas-Kanade optical flow in pyramids, block matching.
GPU-KLT+FLOW
(C/C++/OpenGL/Cg code, LGPL) Gain-Adaptive KLT Tracking and TV-L1 optical flow on the GPU.
RLOF
(C/C++/Matlab code, Custom Lic.) The RLOF library provides GPU / CPU implementation of Optical Flow and Feature Tracking method.

Features Extraction & Matching

SIFT by R. Hess
(C/C++ code, GPL lic) SIFT feature extraction & RANSAC matching
OpenSURF
(C/C++ code) SURF feature extraction algorihtm (kind of fast SIFT)
ASIFT (from IPOL)
(C/C++ code, Ecole Polytechnique and ENS Cachan for commercial Lic) Affine SIFT (ASIFT)
VLFeat (formely Sift++)
(C/C++ code) SIFT, MSER, k-means, hierarchical k-means, agglomerative information bottleneck, and quick shift
SiftGPU
A GPU Implementation of Scale Invariant Feature Transform (SIFT)
Groupsac
(C/C++ code, GPL lic) An enhance version of RANSAC that considers the correlation between data points

Nearest Neighbors matching

FLANN
(C/C++ code, BSD lic) Approximate Nearest Neighbors (Fast Approximate Nearest Neighbors with Automatic Algorithm Configuration)
ANN
(C/C++ code, LGPL lic) Approximate Nearest Neighbor Searching

Tracking

OpenCV
(C/C++ code, BSD lic) Kalman, Condensation, CAMSHIFT, Mean shift, Snakes
KLT: An Implementation of the Kanade-Lucas-Tomasi Feature Tracker
(C/C++ code, public domain) Kanade-Lucas-Tomasi Feature Tracker
GPU_KLT
(C/C++/OpenGL/Cg code, ) A GPU-based Implementation of the Kanade-Lucas-Tomasi Feature Tracker
GPU-KLT+FLOW
(C/C++/OpenGL/Cg code, LGPL) Gain-Adaptive KLT Tracking and TV-L1 optical flow on the GPU
On-line boosting trackers
(C/C++, LGPL) On-line boosting tracker, semi-supervised tracker, beyond semi-supervised tracker
Single Camera background subtraction tracking
(C/C++, LGPL) Background subtraction based tracking algorithm using OpenCV.
Multi-camera tracking
(C/C++, LGPL) Multi-camera particle filter tracking algorithm using OpenCv and intel IPP.

Simultaneous localization and mapping

Real-Time SLAM – SceneLib
(C/C++ code, LGPL lic) Real-time vision-based SLAM with a single camera
PTAM
(C/C++ code, Isis Innovation Limited lic) Parallel Tracking and Mapping for Small AR Workspaces
GTSAM
(C/C++ code, BSD lic) GTSAM is a library of C++ classes that implement smoothing and mapping (SAM) in robotics and vision, using factor graphs and Bayes networks as the underlying computing paradigm rather than sparse matrices

Camera Calibration & constraint

OpenCV
(C/C++ code, BSD lic) Chessboard calibration, calibration with rig or pattern
Geometric camera constraint – Minimal Problems in Computer Vision
Minimal problems in computer vision arise when computing geometrical models from image data. They often lead to solving systems of algebraic equations.
Camera Calibration Toolbox for Matlab
(Matlab toolbox) Camera Calibration Toolbox for Matlab by Jean-Yves Bouguet (C implementation in OpenCV)

Multi-View Reconstruction

Bundle Adjustment – SBA
(C/C++ code, GPL lic) A Generic Sparse Bundle Adjustment Package Based on the Levenberg-Marquardt Algorithm
Bundle Adjustment – SSBA
(C/C++ code, LGPL lic) Simple Sparse Bundle Adjustment (SSBA)

Stereo

Efficiently solving multi-label MRFs (Readme)
(C/C++ code) Segmentation, object category labelling, stereo
LIBELAS: Library for Efficient LArge-scale Stereo Matching
(C/C++ code) Disparity maps, stereo

Structure from motion

Bundler
(C/C++ code, GPL lic) A structure-from-motion system for unordered image collections
Patch-based Multi-view Stereo Software (Windows version)
(C/C++ code, GPL lic) A multi-view stereo software that takes a set of images and camera parameters, then reconstructs 3D structure of an object or a scene visible in the images
libmv – work in progress
(C/C++ code, MIT lic) A structure from motion library
Multicore Bundle Adjustment
(C/C++/GPU code, GPL3 lic) Design and implementation of new inexact Newton type Bundle Adjustment algorithms that exploit hardware parallelism for efficiently solving large scale 3D scene reconstruction problems.
openMVG
(C/C++/GPU code, MPL2 lic) OpenMVG (Multiple View Geometry) “open Multiple View Geometry” is a library for computer-vision scientists and especially targeted to the Multiple View Geometry community. It is designed to provide an easy access to the classical problem solvers in Multiple View Geometry and solve them accurately..

Visual odometry

LIBVISO2: Library for VISual Odometry 2
(C/C++ code, Matlab, GPL lic) Libviso 2 is a very fast cross-platfrom (Linux, Windows) C++ library with MATLAB wrappers for computing the 6 DOF motion of a moving mono/stereo camera.

Posted in Apps Development, C, Computer Hardware, Computer Network & Security, CUDA, Game Development, GPU (CUDA), GPU Accelareted, Graphics Cards, Image Processing, OpenCV, PARALLEL, Simulation, Virtualization | Tagged: , , , , , , , , , , , , , , , , , , , | 3 Comments »

 
Extracts from a Personal Diary

dedicated to the life of a silent girl who eventually learnt to open up

Num3ri v 2.0

I miei numeri - seconda versione

ThuyDX

Just another WordPress.com site

Algunos Intereses de Abraham Zamudio Chauca

Matematica, Linux , Programacion Serial , Programacion Paralela (CPU - GPU) , Cluster de Computadores , Software Cientifico

josephdung

thoughts...

Tech_Raj

A great WordPress.com site

Travel tips

Travel tips

Experience the real life.....!!!

Shurwaat achi honi chahiye ...

Ronzii's Blog

Just your average geek's blog

Karan Jitendra Thakkar

Everything I think. Everything I do. Right here.

VentureBeat

News About Tech, Money and Innovation

Chetan Solanki

Helpful to u, if u need it.....

ScreenCrush

Explorer of Research #HEMBAD

managedCUDA

Explorer of Research #HEMBAD

siddheshsathe

A great WordPress.com site

Ari's

This is My Space so Dont Mess With IT !!

%d bloggers like this: