002. Click on “Free non-commercial” under “Tools & Downloads”

003. Download “Intel® C++ Composer XE 2011 for Linux” and “Intel® Math Kernel Library (Intel® MKL) for Linux”, your email-box will receive letter, which contains the series number for installation.

004. Unpack those two package files, then in each main folder, run:
[bash]
sudo ./install.sh
[/bash]

005. Choose default setting with series number. Then installed files should be in /opt/intel/

006. Edit the .bashrc file in your user’s home folder, add following codes. Those two path are supposed to be your file location, it make change a little. And “ia32″ is the parameter of platform, you can choose what you want following the instruction in file iccvars.sh and mklvars.sh.
[bash]
source /opt/intel/compilerpro-12.0.1.107/bin/iccvars.sh ia32
source /opt/intel/mkl/bin/mklvars.sh ia32
[/bash]

007. Save and close .bashrc file, run:
[bash]
source ~/.bashrc
[/bash]
008. test path:
[bash]
which icc
[/bash]

|*******************************
|** Part 2. Linking in Program ******
|*******************************
009. Add MKL 10.x header file INCLUDE path in your compiler command line, your makefile or configure file. (default: /opt/intel/mkl/10.x.x.xxx/include)

010. Add MKL 10.x library path in your compiler command line, your makefile or configure file. (default: /opt/intel/mkl/10.x.x.xxx/lib/32)

011. Specify the corresponding libraries in your compiler command line, your makefile or configure file.
With static link, they are as follows:
[bash]
-Wl,–start-group
/opt/intel/mkl/10.0.xxx/lib/32/libmkl_intel.a
/opt/intel/mkl/10.0.xxx/lib/32/libmkl_intel_thread.a
/opt/intel/mkl/10.0.xxx/lib/32/libmkl_core.a
Wl,–end-group
/opt/intel/mkl/10.0.xxx/lib/32/libiomp5md.so -lpthread -lm
[/bash]
With dynamic link,
[bash]
-L/opt/intel/mkl/10.0.xxx/lib/32/
-lmkl_intel.so -lmkl_intel_thread.so -lmkl_core.so [-liomp5md]
[-lpthread] [-lm]
[/bash]
the path maybe slightly different due to different installation, just take a look in the install folder.
Note 1: In case of using static linking, the interface layer, threading layer, and computation layer libraries must be enclosed in grouping symbols (<-Wl,--start-group, -Wl,--end-group).
Note 2: Specifying MKL library path in the link command line is required. For example, -L/opt/intel/mkl/10.x.xxx/lib/32, so that the linker can search for real archive libraries.
Note 3: The order of listing libraries in the link line is essential, except for the libraries enclosed in the grouping symbols.

012. Set MKL library path to LD_LIBRARY_PATH environment variable before running application, e.g.,
[bash]
export LD_LIBRARY_PATH=/opt/intel/mkl/10.x.x.xxx/lib/32:$LD_LIBRARY_PATH
[/bash]

References Source:
http://software.intel.com/en-us/articles/performance-tools-for-software-developers-for-easily-migrating-from-mkl-9x-to-10x/
http://www.sciencenet.cn/m/user_content.aspx?id=362146

My webcam, which works fine in OpenCV 2.1, could not even be launched in OpenCV 2.2. After some google work, it seems to be a known Bug of 2.2 version and has been solved in the branch but not in the package.

So, just DIY! Only one file needs to be modified: $(OpenCV Folder)\modules\highgui\src\precomp.hpp

Find:
[cpp]
#if !defined WIN32 && !defined _WIN32
#include “cvconfig.h”
#else
void FillBitmapInfo( BITMAPINFO* bmi, int width, int height, int bpp, int origin );
#endif
[/cpp]

Replace:
[cpp]
#include “cvconfig.h”
#if defined WIN32 || defined _WIN32
void FillBitmapInfo( BITMAPINFO* bmi, int width, int height, int bpp, int origin );
#endif
[/cpp]

Re-compile OpenCV project, and done.

Task1: Using Neural Network with Gradient Decent, Line Search and Conjungate Gradient methods

Task2: Using KNN in classification

Task3: Using Parzen Window in classification

Task4: Using RBF in classification

My document(PDF format) of this task is below, if you have interest, maybe you can read it.

Homework 5. of Machine Intelligence 1 – NN-KNN-PW-RBF

The main task is to detectExtrema and Ridge from images.

My document(PDF format) of this task is below, if you have interest, maybe you can read it.

Homework 3. of Automatic Image Analysis – Extrema and Ridge Detection

Here is output of the 5th. homework.

Figure 1.

Figure 2.

The main task is to do both Projective Reconstruction and Euclidean Reconstruction given corresponding point pairs and some control points in euclidean coordinates.

In Projective Reconstruction we firstly calculate the fundamental matrix from the given point pairs and then derivate the projective matrices using normalized configuration (the most simple way) . With all this information a linear triangulation method is used to calculate the corresponding object points in projective space. And those procedure is so called Projective Reconstruction (of course the simple without any optimization).

In Euclidean Reconstruction we simply using all the information we got from the Projective Reconstruction and make the same procedure to the control points. At the mean time we calculate the spatial homograph using the control points.   Finally all the object points in projective space are transposed into euclidean space using the same spatial homograph, and that is so called Euclidean Reconstruction (without any optimization).

My document(PDF format) of this homework is below, if you have interest, maybe you can read it.

Homework 5. of Photogrammetric Computer Vision – 3D Reconstruction

Figure 1.

Figure 2.

Figure 3.

The task of figure 1. is to identify the origin shape after some scaling, moving, rotating operations with the help of so called Hough Transform. The task of figure 2. is a advanced version of the task before, which will identify the money from a complicated scene. The task of figure 3. is mostly used in camera calibration to automatically find out the control points, which then can be used to calculate the calibration matrix and the parameters of camera.

My document(PDF format) of this task is below, if you have interest, maybe you can read it.

Homework 2. of Automatic Image Analysis – Hough Transform

Figure 1.

The two images in the left show two type of leaves that we want to identify in the right-up image, and the right-down image is the result of my algorithm.

The algorithm just need a so called Fourier Descriptor to finish the job and actually some morphology operators to find out the edges of each leaf.

My document(PDF format) of this task is below, if you have interest, maybe you can read it.

Homework 1. of Automatic Image Analysis – Fourier Descriptor