Content

1. Software Environment
2. Data Generation
3. Codewords Generation
   1. CPU
   2. GPU
      
4. Support Vector Machine
5. Convolutional Neural Network (pending)
6. My Understanding 

1.Software Environment

The required software are listed below:

• python 2.7 
• ipython 
• scipy
• numpy
• matplotlib
• pillow
• h5py
• scikit-learn
  
• tensorflow

It is recommanded to use linux or mac osx operating sytem. I use ubuntu 16.04. If you use different version of operating system, the command lines below may not work.

To set up  software environment, you might need additional packages:

• pip
• git
  

You can get all these packages installed easily via command line "sudo apt-get install ...(name of the packages) " or  "sudo pip install ... (package names)".  It may also help to protect your system from unexpected mistakes by setting up a virtual environments. The simple tutorial for setting up a virtual environment can be found in the link:

http://docs.python-guide.org/en/latest/dev/virtualenvs/

2.Data Generation

6.My Understanding

I think this problem is not one of those that a typical neural network may be good at. 

I believe that currently, neural network is at most as good as human. Or it may be better than human sometimes but that is only because it may use more resource and be more stable. So if a task is in principle impossible for human, then it is highly poossible that no neural network can finish it. It seems to be that this is one of that kind of task.

Some of the images from the vcc are in principle impossible for human to recognize when then noise is too high.  We are able to pinpoint the spot only after the background subtraction. Thus the correlation between different images is crucial for this task.

Of course, the correlation is also important in classification problem. But the situaltion is different here. We need an exact correlation to do the right background subtraction.