Damiles Blog. A computer vision, OpenCV and IT technology blog.

• Neuroph, Java/Netbeans tutorial.

Neuroph is a Neural network for image recognition in java. In netbeans dzone are a netbeans/java tutorial for image recognition with neuroph library.

• Segmentation & object detection by color.

In this tutorial i go to explain how to image segmentation or detect objects byred color, in this case by red color.

This task is simple, but there are some things we must known.

Now i go to explain and get a demo code for segmentation, how to determine if each image pixel is red or no, and then, i go to explain how we  can detect object, it's similar but with diferent concept.

• VIM how to remove ^M at the end of lines

In unix the end of line is different than other systems. More times we edit windows files and when open in VI/VIM we see the ^M character at end of lines.

We can remove this characters with a simply search and replace of vim with this command:

:%s/^M//g

The ^M character is not valid write first ^ character and then M it's not the valid character. To write correctly this we must push Control+v and Contro+M keys, then appear our ^M Character.

Take care with this.

• Compile Opencv with Mac os Snow Leopard 10.6

Today i try install OpenCv in my MacOs Snow Leopard 10.6 and have this error:

error: CPU you selected does not support x86-64 instruction set

• The basics of background substraction

This tutorial explain the basics of background substraction. First of all we need define what is a background and what is a foreground.

We consider a background the pixels of image without motion. And a foreground the pixels with motion. Then the simplest background model assume each background pixel his brightness varies independently with normal distribution. Then we can calculate our statistical model of background by accumulating several dozens of frames and his squares, this is:

$$\displaystyle{S(x,y)=\sum_{f=1}^N p(x,y)}$$
$$\displaystyle{Sq(x,y)=\sum_{f=1}^N p(x,y)^2}$$