From: pier.damato@gmail.com   
      
   Hi everybody!   
   I'm working on a project of mobile robotics and I must develop a system   
   of artificial vision.   
   The operating system of development is RTAI, a Linux realtime   
   extension.   
   After having acquired an image, I must recognize the present objects.   
   The robot moves in a structured world and the obiects have well defined   
   geometric shapes (namely cube, sphere, cone, pyramid etc).   
   How can I do this?   
   Is there an Internet site or a book explaining the possible algorithms   
   to use in order to solve the problem?   
      
   Thanks in advance for your help   
      
   Pier   
      
   [ comp.ai is moderated ... your article may take a while to appear. ]   
      
   --- SoupGate-Win32 v1.05   
    * Origin: you cannot sedate... all the things you hate (1:229/2)