In response to “Computer vision and partial solutions”
The post is published here. This is the main quote:
In computer vision, no problem has been completely solved. People tend to move to more complex problems in an anxiety to do something new, but the fact is that this fatally builds upon a very wobbly foundation of partial solutions. My fear is that there is a high risk that nothing really gets done in this process.
I agree totally! Computer vision lacks a solid foundation. I think there are many reasons but the biggest one is the emphasis on different “solutions”, “methods” and “algorithms”. So, you have many solutions for the same problem, but is this situation good for the user? As a user I wouldn’t mind having several different ways to solve my problem - but only if they give the same answer!
HOW is important but WHAT is more important!
That’s why I think that the only solid foundation can be mathematics. I started the wiki to try to collect as much stuff as possible starting from the most elementary (or most fundamental if you prefer - I do) and then try to work it out so that you wouldn’t have to redo it. But it goes slowly…
January 21st, 2008 at 8:27 pm
[…] Most image analysis methods are intended for specific problems. But each problem may have different methods applicable. No-one is concerned that the results could be also different (see last post). […]
January 22nd, 2008 at 9:39 am
I think you’re right in making such a consideration. But the hope for generality is a common sense in every science that could be someway related to human being: just imagine AI, for a simple example, where we can identify a bunch of simple and singular difficult problems (taxonomy, elastic matching, contextualizing and de-contextualizing, language deformation and so on…) but AI researchers are still working to *global conscience* or *digital conscience* projects…
I’m involved in Computer Vision research (mostly for industrial quality control) and also I teach Robotics/CV @ University, and the first thing I say when I start the first lesson to the class is: “PLEASE, forget to be human! When you think about your eyes, your mind and your capability to solve a problem, PLEASE, just take examples, not rules. Human capabilities to go deep in a problem and subdivide it in simpler task is a thing we haven’t still realized in silicon, so PLEASE, keep it simple and stupid!”.
I wish someone had listened to my words…at least once!
Compliments for your blog and other activities, I’ll follow your news more often. Bye.
January 24th, 2008 at 4:02 pm
Thanks for the feedback, Mario. “Digital conscience” is a good one!