0

Can anyone give some advice to the thought process of matching complex patterns. For example, if I show the user a treble-clef and they draw the pattern.

I need to generate a number representing how close the line was to the source. For my example, i want to ignore speed, pauses, or other time based elements just the final product.

I have been racking my brain and 'google'ing but have not seen any example that helps.

Bill Bonar
  • 1,017
  • 2
  • 10
  • 22
  • It might be helpful if you share what type of drawing device you intend to use. – Gilbert Le Blanc Apr 17 '12 at 18:01
  • In this case the "original" and the "copy" will be an ordered set of lines with start and end plots – Bill Bonar Apr 17 '12 at 18:07
  • Would there be a difference in score if the long, vertical line of the treble clef were drawn first or last? Or if the two dots for the bass clef were drawn first or last? My thinking is that if there is no differnce, then you are doing more character recognition and less gesture recognition. – rajah9 Apr 18 '12 at 19:05
  • In the context of my application, yes the order of the shapes are important – Bill Bonar Apr 18 '12 at 19:08
  • These nuggets from the Consumer Electronics Show might give you a start. http://abcnews.go.com/blogs/technology/2012/01/40031/ or http://www.pcworld.idg.com.au/article/412048/audi_shows_gesture-driven_three-panel_heads-up_dashboard_display/. – rajah9 Apr 18 '12 at 19:13

1 Answers1

0

I searched for "Computer Vision Gesture Recognition" and found a student review paper that surveys the field and may give you some helpful references.

rajah9
  • 11,645
  • 5
  • 44
  • 57