#### Chewy509

##### Wotty wot wot.

A quick question for the programmers among us.

Does anyone know of a suitable pattern recognition algorithm that returns a probability of match, when the input patterns are a string a compass bearings that define a shape. (A bearing of direction is sampled every x time).

eg

shape 1: 0 45 45 270 0 - Is a triangle

shape 2: 0 90 180 270 0 - Is a square.

shape 3: 15 60 60 285 15 - is a what?

So function comparing shape 1 and 2 will return 0.2 (or close to), and a function comparing 1 and 3 will return 1.0.

The other key is that the pattern in shape 3, may be a subset of the values in the pattern to be matched.

I've thought of using naive bayes, but would like to know of any others?

PS. The typical number of values within a pattern will be between 1000 and 2000.