LabVIEW

cancel
Showing results for 
Search instead for 
Did you mean: 

what does the score mean in pattern matching function of IMAQ Vision builder?

Hi,

I have a question about the pattern matching function in IMAQ Vision builder.

What does the score (0~1000) mean in pattern matching function of IMAQ Vision builder? Is it based on the image correlation coeffeicient?
If it is, how does the correlation coefficients converted to the score ranged from 0 to1000?

Thanks,

0 Kudos
Message 1 of 4
(3,923 Views)
I use Vision Development and a match score of 1000 means that is 100% identical and 920 is 92.0 % identical to the original matched image.  Not sure where I read this but this is my understanding of the scores.
 
Matthew Fitzsimons

Certified LabVIEW Architect
LabVIEW 6.1 ... 2013, LVOOP, GOOP, TestStand, DAQ, and Vison
0 Kudos
Message 2 of 4
(3,916 Views)

Hello unc,

In a pattern matching application, the score relates how closely the template resembles the located matches.  A score is produced for each match based on the correlation result at that location.  (See page 12-7 of the Vision Concepts Manual for an in-depth discussion of how the correlation is calculated.)  A high score indicates a very close match, while a low score indicates a poor match.  For more information, please check out the Pattern Matching Strategies Developer Zone article. 

As I have not yet been able to find information on the formulaic relationship between the pattern matching score and the correlation result at a particular location, I suspect that information may be proprietary.

Best Regards,
T. McCarty
Applications Engineering

0 Kudos
Message 3 of 4
(3,901 Views)

An additional note on scores based my use is you always want a match of 800 or above.  700 to 800 is starts to misidentify objects.  700 and below is very unreliable.

Hope this is helpful,

 



Message Edited by mfitzsimons on 01-11-2008 10:46 AM
Matthew Fitzsimons

Certified LabVIEW Architect
LabVIEW 6.1 ... 2013, LVOOP, GOOP, TestStand, DAQ, and Vison
0 Kudos
Message 4 of 4
(3,889 Views)