You mean, you replaced the mean's in the numerator and denominator by mean/2? That doesn't sound like a good idea. Which is precisely what the NCC is trying to tell you with the division by zero.Īlso, when I modified the formula to subtract (mean/2) from every pixel intensity Your answer wouldn't be "I have perfect match for the batmobile, because it's completely black", your answer would be "I can't tell, there's too little contrast in the image". Imagine someone hands you a completely black photograph and asks you what you see. The effect you're seeing makes perfect sense. Note that this isn't a "bug" in the normalized cross correlation. Or a "flat" area in the search image, either. So in a nutshell: You can't match a "flat" template using normalized cross-correlation. Multiply this by 0 and add 91 - and you have a perfect match. Now take any 2x2 pixel area in the search image, e.g. The idea of the normalized cross correlation is that the similarity doesn't change if you add an arbitrary number to every pixel or multiply every pixel by an arbitrary (non-negative) number.
I would love to look into various work arounds many of you might have been using. Using the above modified version I was unable to find appropriate matches. LewisĪlso, when I modified the formula to subtract (mean/2) from every pixel intensity, it seemed to work fine but I am concerned as to how much vulnerable to Illumination this new correlation coefficient is.Įdit: Conditions even worsened when I took a 1 X 1 pattern image and had multiple occurrences in source image. I am using the following formula: from the excellent source by J. Now, when NCC goes through this: It finds the mean of the template image as 91 and underlying source image also as 91 and then it subtracts the intensity value from the pixel which essentially takes all terms in the formula to zero resulting in an undefined correlation value and no matches are found even when there is a perfect match.! While the method is slow, it works good enough for my purpose.
I was working on the Normalized Cross Correlation for Template Matching in Spatial domain.
0 kommentar(er)
