Fast computation of invariant geometric moments: a new method giving correct results
Invariant geometric moments have been widely used in shape analysis and pattern recognition. Using a discrete version of Green's theorem, the authors propose a method for fast computation of the moments in binary images. The method is similar to-and as efficient as-the previous method of Li and...
Saved in:
Published in | Pattern Recognition, 1994 12th International Conference On. Vol. 1 Vol. 1; pp. 201 - 204 vol.1 |
---|---|
Main Authors | , |
Format | Conference Proceeding |
Language | English |
Published |
IEEE
1994
|
Subjects | |
Online Access | Get full text |
ISBN | 0818662654 9780818662652 |
DOI | 10.1109/ICPR.1994.576257 |
Cover
Summary: | Invariant geometric moments have been widely used in shape analysis and pattern recognition. Using a discrete version of Green's theorem, the authors propose a method for fast computation of the moments in binary images. The method is similar to-and as efficient as-the previous method of Li and Shen (1991). But the precision is largely improved. The new method gives exactly the same results as if the moments were computed by direct summation over the object area. |
---|---|
ISBN: | 0818662654 9780818662652 |
DOI: | 10.1109/ICPR.1994.576257 |