| Article ID | Journal | Published Year | Pages | File Type |
|---|---|---|---|---|
| 534231 | Pattern Recognition Letters | 2011 | 10 Pages |
A new method is proposed for fast and low-complexity computation of exact 3D Legendre moments. The proposed method consists of three main steps. In the first step, the symmetry property is employed where the computational complexity is reduced by 87%. In the second step, exact values of 3D Legendre moments are obtained by mathematically integrating the Legendre polynomials over digital image voxels. An algorithm is employed to significantly accelerate the computational process. In this algorithm, the equations of 3D Legendre moments are treated in a separated form. The proposed method is applied to determine translation-scale invariance of 3D Legendre moments in a very simple way. Numerical experiments are performed where the results are compared with those of the existing methods. Complexity analysis and results of the numerical experiments clearly ensure the efficiency of the proposed method.
►A new method is proposed for fast and low-complexity computation of exact 3D Legendre moments. ► This method is applicable to symmetry, asymmetry and irregular 3D objects. ► The symmetry property is effectively applied where 87% of the computational complexity is reduced. ► Also, it is applied to determine translation-scale invariance of 3D Legendre moments very simply. ► This method will contribute to the application of 3D Legendre moments.
