Pseudo-Zernike moment invariants to blur degradation and similarity transformation

Abstract

The moment invariants have been widely used as feature descriptors against both blur degradation and similarity transformation in pattern recognition. Since Pseudo-Zernike moments outperform other moments in feature matching and object recognition, we propose a new set of Pseudo-Zernike moment invariants holding for blur and similarity transformation simultaneously in this paper to improve the match results. In order to construct the proposed invariants, we also establish the relationship between the Pseudo-Zernike moments of the distorted images and those of the original images with respect to circularly symmetric point spread function. The experimental results are presented to confirm that compared to the other moment invariants, the proposed combined invariants have better invariance and more powerful discriminating ability in terms of pattern recognition accuracy, especially when the images contain noises.

Keywords:

• combined invariants
• Pseudo-Zernike moments
• blur degradation
• similarity transformation
• image recognition

2010 AMS Subject Classifications:

• 68T10
• 33C47
• 44A15
• 42C10
• 94A08

Acknowledgements

This work was supported by the Starting Scientific Research Foundation of Nanjing University of Posts and Telecommunications for New Teachers (NY211030), by the National Natural Science Foundation of China under Grants 31200747 and 60911130370, by the Natural Science Foundation of Jiangsu Province under Grants BK2012437.