Recognition of Degraded Images by Legendre Moment Invariants

Analysis and interpretation of an image which was acquired by a non ideal imaging system is the key problem in many application areas. Existing methods to obtain blur invariants which are invariant with respect to centrally symmetric blur are based on geometric moments or complex moments.. In this paper, we propose an alternative approach. We derive the features for image representation which are invariant with respect to blur regardless of the degradation point spread function (PSF) provided that it is centrally symmetric. Methods to obtain blur invariants which are invariants with respect to centrally symmetric blur are based on geometric moments or complex moments, orthogonal Legendre moments. The performance of the proposed descriptors is evaluated with various point-spread functions and different image noises. The comparison of the different approaches with previous methods in terms of pattern recognition accuracy is also provided. The experimental results show that the proposed descriptors are more robust to noise and have better discriminative power than the methods based on geometric or complex moments.