New fractional-order Legendre-Fourier moments for pattern recognition applications
作者：
Highlights：
• New fractional-order Legendre-Fourier orthogonal polynomials are derived.
• New fractional-order Legendre-Fourier moments are defined.
• Direct rotation, scaling and translation invariants are derived.
• The proposed moments archive high recognition rates in presence of geometric and noise attacks.
• The proposed outperformed the classical integer-order Legendre-Fourier moments.
• The proposed moments outperformed all existing orthogonal image moments.
摘要
•New fractional-order Legendre-Fourier orthogonal polynomials are derived.•New fractional-order Legendre-Fourier moments are defined.•Direct rotation, scaling and translation invariants are derived.•The proposed moments archive high recognition rates in presence of geometric and noise attacks.•The proposed outperformed the classical integer-order Legendre-Fourier moments.•The proposed moments outperformed all existing orthogonal image moments.
论文关键词：Color image descriptors,Pattern recognition,Rotation invariance,Fractional-order moments,Legendre-Fourier moments
论文评审过程：Received 12 April 2019, Revised 4 January 2020, Accepted 28 February 2020, Available online 2 March 2020, Version of Record 11 March 2020.
论文官网地址：https://doi.org/10.1016/j.patcog.2020.107324
