Radial shifted Legendre moments for image analysis and invariant image recognition

作者：

Highlights：

• Two types of radial Legendre moments for image analysis are proposed.

• The proposed moments are transformed Legendre moments.

• These proposed moments can be thought as orthogonalized complex moments.

• A framework of deriving RST invariance of the transformed moments is investigated.

• The proposed invariants are robust to additive white noise.

摘要

•Two types of radial Legendre moments for image analysis are proposed.•The proposed moments are transformed Legendre moments.•These proposed moments can be thought as orthogonalized complex moments.•A framework of deriving RST invariance of the transformed moments is investigated.•The proposed invariants are robust to additive white noise.

论文关键词：Orthogonal moments,Legendre moments,Shifted Legendre polynomials,Image reconstruction,Invariant image recognition,Moment invariants

论文评审过程：Received 24 June 2013, Revised 14 May 2014, Accepted 9 September 2014, Available online 19 September 2014.

论文官网地址：https://doi.org/10.1016/j.imavis.2014.09.002