Image analysis by fractional-order orthogonal moments

详细信息    查看全文

• 作者：Bin Xiao^a ; ^{xiaobin@cqupt.edu.cn} ; Linping Li^a ; Yu Li^b ; Weisheng Li^a ; Guoyin Wang^a
• 关键词：Fractional-order polynomials ; Orthogonal polynomials ; Image reconstruction ; Invariant recognition ; Orthogonal moments ; Moment invariants
• 刊名：Information Sciences
• 出版年：2017
• 出版时间：March 2017
• 年：2017
• 卷：382-383
• 期：Complete
• 页码：135-149
• 全文大小：2652 K
• 卷排序：382

文摘

Orthogonal moments play an important role in image analysis and other similar applications. However, existing orthogonal moments are restricted to integer order, and little investigation of non-integer order orthogonal moments has been conducted to date. In this paper, a general framework of real-order orthogonal moments, also known as fractional-order orthogonal moments, is proposed. In this general framework, fractional-order orthogonal moments can be defined in Cartesian and polar coordinate systems. Shifted Legendre polynomials are implemented in this paper to investigate the properties of fractional-order orthogonal moments. A series of experiments are performed, which demonstrate that fractional-order orthogonal moments are not only capable of region-of-interest (ROI) feature extraction but also have potential for image reconstruction and face recognition and have high noise robustness in invariant image recognition.