Construction of a complete set of orthogonal Fourier-Mellin moment invariants for pattern recognition applications

被引：40
|
作者：
Zhang, H. [1 ]
Shu, H. Z. [1 ]
Haigron, P. [2 ,3 ]
Li, B. S. [4 ]
Luo, L. M. [1 ]
机构：
[1] Southeast Univ, Lab Image Sci & Technol, Sch Engn & Comp Sci, Nanjing 210096, Peoples R China
[2] INSERM, U642, F-35042 Rennes, France
[3] Univ Rennes 1, Lab Traitement Signal & Image, F-35042 Rennes, France
[4] Shandong Canc Hosp, Dept Radiat Oncol, Jinan 250117, Peoples R China
来源：
IMAGE AND VISION COMPUTING | 2010年 / 28卷 / 01期
基金：
中国国家自然科学基金;
关键词：
Orthogonal Fourier-Mellin moments; Completeness; Similarity invariants; Moment invariants; Pattern recognition; SCALE INVARIANTS; CHARACTER-RECOGNITION; IMAGE-RECONSTRUCTION; ZERNIKE; TRANSLATION;
D O I：
10.1016/j.imavis.2009.04.004
中图分类号：
TP18 [人工智能理论];
学科分类号：
081104 ; 0812 ; 0835 ; 1405 ;
摘要：
The completeness property of a set of invariant descriptors is of fundamental importance from the theoretical as well as the practical points of view. In this paper, we propose a general approach to construct a complete set of orthogonal Fourier-Mellin moment (OFMM) invariants. By establishing a relationship between the OFMMs of the original image and those of the image having the same shape but distinct orientation and scale, a complete set of scale and rotation invariants is derived. The efficiency and the robustness to noise of the method for recognition tasks are shown by comparing it with some existing methods on several data sets. (C) 2009 Elsevier B.V. All rights reserved.
引用
收藏
页码：38 / 44
页数：7
相关论文
共 50 条
  • [31] Fourier-Mellin moment-based intertwining map for image encryption
    Kaur, Manjit
    Kumar, Vijay
    MODERN PHYSICS LETTERS B, 2018, 32 (09):
  • [32] Invariant character recognition using the Fourier-Mellin image descriptors
    Li, Y.
    Optik (Stuttgart), 1992, 90 (01):
  • [33] APPLICATIONS OF MOMENT INVARIANTS TO NEUROCOMPUTING FOR PATTERN-RECOGNITION
    LI, Y
    ELECTRONICS LETTERS, 1991, 27 (07) : 587 - 588
  • [34] New set of generalized legendre moment invariants for pattern recognition
    Benouini, Rachid
    Batioua, Imad
    Zenkouar, Khalid
    Mrabti, Fatiha
    El Fadili, Hakim
    PATTERN RECOGNITION LETTERS, 2019, 123 : 39 - 46
  • [35] Fast computation of Orthogonal Fourier-Mellin moments using modified direct method
    Papakostas, G. A.
    Boutalis, Y. S.
    Karras, D. A.
    Mertzios, B. G.
    2007 14TH INTERNATIONAL WORKSHOP ON SYSTEMS, SIGNALS, & IMAGE PROCESSING & EURASIP CONFERENCE FOCUSED ON SPEECH & IMAGE PROCESSING, MULTIMEDIA COMMUNICATIONS & SERVICES, 2007, : 355 - +
  • [36] A COMPARISON BETWEEN FOURIER-MELLIN DESCRIPTORS AND MOMENT BASED FEATURES FOR INVARIANT OBJECT RECOGNITION USING NEURAL NETWORKS
    GRACE, AE
    SPANN, M
    PATTERN RECOGNITION LETTERS, 1991, 12 (10) : 635 - 643
  • [37] Novel Quaternion Orthogonal Fourier-Mellin Moments Using Optimized Factorial Calculation
    Wang, Chunpeng
    Chen, Long
    Xia, Zhiqiu
    Li, Jian
    Li, Qi
    Wei, Ziqi
    Wang, Changxu
    Han, Bing
    DIGITAL FORENSICS AND WATERMARKING, IWDW 2023, 2024, 14511 : 262 - 276
  • [38] INVARIANT CHARACTER-RECOGNITION USING THE FOURIER-MELLIN IMAGE DESCRIPTORS
    LI, Y
    OPTIK, 1992, 90 (01): : 20 - 26
  • [39] Palmprint recognition using Fourier-Mellin transformation based registration method
    Li, L
    Yang, X
    Hi, YL
    Tian, T
    AUDIO AND VIDEO BASED BIOMETRIC PERSON AUTHENTICATION, PROCEEDINGS, 2005, 3546 : 730 - 738
  • [40] Moment invariants for pattern recognition
    Boyce, J. F.
    Hossack, W. J.
    PATTERN RECOGNITION LETTERS, 1983, 1 (5-6) : 451 - 456
12345