Fourier Spectrum Image Texture Analysis

被引:0
作者
Hu, Xinyu [1 ]
Ensor, Andrew [2 ]
机构
[1] AUT, Sch Engn Comp & Math Sci, Auckland, New Zealand
[2] AUT, High Performance Comp Res Lab, Auckland, New Zealand
来源
2018 INTERNATIONAL CONFERENCE ON IMAGE AND VISION COMPUTING NEW ZEALAND (IVCNZ) | 2018年
关键词
D O I
暂无
中图分类号
TP18 [人工智能理论];
学科分类号
081104 ; 0812 ; 0835 ; 1405 ;
摘要
A texture descriptor is a collection of quantified measurements of a texture's properties. They are used to describe how the basic unit of a texture is repeated in an image, such as the pattern size, pattern linelikeness, directional unification and directionality. These quantified measures have often been calculated in the spatial domain. This paper proposes a new approach of calculating texture deature descriptors in the frequency domain. It also introduces new texture feature descriptors, which describe how the unit of texture is repeated global throughout the image, such as pattern formation linelikeness and repetition directionality.
引用
收藏
页数:6
相关论文
共 19 条
[1]  
[Anonymous], 2008, DIGITAL IMAGE PROCES
[2]  
Bagri N., 2015, International Journal of Advanced Science and Technology, V80, P41
[3]  
Bracewell R., 1995, Two-Dimensional Imaging (Prentice-Hall Signal Processing Series)
[4]  
Bracewell Ronald N., 2000, The Fourier Transform and Its Applications
[5]  
Castelli V., 2002, Image Databases: Search and Retrieval of Digital Imagery
[6]  
Efford N., 2000, Digital image processing: a practical introduction using Java, Inc
[7]  
Graham D. F, 2002, REMOVING SHADOWS IMA
[8]  
HARALICK RM, 1973, IEEE T SYSTEM MAN CY, V3
[9]  
Haykin SO., 2014, Adaptive Filter Theory, V5th edition
[10]  
Huang K. Y., 2002, Syntactic Pattern Recognition for Seismic Oil Exploration