Invariance of image ellipse oblateness degree and its application to construction of affine invariants

Chao* JI; Xiao-dong YANG; Wei WANG

doi:10.3788/OPE.20162408.2078

您当前的位置：

首页 >

文章列表页 >

Invariance of image ellipse oblateness degree and its application to construction of affine invariants

Information Sciences | 更新时间：2020-07-07

- Invariance of image ellipse oblateness degree and its application to construction of affine invariants
- Optics and Precision Engineering Vol. 24, Issue 8, Pages: 2078-2086(2016)
- 作者机构：
  
  海军潜艇学院, 山东青岛 266199
- 作者简介：
- 基金信息：
- DOI：10.3788/OPE.20162408.2078
  CLC： TP391.4
- Received：06 May 2016，
  
  Accepted：22 June 2016，
  
  Published：25 August 2016
- 稿件说明：
移动端阅览
Chao* JI, Xiao-dong YANG, Wei WANG. Invariance of image ellipse oblateness degree and its application to construction of affine invariants[J]. Optics and precision engineering, 2016, 24(8): 2078-2086.
DOI：

Chao* JI, Xiao-dong YANG, Wei WANG. Invariance of image ellipse oblateness degree and its application to construction of affine invariants[J]. Optics and precision engineering, 2016, 24(8): 2078-2086. DOI： 10.3788/OPE.20162408.2078.

摘要

针对传统基于面积比不变的仿射不变量方法具有的特征点选取不稳定且有冗余以及区域面积误差累积等特点，提出了一种基于图像椭圆扁度划分策略的仿射不变量构造方法。介绍了图像仿射变换模型，得到了图像仿射近似条件。结合图像椭圆扁率定义，依据不变矩理论证明了仿射变换下图像扁率的不变性。给出了图像扁度的定义及其物理含义，并以此作为图像同心圆划分依据，选取三阶以下仿射不变矩作为图像特征量，通过计算各同心圆区域的仿射不变量描述图像目标。将提出的方法应用于实际舰船图像并结合离散系数对其稳定性进行了分析。结果表明：同一舰船目标各种仿射变换图像计算所得扁度相同，所在划分特征圆区域仿射不变量离散系数最大为1.55%。得到的结果显示该方法对目标图像的特征区域划分具有唯一性，构造的仿射不变特征稳定性较好。

Abstract

As the traditional affine invariants based on the invariant of area ratio are characterized by unstable and redundant feature points

error accumulation

this paper proposes a novel method based on the division strategy of image ellipse oblateness degree for construction of affine invariants. The affine transformation model was presented

and the condition of affine approximation was obtained. In combination of the definition of image ellipse oblateness degree and the invariant moment theory

the invariance of image ellipse oblateness under affine transformation was verified. Meanwhile

the definition of image oblateness degree and its physical meaning were given. Then

on the basis of the image ellipse oblateness degree

the affine invariant moments below the 3rd order were selected as the feature descriptors

the image target was described by calculation of the affine invariants of each concentric region. Finally

the proposed method was applied to the actual ship images and its stability was analyzed by discrete coefficients. Experimental results indicate that all kinds of the target images for the same ship under different affine transformations have the same oblateness degree

and the maximum discrete coefficient in the divided feature region is 1.55%.It concludes that the proposed method is unique for the image division and constructed affine invariants have good stability.

关键词

Keywords

references

FLUSSER J, SUK T. Pattern recognition by affine moment invariants[J]. Pattern Recognition, 1993, 26(1): 167-174.

王晓年, 邱立可, 程宇, 等. 一种基于环间面积比的旋转､平移和缩放不变性描述符[J]. 模式识别与人工智能, 2012, 25(1): 82-88.

刘亦书. 基于协方差矩阵的仿射不变量[J]. 小型微型计算机系统, 2007, 28(7): 1282-1286.

刘亦书. 一种基于质量(面积)的不变量[J]. 华南师范大学学报(自然科学版), 2007(2): 57-61.

YANG Z W, COHEN F S. Image registration and object recognition using affine invariants and convex hulls [J]. IEEE Trans. on Image Processing, 1999, 8(7): 934-946.

ZHANG J Q, TAN T N. Affine invariant texture analysis based on structural properties[C]. Proc. of the Fifth Asian Conference on Computer Vision, Melbourne, Australia, 2002: 216-221.

陈涛, 粟毅, 蒋咏梅, 等. 利用仿射几何特性提取图像中的仿射不变特征[J]. 中国图象图形学报, 2007, 12(9): 1633-1641.

FLUSSER J. Moment invariants in image analysis[C]. Proc. of World Academy of Science Engineering and Technology, 2006, 11: 196-201.

HU M K. Visual pattern recognition by moment invariants[J].Trans. on Information Theory, 1962, 8: 179-187.

HORNG M. Multilevel thresholding selection based on the artificial bee colony algorithm for image segmentation[J].Expert Systems with Applications, 2011, 38(11): 13785-13791.

AVID D, LOWE G. Distinctive image features from scale-invariant keypoints[J].International Journal of Computer Vision, 2004, 60(2): 99-114.

RAHTU E, SALO M, HEIKILA J. Affine invariant pattern recognition using multiscale autoconvolution[J].IEEE Trans.on Pattern Analysis and Machine Intelligence, 2005, 27(6): 908-918.

王丽, 魏巍, 吴林钢, 等. SAR图像目标识别新方法[J]. 液晶与显示, 2014, 29(3): 429-434.

李兴唐, 曹立华, 王思雯. 仿射变换的飞行器识别[J]. 光学精密工程, 2009, 17(2): 402-408.

MIKOLAJCZYK K.A comparison of affine region detectors[J]. International Journal of Computer Vision, 2005, 65(1/2): 43-72.

孟亚州, 马瑜, 白冰, 等. 基于粒子群优化的Otsu肺组织分割算法[J]. 液晶与显示, 2015, 30(6): 1000-1007.

KROLUPPER F, FLUSSER J. Polygonal shape description for recognition of partially occluded objects[J].Pattern Recognition Letters, 2007, 28: 1002-1011.

贾平, 徐宁, 张叶. 基于局部特征提取的目标自定识别[J]. 光学精密工程, 2013, 21(7): 1898-1905.

WANG X N, QIU L K, CHENG Y, et al. An area ratio between rings based translation, rotation and scale invariant descriptor[J]. Pattern Recognition and Artificial Intelligence, 2012, 25(1): 82-88. (in Chinese)

LIU Y SH.Affine invariants based on covariance matrix[J]. Journal of Chinese Computer Systems, 2007, 28(7): 1282-1286. (in Chinese)

LIU Y SH. A set of invariants based on mass/area[J]. Journal of South China Normal University(Natural Science Edition) , 2007(2): 57-61. (in Chinese)

CHEN T, SU Y, JIANG Y M, et al. Affine invariant feature extraction based on affine geometry[J]. Journal of Image and Graphics, 2007, 12(9): 1633-1641.

WANG L, WEI W, WU L G, et al. Novel target recognition method for SAR images[J]. Chinese Journal of Liquid Crystals and Displays, 2014, 29(3): 429-434.(in Chinese)

LI X T, CAO L H, WANG S W. Aircraft recognition based on affine transform[J]. Opt. Precision Eng., 2009, 17(2): 402-408.(in Chinese)

MENG Y ZH, MA Y, BAI B, et al. Improved lung segmentation algorithm based on 2D Otsu optimized by PSO[J].Chinese Journal of Liquid Crystals and Displays, 2015, 30(6): 1000-1007.(in Chinese)

JIA P, XU N, ZHANG Y. Automatic target recognition based on local feature extraction[J]. Opt. Precision Eng., 2013, 21(7): 1898-1905.(in Chinese)

Views

504

下载量

CSCD

Alert me when the article has been cited

提交

Tools

Publicity Resources

Spatiotemporal distribution characteristics analysis of local flameout in jet flames based on 5 kHz planar laser-induced fluorescence

Simulating primary visual cortex to improve robustness of CNN neural network structures

Non-contact wave height measurement method based on laser incident spot recognition

Blind sidewalk image location based on machine learning recognition and marked watershed segmentation

Identification of bruised kiwifruits during storage by near infrared spectroscopy and extreme learning machine

Related Author

LIU Wenbei

YUAN Xun

CAO Zhen

YANG Chaobo

YU Xin

PENG Jiangbo

GAO Long

LI Dongming

Related Institution

Institute of Opto-electronics， School of Astronautics， Harbin Institute of Technology

China North Vehicle Research Institute

Collegel of Computer Science and Technology， Changchun University of Technology

School of Internet of Things Engineering， Wuxi University

Chongqing Xike Waterway Engineering Consulting Center

AI问答

Address：No.3888 Dong Nanhu Road, Changchun, Jilin, China Postal code：130033
Tel：0431-86176855 Email：gxjmgc@ciomp.ac.cn
Technical support is provided by Beijing Founder electronics co., LTD 吉ICP备11002662号-17 京公网安备11010802024621
It is recommended to read the content of this site in Chrome&IE9+. Please switch to extreme mode in browser 360.
Cookies We use cookies to help provide and enhance our service and tailor content. By continuing, you agree to the use of cookies.

⁰