计算机工程

• 开发研究与工程应用 • 上一篇    下一篇

基于平稳小波变换和亮度序的局部特征描述子

房贻广 1,颜普 2,刘武 3,张骥 4,谭守标 2   

  1. (1.国网安徽省电力公司 安全监察质量部,合肥 230022; 2.安徽大学 计算智能与信号处理教育部重点实验室,合肥 230601; 3.国网安庆供电公司 安全监察质量部,安徽 安庆 246000; 4.安徽南瑞继远电网技术有限责任公司,合肥 230088)
  • 收稿日期:2016-10-10 出版日期:2017-11-15 发布日期:2017-11-15
  • 作者简介:房贻广(1969—),男,高级工程师、硕士,主研方向为计算机视觉、电力安全监察技术;颜普,博士;刘武,工程师、硕士;张骥,硕士;谭守标(通信作者),副教授、博士。
  • 基金项目:
    国家科技支撑计划项目(2014BAH27F01);国家电网公司科技项目(5212D01502DB)。

Local Feature Descriptor Based on Stationary Wavelet Transform and Intensity Order

FANG Yiguang 1,YAN Pu 2,LIU Wu 3,ZHANG Ji 4,TAN Shoubiao 2   

  1. (1.Safety Supervision Quality Department,State Grid Anhui Electric Power Supply Co.,Hefei 230022,China; 2.Key Laboratory of Intelligent Computing and Signal Processing,Ministry of Education,Anhui University,Hefei 230601,China; 3.Safety Supervision Quality Department,State Grid Anqing Electric Power Supply Co.,Anqing,Anhui 246000,China; 4.Anhui Nanrui Jiyuan Power Grid Tech Co.,Ltd.,Hefei 230088,China)
  • Received:2016-10-10 Online:2017-11-15 Published:2017-11-15

摘要: 局部区域的非线性亮度变化通常会造成局部特征描述子的不稳定。针对该问题,在平稳小波变换和亮度序的基础上,提出一种局部特征描述子。利用Hessian-Affine算子检测仿射协变区域,对检测区域进行平稳小波变换分解,将不同尺度的多个低频子带作为支持区域,多支持区域的使用可以有效地降低图像扭曲带来的不利影响。采用亮度序对支持区域进行区域划分,确保所构造描述子对单调亮度变化具有不变性,并在局部旋转不变坐标系下计算局部特征描述子。实验结果表明,该描述子在视角、线性亮度和JPEG压缩等变化下具有较好的鲁棒性。

关键词: 特征描述子, 局部特征, 平稳小波变换, 亮度序, 多支持区域, 旋转不变坐标系

Abstract: The nonlinear illumination changes of local region frequently have a negative impact on the stability of local feature descriptor.In order to solve the problem,a local feature descriptor based on Stationary Wavelet Transform(SWT) and intensity order is proposed.The affine covariant region is detected by using Hessian-Affine detector.The detected region is decomposed by SWT to get multiple low-frequency subbands of different scales as support regions,and the used multiple support regions can effectively reduce the negative impact which is caused by image distortion.The support regions are divided by intensity orders and this ensures that the proposed descriptor is invariant to the monotonous illumination changes.The local feature descriptor is obtained under the local rotation invariant coordinate system.Experimental results show the robustness of the proposed descriptor for the image with viewpoint changes,linear illumination changes,JPEG compression changes and so on.

Key words: feature descriptor, local feature, Stationary Wavelet Transform(SWT), intensity order, multiple support region, rotation invariant coordinate system

中图分类号: