基于HVS的自然场景图像特征提取方法

作者：诸葛振荣，徐 敏 日期：2007-12-28/span> 浏览：3568 查看PDF文档

基于HVS的自然场景图像特征提取方法

诸葛振荣，徐 敏
(浙江大学 电气工程学院，浙江 杭州 310027)

摘 要：提出了基于人类视觉系统的自然场景图像颜色和纹理特征提取方法。介绍了两类低层图像特征颜色和纹理特征提取方法，分别提出了以自适应主导色原理来表示颜色特征、采用纹理灰度图的空频域特性表示空间纹理特征;以ACA方法获得自适应主导色、以可控金字塔滤波分解的方法获取纹理特征。同时还介绍了优化颜色构成距离度量和纹理距离度量，最后给出了实验结果和分析。
关键词：人类视觉系统；特征提取；优化颜色构成距离；纹理距离度量；可控金字塔滤波分解

Nature scene image extraction method based on HVS
ZHUGE Zhenrong, XU Min
(College of Electrical Engineering, Zhejiang University, Hangzhou 310027, China)

Abstract: A nature scene image colortexture feature extraction method based on human visual system (HVS) was proposed. Two types of lowlevel image features color and texture feature extraction methods were introduced, and adaptive dominant colors principle described color features, spatial and frequency characterristic of texture grayscale component describes texture features, using adaptive clustering algorithm(ACA) to get adaptive dominant colors and steerable pyramid filter decomposition to extract texture features. Meanwhile, optimal colorcomposition distance (OCCD) and texture distance metric approach were also presented. Finally experiment results and analysis were given out.
Key words: human visual system (HVS); feature extraction; optimal color composition distancel (OCCD); texture distance metricl (TDM); streerable pyramid filter decomposition

参考文献(Reference)：
［1］PAPPAS T N. An adaptive clustering algorithm for image segmentation［J］. IEEE Trans. Signal Process,1992,40(4):901-914.
［2］MOJSILOVIC A, HU J, SOLJANIN E. Extraction of perceptually important colors and similarity measurement for image matching, retrieval, and analysis［J］. IEEE Trans Image Process,2002,11(11): 1238-1248.
［3］FREEMAN W T， ADELSON E H. The design and use of steerable filters［J］. IEEE Trans. Pattern Anal. Mach. Intell.,1991,13(9):891-906.
［4］SIMONCELLI E P, FREEMAN W T. The Steerable Pyramid: A Flexible Architecture for Multiscale Derivative Computation［C］//Proc. Int. Conf.Image Processing, vol III, Washington DC, 1995:444-447.
［5］CHEN Junqing, PAPPAS T N, MOJSILOVIC A, et al. Adaptive image segmentation based on color and texture［J］. IEEE Image Process,2002,3:777-780.
［6］COMANICIU D, MEER P. Robust Analysis of Feature Spaces: Color Image Segmentation［C］. Proc. IEEE Conf. Computer Vision and Pattern Recognition, San Juan, PR, 1997:750-755.