面向小目标图像的快速核密度估计图像阈值分割算法

王骏; 王士同; 邓赵红; 应文豪

doi:10.3724/SP.J.1004.2012.01679

面向小目标图像的快速核密度估计图像阈值分割算法

doi: 10.3724/SP.J.1004.2012.01679

1.
江南大学数字媒体学院无锡 214122

详细信息

通讯作者:
王骏

计量
- 文章访问数: 1853
- HTML全文浏览量: 81
- PDF下载量: 1942
- 被引次数: 0
出版历程
- 收稿日期: 2011-05-05
- 修回日期: 2011-07-16
- 刊出日期: 2012-10-20

Fast Kernel Density Estimator Based Image Thresholding Algorithm for Small Target Images

1.
School of Digital Media, Jiangnan University, Wuxi 214122

摘要

摘要: 针对当前小目标图像阈值分割研究工作面临的难题,提出了快速核密度估计图像阈值分割新方法.首先给出了基于加权核密度估计器的概率计算模型,通过引入二阶Renyi熵作为阈值选取准则,提出了基于核密度估计的图像阈值分割算法 (Kernel density estimator based image thresholding algorithm, KDET), 然后通过引入快速压缩集密度估计 (Fast reduced set density estimator, FRSDE)技术,得到核密度估计的稀疏权系数表示形式,提出快速核密度估计图像阈值分割算法fastKDET,并从理论上对相关性质进行了深入探讨.实验表明,本文算法对小目标图像阈值分割问题具有更广泛的适应性,并且对参数变化不敏感.
- 核密度估计 /
- 快速压缩集密度估计 /
- 阈值分割 /
- 小目标图像
Abstract: In order to threshold the image containing small targets well, a novel fast kernel density estimator based image thresholding algorithm is proposed. Firstly, a novel computation model for probability density estimation based on the kernel density estimator with weighting coefficients is presented. By introducing the 2nd-order Renyi entropy as the threshold selection criterion, a novel kernel density estimator based image thresholding algorithm (KDET) is proposed. Then a fast version for KDET, named fastKDET, is proposed by integrating fast reduced set density estimator (FRSDE) and RSDE into the data condensation procedure. Moreover, some fundamental theoretical properties are fully studied. At last, several experiments are conducted and show that our fastKDET is more general than some of the existing algorithms and is insensitive to the parameters.
- Kernel density estimation /
- fast reduced set density estimator (FRSDE) /
- image thresholding /
- small target image

HTML全文

参考文献(1)

[1]

Sezgin M, Sankur B. Survey over image thresholding techniques and quantitative performance evaluation. Journal of Electronic Imaging, 2004, 13(1): 146-165[2] Li Zuo-Yong. Research on Image Thresholding Methods Based on Statistic and Spectral Graph [Ph.D. dissertation], Nanjing University of Science and Technology, China, 2010(李佐勇. 基于统计和谱图的图像阈值分割方法研究 [博士学位论文], 南京理工大学, 中国, 2010)[3] Otsu N. A threshold selection method from gray-level histograms. IEEE Transactions on Systems, Man, and Cybernetics, 1979, 9(1): 62-66[4] Hou Z, Hu Q, Nowinski W L. On minimum variance thresholding. Pattern Recognition Letters, 2006, 27(14): 1732-1743[5] Ng H F. Automatic thresholding for defect detection. Pattern Recognition Letter, 2006, 27(14): 1644-1649[6] Li Z Y, Liu C C, Liu G H, Yang X B, Cheng Y. Statistical thresholding method for infrared images. Pattern Analysis and Applications, 14(2): 109-126[7] Tao Wen-Bing, Jin Hai. A new image thresholding method based on graph spectral theory. Chinese Journal of Computers, 2007, 30(1): 110-119(陶文兵, 金海. 一种新的基于图谱理论的图像阈值分割方法. 计算机学报, 2007, 30(1): 110-119)[8] Girolami M, Chao H. Probability density estimation from optimally condensed data samples. IEEE Transactions on Pattern Analysis and Machine Intelligence, 2003, 25(10): 1253-1264[9] Torkkola K. Feature extraction by non parametric mutual information maximization. Journal of Machine Learning Research, 2003, 3: 1415-1438[10] Deng Z H, Chung F L, Wang S T. FRSDE: Fast reduced set density estimator using minimal enclosing ball approximation. Pattern Recognition, 2008, 41(4): 1363-1372[11] Wang S T, Chung F L, Xiong F S. A novel image thresholding method based on Parzen window estimate. Pattern Recognition, 2008, 41(1): 117-129[12] Pal N R. On minimum cross-entropy thresholding. Pattern Recognition, 1996, 29(4): 575-580[13] Yasnoff W A, Mui J K, Bacus J W. Error measures for scene segmentation. Pattern Recognition, 1997, 9(4): 217-231

施引文献

资源附件(0)

访问统计