一种改进的基于峭度指标的FastICA算法

doi:10.7523/j.issn.2095-6134.2019.03.015

中国科学院大学学报 ›› 2019, Vol. 36 ›› Issue (3): 410-416.DOI: 10.7523/j.issn.2095-6134.2019.03.015

一种改进的基于峭度指标的FastICA算法

孟令博^1,2, 耿修瑞^1,2, 杨炜暾^1,2

1. 中国科学院电子学研究所中国科学院空间信息处理与应用系统技术重点实验室, 北京 100190;
2. 中国科学院大学, 北京 100049

收稿日期:2017-11-28 修回日期:2018-03-27 发布日期:2019-05-15
通讯作者: 耿修瑞
基金资助:
国家自然科学基金（41601402，41701539）资助

An improved FastICA algorithm based on kurtosis index

MENG Lingbo^1,2, GENG Xiurui^1,2, YANG Weitun^1,2

1. Key Laboratory of Technology in Geo-spatial Information Processing and Application System of CAS, Institute of Electronics, Chinese Academy of Sciences, Beijing 100190, China;
2. University of Chinese Academy of Sciences, Beijing 100190, China

Received:2017-11-28 Revised:2018-03-27 Published:2019-05-15

摘要/Abstract

摘要： 基于峭度指标的FastICA算法具有较快的收敛速度和较高的计算效率，被广泛应用于多光谱图像的特征提取。经典的FastICA算法基于固定点迭代法得到图像的各个独立成分，在迭代过程中，每一个独立成分的求解都需要所有像元的参与。因此，当数据量较大或图像中像元较多时，FastICA的计算量很大，此时它的速度优势就会大打折扣。遥感数据一般都具有较大的尺寸，因此如何将FastICA直接应用于遥感数据，是一个具有实际意义的问题。通过引入多光谱图像协峭度张量的概念，将FastICA的固定点迭代问题转化为代数形式的张量计算，避免每次迭代过程中需所有像元参与的缺陷，因而大大降低计算复杂度。多光谱图像实验结果表明，该算法明显快于传统的基于峭度指标的FastICA算法。

关键词: FastICA, 高阶统计特性, 峭度指标, 协峭度张量

Abstract: Independent component analysis (ICA) is a popular signal processing method based on the high-order statistical characteristics of data. It has been widely used in imagery processing. However, classical FastICA algorithm achieves independent components (ICs) of the data by the fixed-point iteration method. It needs cyclic iterations to get every IC, and in the iterative process the solution of each IC requires the participation of all pixels. Therefore, when the amount of data or the number of pixels is large, FastICA is time-consuming. At this point, its speed advantage is greatly reduced. The remote sensing data generally has a large size. So how to directly apply FastICA to remote sensing data is a practical problem. In this study, by introducing the cokurtosis tensor, the fixed point iteration problem of FastICA is transformed into tensor computation in algebraic form, and the participation of all pixels is avoided, thus greatly reducing the computational complexity. Experimental results for multispectral images show that the proposed algorithm is faster than the classical FastICA algorithm based on kurtosis.

Key words: FastICA, high order statistics, kurtosis index, cokurtosis tensor

中图分类号:

TN911.7

孟令博, 耿修瑞, 杨炜暾. 一种改进的基于峭度指标的FastICA算法[J]. 中国科学院大学学报, 2019, 36(3): 410-416.

MENG Lingbo, GENG Xiurui, YANG Weitun. An improved FastICA algorithm based on kurtosis index[J]. , 2019, 36(3): 410-416.

参考文献

[1] Castaldi F, Palombo A, Santini F, et al. Evaluation of the potential of the current and forthcoming multispectral and hyperspectral imagers to estimate soil texture and organic carbon[J]. Remote Sensing of Environment, 2016, 179:54-65.
[2] Tian Y, Guo P, Lyu M R. Comparative studies on feature extraction methods for multispectral remote sensing image classification[C]//Systems Man and Cybernetics. Waikoloa HI:IEEE, 2006:1275-1279.
[3] Kaur R, Sehgal S. Dimension reduction of multispectral data using canonical analysis[J]. International Journal of Computer Applications, 2014,70(21):18-21.
[4] Jaime Z, Ren J, Ren J. Structured covariance principal component analysis for real-time onsite feature extraction and dimensionality reduction in hyperspectral imaging[J]. Applied Optics, 2014, 53(20):4440-4449.
[5] Wold S, Esbensen K, Geladi P. Principal component analysis[J]. Chemometrics and Intelligent Laboratory Systems, 1987, 2(1):37-52.
[6] Green A A, Berman M, Switzer P, et al. A transformation for ordering multispectral data in terms of image quality with implications for noise removal[J]. IEEE Transactions on Geoscience and Remote Sensing, 1988, 26(1):65-74.
[7] Lee J B, Woodyatt A S, Berman M. Enhancement of high spectral resolution remote-sensing data by a noise-adjusted principal components transform[J]. IEEE Transactions on Geoscience and Remote Sensing, 1990, 28(3):295-304.
[8] Wang C, Zhang J, Gu Y. Target detection for hyperspectral images using ICA-based feature extraction[C]//Geoscience and Remote Sensing Symposium. Denver CO:IEEE, 2006:850-853.
[9] Ren H, Du Q, Wang J, et al. Automatic target recognition for hyperspectral imagery using high-order statistics[J]. IEEE Transactions on Aerospace and Electronic Systems, 2006, 42(4):1372-1385.
[10] Gu Y, Liu Y, Zhang Y. A selective KPCA algorithm based on high-order statistics for anomaly detection in hyperspectral imagery[J]. IEEE Geoscience and Remote Sensing Letters, 2008, 5(1):43-47.
[11] Wang N, Du B, Zhang L. An abundance caracteristic-based independent component analysis for hyperspectralunmixing[J]. IEEE Geoscience and Remote Sensing, 2015, 3(1):416-428.
[12] Wang J, Chang C. Applications of independent component analysis in endmember extraction and abundance quantification for hyperspectral imagery[J]. International Society for Optical Engineering, 2006, 44(9):2601-2616.
[13] Lennon M, Mercier G, Mouchot MC, et al. Independent component analysis as a tool for the dimensionality reduction and the representation of hyperspectral images[C]//Geoscience and Remote Sensing Symposium. Sydney NSW:IEEE, 2001, 6(3):2893-2895.
[14] Hyvarinen A, Oja E, Hoyer P, et al. Image feature extraction by sparse coding and Independent component analysis[C]//Pattern Recognition. Brisbane:IEEE, 1998, 2:1268-1273.
[15] Comon P. Independent component analysis, a new concept?[J]. Signal Processing, 1994, 36(3):287-314.
[16] Chen P, Hung H, Komori O, et al. Robust independent component analysis via minimum-divergence estimation[J]. IEEE Journal of Selected Topics in Signal Processing, 2013, 7(4):614-624.
[17] Shen H, Gretton A. Fast kernel-based independent component analysis[J]. IEEE Transactions on Signal Processing, 2009, 57(9):3498-3511.
[18] Karvanen J, Koivunen V. Independent component analysis via optimum combining of kurtosis and skewness-based criteria[J]. Journal of the Franklin Institute, 2004, 341(5):401-418.
[19] Hyvarinen A. Fast and robust fixed-point algorithms for independent component analysis[J]. IEEE Transactions on Neural Networks, 1999, 10(3):626-634.
[20] Hyvärinen A, Köster U. A fast fixed-point algorithm for independent component analysis[J]. Neural Computation, 1997, 9(7):1483-1492.

一种改进的基于峭度指标的FastICA算法

An improved FastICA algorithm based on kurtosis index

PDF (PC)

可视化

摘要/Abstract

引用本文

使用本文

参考文献

相关文章 15

编辑推荐

Metrics

本文评价

访问统计

联系我们

[1]	史达亨, 刘立刚, 周斌, 卜智勇. 跨时间迁移的多源无线信号指纹融合定位方法[J]. 中国科学院大学学报, 2021, 38(6): 817-824.
[2]	蔚瑞, 谢卓辰, 刘洁, 刘会杰. 基于图像超分辨重建的低轨卫星频谱感知数据空间分辨率提高方法^*[J]. 中国科学院大学学报, 0, (): 76-76.
[3]	李利, 尹增山, 石神. 联合L1和L0先验模型的超分辨率重建算法研究[J]. 中国科学院大学学报, 0, (): 21543-21543.
[4]	孙宇豪, 李国通, 张鸽. 一种基于相关概率模型的卫星异常检测方法[J]. 中国科学院大学学报, 2021, 38(3): 409-416.
[5]	孙晓丽, 郭艳, 李宁, 宋晓祥. 基于改进神经过程的缺失数据填充算法[J]. 中国科学院大学学报, 2021, 38(2): 280-287.
[6]	吴培培, 张旻, 史英春. 基于Duffing混沌振子的短波3G-ALE信号多通道检测方法[J]. 中国科学院大学学报, 2019, 36(6): 832-838.
[7]	贾志成, 王娜娜, 陈雷, 张艳. 基于非线性函数和简化粒子群优化的盲源分离算法[J]. 中国科学院大学学报, 2014, 31(4): 530-536.
[8]	王海军, 柳明, 张圣燕. 基于局部熵的融合局部和全局信息的主动轮廓模型[J]. 中国科学院大学学报, 2013, 30(6): 819-823.
[9]	温媛媛, 陈豪. 基于时域卷积盲信号分离的雷达干扰抑制算法[J]. 中国科学院大学学报, 2013, 30(4): 523-527.
[10]	桑睿, 吴杰, 许华, 郭强. 基于改进的遗传算法的后非线性盲源分离[J]. 中国科学院大学学报, 2012, 29(5): 707-713.
[11]	王璐, 张志敏. 基于改进SPIHT算法的SAR图像压缩[J]. 中国科学院大学学报, 2012, (2): 220-226.
[12]	樊计昌, 刘明军, 海燕. 三维Q值层析成像人机交互软件及其在地震数据处理中的应用[J]. 中国科学院大学学报, 2011, 28(4): 475-480.
[13]	汪赵华, 郭立, 李辉. 基于改进小波脊提取算法的数字信号瞬时频率估计方法[J]. 中国科学院大学学报, 2009, 26(4): 466-473.
[14]	沈怡平侯朝焕马晓川. 基于四阶累积量的CSPRIT算法[J]. 中国科学院大学学报, 2007, 24(3): 325-330.
[15]	陈鹏侯朝焕马晓川. 用于计算离散分数阶傅立叶变换的MA-CDFRFT算法改进[J]. 中国科学院大学学报, 2007, 24(2): 229-234.