基于ICA的近红外图像去噪方法的研究与应用.pdfVIP

25 卷 22 期 中 国 电 机 工 程 学 报 Vol.25 No.22 Nov. 2005 2005 年11 月 Proceedings of the CSEE 2005 Chin.Soc.for Elec.Eng. 文章编号：0258-8013 （2005 ）22-0094-05 中图分类号：TM711 文献标识码：A 学科分类号：47040 基于独立分量分析的近红外图像 去噪方法的研究与应用 1 1 1 2 强 ，赵振兵 ，李 然 ，俞晓雯 （⒈华北电力大学电子与通信工程系，河北省保定市 071003； ⒉福建省厦门市电业局，福建省 厦门市 361004 ） RESEARCH AND ITS APPLICATION OF A METHOD OF NEAR-INFRARED IMAGE DE-NOISING BASED ON ICA GAO Qiang, ZHAO Zhen-bing, LI Ran, YU Xiao-wen ( ⒈Department of Electronic and Telecommunication Engineering, North China Electric Power University, Baoding 071003, Hebei Province, China; ⒉Xiamen Electric Industrial Bureau, Xiamen 361004, Fuji an Province, China) ABSTRACT Independent component analysis (ICA) is a new 法可以有效的去除监测图像中的噪声，使温度场的显示更清 approach of blind source separation. In recent years, it has 晰，满足了实际的需求。 received considerable attention from the signal processing 关键词 独立分量分析；近红外图像去噪；黑白电荷耦合器 community and the neural network community. A method of 件传感器；电力设备；在线监测 near-infrared image de-noising based on ICA is presented in this paper. It can process availably images in monitoring power 1 引言 equipments by using monochrome CCD sensor, and it has practical significance. The on-line monitoring system with a 在电力系统中，保证供电系统的安全、稳定、 monochrome CCD sensor as the key device is described. The 可靠运行是电力管理的根