Infrared temperature measurement has been already applied for online monitoring of electric power equipment. However, for the high noise and low contrast degree of infrared images produced by monitoring process, how to remove the noise of images effectively has become the key point of recent research. In this paper, we propose a new insulator infrared image denoising method using significant coefficient rule. In order to incorporate the spatial dependencies into the denoising procedure, HMT model is explored and EM algorithm is proposed to estimate model parameters. The experimental results show that, compared with the existing insulator infrared image denoising methods, the proposed method is not only propitious to keep image edge from damaging and solve the edge blurring problem, but also increasing PSNR of images. In addition, the proposed method also gets a better visual effect.
Research on Insulator Infrared Image Denoising Using Significant Wavelet-Domain Hidden Markov Tree Models
2008 Congress on Image and Signal Processing ; 3 ; 398-402
2008-05-01
552935 byte
Conference paper
Electronic Resource
English
Wavelet-based image denoising using contextual hidden Markov tree model
British Library Online Contents | 2005
|Multiscale fusion of wavelet-domain hidden Markov tree through graph cut
British Library Online Contents | 2009
|Process Trends Analysis Based on Wavelet-domain Hidden Markov Tree Model
British Library Online Contents | 2005
|Multivariate Statistical Models for Image Denoising in the Wavelet Domain
British Library Online Contents | 2007
|Research on Image Denoising Based on Wavelet Threshold
TIBKAT | 2021
|