基于小波分解灰关联的热波检测图像增强

针对热波检测图像存在的高噪声、低对比度等问题,提出一种基于小波分解和灰关联分析的图像增强方法。该方法首先采用小波变换对待处理的热波图像进行三级小波分解,得到图像相应的低频分量和高频分量,然后利用图像中干扰信号和有用信号在分解后不同分量上的分布规律,采用灰色理论中的灰色关联分析理论来区分高频分量中的干扰信号和有用信号,从而实现对图像中噪声的抑制以提高图像的质量。实验结果表明:提出的方法与常规的滤波方法、小波阈值去噪增强等方法相比,图像的对比度得到明显改善,峰值信噪比最大,因此该方法可用于热波检测图像的增强处理中。

Image enhancement of infrared thermal waving inspection based on thewavelet decomposition and grey relational analysis

To address problem thermal waving images with high noise and low contrast, a new image enhancement algorithm based on the wavelet decomposition and grey relational analysis was proposed in this paper. Firstly, the image was decomposed with three level wavelet decomposition by wavelet transform, and the low frequency and high frequency of image were obtained. Then the grey relational analysis of grey theory was employed to distinguish the interference signal from the useful signal in image based on the regularities of coefficient distribution of the signal and the noise in the image, and the image quality was improved by noise suppression. Results showed that the proposed algorithm was superior to most traditional spatial filters and wavelet threshold method in visual effect and the contrast, and the peak signal to noise ratio (PSNR) was most. This method could be applied to image enhancement of thermal waving images.