基于改进MSR的小波变换图像增强算法

Wavelet Transform Image Enhancement Algorithm Based on Improved MSR

针对采集的触摸屏图片存在图片整体偏暗、对比度低,背景噪声较多,难以分割图像中缺陷的问题,提出一种基于改进MSR (多尺度Retinex滤波)的小波变换图像增强算法。该算法首先对图像进行小波分解,得到图像的低频分量使用以中值滤波模板代替高斯滤波模板的改进MSR处理以增强低频系数,对高频分量进行同态滤波以限制噪声,最后通过小波逆变换重建图像。本文将改进的算法应用于采集的触摸屏表面缺陷图片,通过VS2017软件进行仿真实验,并与同态滤波算法、MSR算法进行对比。实验结果表明,使用改进MSR算法提高了算法的运行速度,该算法优于传统的MSR算法,对图像的增强、噪声的抑制有良好的效果,改善了图像的整体视觉效果且大大缩短了算法的运行时间。

As for the problems existed in the Touch screen picture such as relatively dark image as a whole, low contrast, background noise interference and difficulties in segmenting the defects in image, a wavelet transform image enhancement algorithm based on improved Multi-Scale Retinex (MSR) is proposed. The algorithm first performs Wavelet Transform on image, does improved MSR using median filter template instead of Gaussian filter template on the low frequency component of image to enhance the low-frequency coefficient, finishes homomorphic Filter on the high frequency component to limit the noise, and finally reconstructs the image by inverse wavelet transform. This paper applies improved algorithm to image enhancement and carries out simulation experiments by using multiple images. The algorithm proposed in this paper is realized by VS2017 software programming and is compared with homomorphic filter algorithm and the MSR algorithm. The experimental results show that the use of the improved MSR algorithm improves the running speed of the algorithm. This algorithm is better than the HOMOMORPHIC filtering algorithm and MSR algorithm and has a good effect on image enhancement and noise suppression, improves the overall visual effect of the image and greatly shortens the running time of the algorithm.