基于多尺度Retinex的数字X光图像增强方法研究

提出了基于多尺度Retinex(MSR)方法的医学数字X光图像增强处理方法,论述了该算法的原理及实现方法。在3种标准偏差下,求得高斯滤波系数;然后使用3种不同的高斯滤波系数对X光图像进行卷积操作,将3种标准偏差尺度下得到的结果进行加权平均;最后将输出灰度值进行增益映射,得到可用于显示的结果。试验结果表明:MSR算法既可实现低对比的数字X光图像增强,又能实现图像的动态范围压缩,可显著提高暗区数字X光图像的信息。将该方法与几种常用图像增强方法进行了分析比较,表明MSR算法使得X光图像具有更好的灰度分布,能够显著提高暗区图像的信息量,其增强后的信息熵是常规增强方法的2倍,表现出了优良的性能。该方法克服了目前常规的数字X光图像增强方法的不足,能够满足医生临床诊断的要求。

Enhancement of radiography based multiscale Retinex

An enhancement algorithm of radiography based on multiscale Retinex was presented. The three different Gaussian filter coefficients under three different deviations were calculated, and the convolution operation was implemented between the image distribution and Gaussian filters, a weighted average of multiscale was gained and mapped to gray range of display device. With this method, image contrast enhancement, sharpening and dynamic range compression were achieved at the same time. The information of hidden area of digital radiograph was obviously enhanced. The enhancement technique was compared with other techniques such as histogram equalization, homomorphic filter. The results of experiment show that MSR can more observably improve entropy of digital X-rays than other techniques, and also show that the algorithm can overcome the lack of enhancement of traditional digital X-rays methods and satisfy the clinic demand.