基于高斯-拉普拉斯金字塔的DR图像增强改进算法研究

Research on Improved Algorithm of DR Image Enhancement Based on Gauss-Laplacian Pyramid

目的为从数字X线成像(Digital Radiography,DR)图像中获取更多的诊断决策信息,在传统高斯-拉普拉斯金字塔算法的基础上提出了改进。方法在基于人眼视觉特性及获得更好细节增强效果的基础上,对图像低频分量采用直方图均衡使图像灰度显示更加均衡,对图像高频分量采用分层指数增强使图像细节更加清晰。结果改进算法提高了胸部、盆腔和脊椎等部位的DR图像的对比度,使图像更有层次感,获得了良好的图像增强效果。结论实现结果表明,该算法的增强效果优于传统高斯-拉普拉斯金字塔算法。

Objective In order to obtain more decision information from Digital Radiography(DR) images, an improved image enhancement algorithm is proposed based on the algorithm of Gauss-Laplacian pyramid. Methods The original algorithm is improved on the basis of the human visual characteristics and better enhancements, the low frequency components of the image is histogram equalized to make the image gray scale more balanced, and the high frequency component is enhanced by a hierarchical exponential enhancement to make the details of the image clearer. Results The improved algorithm improves the contrast of DR images in chest, pelvic and spine, and makes the image more layered and obtains good image enhancement effect. Conclusion The results show that the improved algorithm is superior to the traditional algorithm in terms of image enhancement.