Zhu Wei, Liu Jian, Zhu Mingyue, Shao Qin, Yan Yu
Affiliated Hospital Nanjing University of TCM(Jiangsu Province Hospital of TCM), Nanjing, 210029.
Biomedical Engineering Department, Nanjing Medical University, Nanjing, 210029.
Zhongguo Yi Liao Qi Xie Za Zhi. 2019 Jan 30;43(1):10-13. doi: 10.3969/j.issn.1671-7104.2019.01.003.
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.
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.
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.
The results show that the improved algorithm is superior to the traditional algorithm in terms of image enhancement.
为了从数字X线摄影（DR）图像中获取更多决策信息，基于高斯-拉普拉斯金字塔算法提出一种改进的图像增强算法。
在人类视觉特性和更好增强效果的基础上对原算法进行改进，对图像的低频分量进行直方图均衡化以使图像灰度更加平衡，对高频分量采用分层指数增强以使图像细节更清晰。
改进算法提高了胸部、骨盆和脊柱DR图像的对比度，使图像更具层次感，获得了良好的图像增强效果。
结果表明，改进算法在图像增强方面优于传统算法。
