中国组织工程研究

中国组织工程研究 ›› 2010, Vol. 14 ›› Issue (35): 6551-6554.doi: 10.3969/j.issn.1673-8225.2010.35.023

• 骨与关节图像与影像 bone and joint imaging • 上一篇    下一篇

基于灰度对比和自适应小波变换的X射线图像增强

师  黎，陈欣欣   

  1. 郑州大学电气工程学院，河南省郑州市  450001
  • 出版日期:2010-08-27 发布日期:2010-08-27
  • 作者简介:师黎☆，女，1964年生，河南省许昌市人，汉族，2007年上海大学毕业，博士，主要从事生物信息检测与智能处理的研究。 shili@zzu.edu.cn
  • 基金资助:

    国家自然科学基金项目(60841004)：基于基函数超完备集的动物视觉图像重构研究；国家自然科学基金项目(60971110)：初级视觉皮层中视像整体特征的稀疏表象模型的研究。

X-ray enhancement based on gray-contrast and adaptive wavelet transform 

Shi Li, Chen Xin-xin   

  1. School of Electrical Engineering, Zhengzhou University, Zhengzhou  450001, Henan Province, China
  • Online:2010-08-27 Published:2010-08-27
  • About author:Shi Li☆, Doctor, School of Electrical Engineering, Zhengzhou University, Zhengzhou 450001, Henan Province, China shili@zzu.edu.cn
  • Supported by:

    the National Natural Science Foundation of China, No. 60841004*, 60971110*

PDF

521

被引次数

3

摘要：

背景：X射线检查作为常规的检查方式得到了广泛的应用，然而由于现有技术的局限性，使得X射线图像往往具有灰度对比度低和噪声影响等缺点，因此，现有的X射线图像往往达不到医生的要求。
目的：增强和去噪处理对比度较低且含有噪声的X射线图像，以达到易于医生理解和识别的目的。
方法：针对空间域处理和变换域处理增强X射线图像的不足，提出了基于灰度对比和自适应小波变换的X射线图像增强算法。首先，选择需要增强和减弱的灰度范围，并根据八邻域灰度对比增强算法对X射线图像进行灰度变换，并用中值滤波算法对图像进行平滑；然后，对X射线图像进行小波分解，并运用相邻分解层之间相关系数的大小来确定细节信号和噪声。
结果与结论：应用了灰度对比和自适应小波变换相结合的X射线图像增强算法，把基于空间域增强的方法和基于变换域的方法有机地结合起来，比传统的单一增强方法更为优越。实验结果证明它能自适应地增强X射线图像的灰度对比，使得图像细节的显示更加清晰，同时在一定程度上去除了噪声的干扰，对于灰度对比度较低的图像效果更加明显。

关键词: 灰度对比, 图像增强, 小波变换, X射线, 噪声

Abstract:

BACKGROUND: As a routine way of checking, X-ray examination has been widely used, but because of the limitations of existing technology, X-ray images have disadvantages of low intensity contrast, and noise. Therefore, nowadays the X-ray images are often not meet medical requirements.
OBJECTIVE: To enhance and denoise X-ray images with low intensity contrast and noise, to achieve the purpose of medical understanding and recognition.
METHODS: Due to the shortage of image enhancement algorithm in the spatial domain and transform domain, an algorithm based on gray-contrast and adaptive wavelet transform was addressed. First, gray-scale ranges needed to strengthen or weaken were selected. The algorithm of eight neighborhood gray-scale contrast enhancement was used to enhance the X-ray image, and algorithm of median filtering was used to smooth the image. Second, the X-ray image was decomposed using wavelet decomposition algorithm, and the size of the correlation coefficients between adjacent layers were used to determine the details and noise of the image.
RESULTS AND CONCLUSION: The algorithm based on gray-contrast and adaptive wavelet transform integrates methods based on space domain enhancement or transform domain, which is better than enhancement method alone. The results show that this method achieved a good enhancement and denoising effect. Compared with the results of only contrast and modified the wavelet coefficients, this method obtains a better enhancement and denoising effect.

中图分类号: