基于Curvelet变换的X射线图像增强  

X-ray Image Enhancement Based on Curvelet Transform

作　　者：杨振亚[1,2] 陈裕泉[1] 潘敏[1] 

机构地区：[1]浙江大学生物医学工程系,杭州310027 [2]湖南工业大学电气与信息工程学院,株洲412008

出　　处：《计算机科学》2010年第3期275-277,共3页Computer Science

基　　金：国家"十一五"科技支撑计划项目(2006BAD30B03)资助

摘　　要：针对传统X-射线图像增强方法中图像细节不够清晰或噪声增强过大的问题,基于数学定义严谨的多尺度几何分析方法Curvelet变换,给出了一种灵活的非线性增强函数。首先,对X-射线图像进行Curvelet分解,然后在各精细尺度上对系数按增强函数进行映射,最后根据修正后的Curvelet系数重建图像。实验表明,根据所给定的增强函数,Curvelet变换能有效增强X-射线图像边缘对比度,细节清晰,噪声小,与传统方法比较,具有更好的视觉效果。Traditional X-ray image enhancement methods have the problem that enhanced image detail is not clear enough or too much noisy. Based on rigorous mathematical defined multi-scale geometric analysis method, Curvelet transform, a flexible non-linear enhancement function was presented. First of all, Curvelet transform was applied to the X-ray image, then, the fine Curvelet coefficients were mapped by the presented enhancement function, and finally the enhancement X-ray image was reconstructed from the amended Curvelet coefficients. The experiment results show that the Curvelet transform can effectively enhance the X-ray image edge contrast by presented enhancement function. The enhanced X-image has better visual effects with clear edge details and smaller noise compared with the traditional methods.

关 键 词：图像增强 CURVELET变换 多尺度几何分析 X-射线图像 

分 类 号：TP391.41[自动化与计算机技术—计算机应用技术]