数字化可视人体图像的目标提取  

Background removal of visible digital images of human body

作　　者：宁旭[1] 张绍祥[2] 谭立文[2] 邱全光[2] 

机构地区：[1]第三军医大学基础医学部物理学教研室,重庆400038 [2]第三军医大学基础医学部人体解剖学教研室重庆市计算医学研究所,重庆400038

出　　处：《第三军医大学学报》2007年第16期1549-1551,共3页Journal of Third Military Medical University

基　　金：国家自然科学基金(60473128)~~

摘　　要：目的探讨数字化可视人体图像的目标提取。方法利用归一化阈值分割排除大部分背景,再结合边缘跟踪对目标边界附近保留的边缘特征进行识别、连接、去噪,构建一种准确、有效的目标提取算法。结果基于边缘和阈值混合的分割技术有效地去除了数字化人体图像的背景。结论通过与其他几种分割算法的比较,本计算法实际使用效果较好。Objective To study on how to remove the background in the digital images of visible human body. Methods After removing most of the background with standardized thresholds segmentation, we did identification, connection and noise-removing work against the edge around the target verge, and then the results of these two methods were combined to get the final image. Results Complex segmentation technology based on edge and thresholds effectively removed the background in the image of human body. Conclusion Compared with other segmentation algorithm, the algorithm presented here has better practical effect.

关 键 词：目标提取 图像分割 薄层断层解剖 

分 类 号：R319[医药卫生—基础医学] R322