摘要
目的研究一种红外医学图像处理与分析方法,实现红外人脸图像中特征区域的自动定位。方法针对红外正面脸部图像,采用一种无监督的局部和全局的特征提取方法,首先通过阈值法区分出前景和背景,并根据面部特征对称性在前景中确定鼻区;然后在面部确定一个包含所有特征的矩形区域,利用Harris算子在该区域检测出角点,并找出这些点的局部最大值点;最后用K-means方法对这些点进行聚类。结果100幅临床图像的实验表明,该方法可实现红外人脸图像中眼、鼻、口的自动定位,并能够准确划分脸部的特征区域。结论本文所建立的图像分析方法可快速、简捷地实现红外图像面部特征自动定位,且重复性较好、可信度较高。
Objective To develop an image analyzing procedure for automatic localization of facial features on infrared images, Methods An unsupervised local and global features extraction method was adopted for the localization of facial features of frontal view face image. First, a threshold was used to segment the image into foreground and background, and the nose was localized by considering the symmetry of the face, Second, Harris operator was adopted to detect interest points in a rectangular area covering all the facial features, and then local maximum of the interest points were detected. And finally, K-means clustering method was used to cluster the points and obtain the facial features localization. Results The experimental result of 100 images demonstrated that the procedure could automatically localize eyes, nose, mouth, and distinguish the feature areas. Conclusion The proposed infrared image analyzing procedure based on Harris operator and K-means clustering can be used to locate facial features on infrared image more rapidly and reliablely.
出处
《航天医学与医学工程》
CAS
CSCD
北大核心
2007年第4期285-288,共4页
Space Medicine & Medical Engineering
基金
国家"十一五"科技支撑项目(2006BAI03A19)
