多尺度形态梯度和标记分水岭的时频谱图分割  

Time-Frequency Spectrogram Segmentation Using the Multi-Scale Morphological Gradient and the Marked Watershed Algorithm

作　　者：郭海涛[1,2] 徐雷[3] 赵红叶[3] 田原嫄[4] 焦圣喜[3] 

机构地区：[1]内蒙古大学电子信息工程学院,内蒙古呼和浩特010021 [2]东北电力大学电气工程学院,吉林吉林132012 [3]东北电力大学自动化工程学院,吉林吉林132012 [4]东北电力大学机械工程学院,吉林吉林132012

出　　处：《吉首大学学报（自然科学版）》2015年第4期12-17,共6页Journal of Jishou University(Natural Sciences Edition)

基　　金：国家自然科学基金资助项目(41076060);吉林省自然科学基金资助项目(20130101056JC);内蒙古自然科学基金资助项目(2014MS0601);内蒙古大学高层次人才引进科研项目(135123)

摘　　要：时频谱图干扰强,目标之间、目标与干扰之间有重叠,其分割是重要而困难的问题.提出一种基于图像熵定义的时频谱图多尺度形态梯度图像融合方法,将该方法与标记分水岭分割结合形成一种基于多尺度形态梯度和标记分水岭的时频谱图分割方法.实验结果表明,与基于单尺度形态梯度和标记分水岭的分割方法相比,新方法实用性更强;与Otsu法相比,新方法分割更准确.It is important and difficult to segment a time-frequency spectrogram due to its strong interference as well as serious overlap among targets and between targets and interference .An image entropy based fusion method for multi-scale morphological gradient image of a time-frequency spectrogram is presented .By combining that method with the marked watershed algorithm ,a method for segmenting time-frequency spectrogram based on the multi-scale morphological gradient image and the marked wa-tershed algorithm ,is obtained .The experiment results show that it is more practical than the segmentation method which is based on single scale morphological gradient and marker watershed ,and more accurate than Otsu method .

关 键 词：时频谱图 多尺度梯度图像 图像熵 水岭算法 图像分割 

分 类 号：TP391.4[自动化与计算机技术—计算机应用技术]