多尺度形态梯度和标记分水岭的时频谱图分割

doi:10.3969/j.cnki.jdxb.2015.04.004

journal6 ›› 2015, Vol. 36 ›› Issue (4): 12-17.DOI: 10.3969/j.cnki.jdxb.2015.04.004

多尺度形态梯度和标记分水岭的时频谱图分割

郭海涛，徐雷，赵红叶，田原嫄，焦圣喜

（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）

出版日期:2015-07-25 发布日期:2015-07-27
作者简介:郭海涛（1965—），男，黑龙江安达人，内蒙古大学电子信息工程学院教授，博士，主要从事图像处理、模式识别等研究.
基金资助:
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）

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

GUO Hai-Tao, XU Lei, ZHAO Hong-Ye, TIAN Yuan-Yuan, JIAO Sheng-Xi

(1.College of Electronic Information Engineering，Inner Mongolia University，Hohhot 010021，China;2.Electrical Engineering College，Northeast Dianli University，Jilin 132012，Jilin China;3.School of Automation Engineering，Northeast Dianli University，Jilin 132012，Jilin China;4.School of Mechanical Engineering，Northeast Dianli University，Jilin 132012，Jilin China)

Online:2015-07-25 Published:2015-07-27

摘要/Abstract

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.

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

Abstract: 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 watershed 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.

Key words: time-frequency spectrogram, multi-scale morphological gradient image, image entropy, watershed algorithm, image segmentation

郭海涛, 徐雷, 赵红叶, 田原嫄, 焦圣喜. 多尺度形态梯度和标记分水岭的时频谱图分割[J]. journal6, 2015, 36(4): 12-17.

GUO Hai-Tao, XU Lei, ZHAO Hong-Ye, TIAN Yuan-Yuan, JIAO Sheng-Xi. Time-Frequency Spectrogram Segmentation Using the Multi-Scale Morphological Gradient and the Marked Watershed Algorithm[J]. journal6, 2015, 36(4): 12-17.

参考文献

[1] 蔡艳平，李艾华，王涛，等.基于时频谱图与图像分割的柴油机故障诊断[J].内燃机学报，2011，29（2）:181-186.

[2] GAVROVSKA A M，PASKAS M P，DUJKOVIC D，et al.Region-Based Phonocardiogram Event Segmentation in Spectrogram Image[C].IEEE:The 10th Symposium on Neural Network Applications in Electrical Engineering，2010:69-72.

[3] GAVROVSKA A M，PASKA M P，RELJIN I S.Determination of Morphologically Characteristic PCG Segments from Spectrogram Image[J].Telfor Journal，2010，2(2):4-77.

[4] SHAFI I，AHMAD J，SHAH S I，et al.Time Frequency Image Analysis Using Neural Networks[C].IEEE:IMACS Multiconference on Computational Engineering in Systems Applications，2006:315-320.

[5] LEPRETTRE B，MARTIN N.Extraction of Pertinent Subsets from Time-Frequency Representations for Detection and Recognition Purposes[J].Signal Processing，2002，82(2):229-238.

[6] STEINBERG R，O’SHAUGHNESSY D.Segmentation of a Speech Spectrogram Using Mathematical Morphology[C].IEEE:IEEE International Conference on Acoustics，Speech and Signal Processing，2008:1 637 -1 640.

[7] YUWONO M，SU S W，MOULTON B D，et al.Gait Cycle Spectrogram Analysis Using a Torso-Attached Inertial Sensor[C].IEEE:Annual International Conference of the IEEE Engineering in Medicine and Biology Society，2012:6 539-6 542.

[8] OZA A，CANAGARAJAH N，BULL D.Region Feature-Based Segmentation of Time-Frequency Images[C].Poznan，Poland:The 11th International Workshop on Systems，Signals and Image Processing，2004:375-378.

[9] ZHANG Zhenggang，XU Kailiang，TA Dean，et al.Joint Spectrogram Segmentation and Ridge-Extraction Method for Separating Multimodal Guided Waves in Long Bones[J].Science China-Physics，Mechanics and Astronomy，2013，56(7):1 317-1 323.

[10] MUKHOPADHYAY S，CHANDA B.An Edge Preserving Noise Smoothing Technique Using Multiscale Morphology[J].Signal Processing，2002，82:527-544.

[11] WANG D.A Multiscale Gradient Algorithm for Image Segmentation Using Watersheds[J].Pattern Recognition，1997，30(12):2 043-2 052.

[12] SALEMBIER P.Morphological Multiscale Segmentation for Image Coding[J].Signal Processing，1994，38(3):359-386.

[13] VINCENT L，SOILLE P.Watersheds in Digital Spaces:An Efficient Algorithm Based on Immersion Simulations[J].IEEE Transactions on Pattern Analysis and Machine Intelligence，1991，13(6):583-598.

[14] PUN T，KAPUR J N，WESZKA J S.Entropic Thresholding:A New Approach[J].Computer Vision，Graphics and Image Processing，1981，16(3):210-239.

[15] WU Qiang，MERCHANT F A，CASTLEMAN K R.Microscope Image Processing[M].Waltham，Massachusetts:Academic Press Elsevier，2008:135-142.

[16] SOILLE P.Morphological Image Analysis:Principle and Applications[M].New York:Springer-Verlag，2003.

[17] LEPRETTRE B，MARTIN N.Extraction of Pertinent Subsets from Time-Frequency Representations for Detection and Recognition Purposes[J].Signal Processing，2002，82(2):229-238.

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

PDF (PC)

可视化

摘要/Abstract

引用本文

使用本文

参考文献

相关文章 5

编辑推荐

Metrics

本文评价

[1]	郭海涛, 赵红叶, 徐雷, 侯一民, 焦圣喜. 多分辨分析和K均值聚类改进FCM图像分割[J]. journal6, 2015, 36(2): 29-32.
[2]	张小琴, 余列, 李懿. 基于PCNN模型的生物细胞图像分割[J]. journal6, 2014, 35(1): 46-49.
[3]	张小琴, 李懿, 鲜雪梅, 郝葆青. 尿沉渣细胞图像的预处理和分割研究综述[J]. journal6, 2012, 33(4): 49-52.
[4]	陈炳权, 刘宏立, 孟凡斌. 数字图像处理技术的现状及其发展方向[J]. journal6, 2009, 30(1): 63-70.
[5]	樊晓兵. 基于小波变换的弱小目标检测[J]. journal6, 2008, 29(1): 75-78.