一种改进的新型广义熵在图像分割中的应用
|
摘要
在图像分割中引入了一种能够通过参数r处理物理系统中附加信息或者非广义信息的新型广义熵,在此基础上提出了一种改进的新型广义熵分割算法,用粒子群算法在所有参数中搜索最优值,引入均匀性测度函数指标为适应度函数,从而实现参数的自适应选取,得出最佳分割阈值。结果表明,该方法可以实现以上内容。
A novel generalized entropy that can handle the additive/nonextensive information existed in image by parameterrwas been introduced in image segmentation.Based on this method,a new method of adaptively segmentation method was proposed,then use the uniformity measure function of image segmentation quality evaluation index as fitness function and the particle swarm optimization algorithm to search in parameter space,so that parameter can be adaptively selected according to the nature of the image to get the best segmentation threshold.The results show that this method can adaptively select parameters and obtain the better segmentation image.
A novel generalized entropy that can handle the additive/nonextensive information existed in image by parameterrwas been introduced in image segmentation.Based on this method,a new method of adaptively segmentation method was proposed,then use the uniformity measure function of image segmentation quality evaluation index as fitness function and the particle swarm optimization algorithm to search in parameter space,so that parameter can be adaptively selected according to the nature of the image to get the best segmentation threshold.The results show that this method can adaptively select parameters and obtain the better segmentation image.
引文
[1]宋亚玲.基于熵的图像阈值分割研究[D].泉州:华侨大学,2016.
[2]吴诗婳,吴一全,周建江,等.基于2维灰度熵阈值选取快速迭代的图像分割[J].中国图象图形学报,2015,20(8):1042-1050.
[3]ZHONG S.New Entropic Thresholding Approach Using Gray-level Spatial Correlation Histogram[J/OL].Optical Engineering,2010,49(12):1127-1134.
[4]王莹莹,何苹,魏彤,等.二维信息熵的红外图像分割算法[J].空军工程大学学报(自然科学版),2015,16(1):77-80.
[5]MASI M.A Step Beyond Tsallis and Rényi entropies[J/OL].Physics Letters A,2005,338(3):217-224.
[6]NIE F,ZHANG P,LI J,et al.A Novel Generalized Entropy and Its Application in Image Thresholding[J/OL].Signal Processing,2017,134(C):23-34.
[7]雷博,范九伦.一维Renyi熵阈值法中参数的自适应选取[J/OL].光子学报,2009,38(9):2439-2443.
[8]林爱英,李辉,吴莉莉,等.二维Tsallis熵阈值法中基于粒子群优化的参数选取[J/OL].郑州大学学报(理学版),2012,44(1):50-55.
[9]LIN Q,OU C.Tsallis Entropy and the Long-range Correlation in Image Thresholding[J/OL].Signal Processing,2012,92(12):2931-2939.
[10]IEEE OTCBVS WS Series Bench;Roland Miezianko,Terravic Research Infrared Database.August 16,2016.
[11]SARKAR S,DAS S,CHAUDHURI S S.Hyper-spectral Image Segmentation Using Rényi Entropy Based Multilevel Thresholding Aided with Differential Evolution[J/OL].Expert Systems with Applications,2016,50:120-129.
[2]吴诗婳,吴一全,周建江,等.基于2维灰度熵阈值选取快速迭代的图像分割[J].中国图象图形学报,2015,20(8):1042-1050.
[3]ZHONG S.New Entropic Thresholding Approach Using Gray-level Spatial Correlation Histogram[J/OL].Optical Engineering,2010,49(12):1127-1134.
[4]王莹莹,何苹,魏彤,等.二维信息熵的红外图像分割算法[J].空军工程大学学报(自然科学版),2015,16(1):77-80.
[5]MASI M.A Step Beyond Tsallis and Rényi entropies[J/OL].Physics Letters A,2005,338(3):217-224.
[6]NIE F,ZHANG P,LI J,et al.A Novel Generalized Entropy and Its Application in Image Thresholding[J/OL].Signal Processing,2017,134(C):23-34.
[7]雷博,范九伦.一维Renyi熵阈值法中参数的自适应选取[J/OL].光子学报,2009,38(9):2439-2443.
[8]林爱英,李辉,吴莉莉,等.二维Tsallis熵阈值法中基于粒子群优化的参数选取[J/OL].郑州大学学报(理学版),2012,44(1):50-55.
[9]LIN Q,OU C.Tsallis Entropy and the Long-range Correlation in Image Thresholding[J/OL].Signal Processing,2012,92(12):2931-2939.
[10]IEEE OTCBVS WS Series Bench;Roland Miezianko,Terravic Research Infrared Database.August 16,2016.
[11]SARKAR S,DAS S,CHAUDHURI S S.Hyper-spectral Image Segmentation Using Rényi Entropy Based Multilevel Thresholding Aided with Differential Evolution[J/OL].Expert Systems with Applications,2016,50:120-129.