正在加载图片...
童何俊等:基于免疫遗传形态学的视网膜光学相干断层图像边缘检测方法 ·545· 表3多种边界提取方法与专家结果量化平均相对误差比较(以面积为例) Table 3 Comparison of the average relative errors determined by multiple boundary extraction methods and expert results (as an example of area) 边界提取方法 Single_3 Single_5 Multi Canny GTDP IGM IGSM ARE 0.0383 0.1586 0.0303 0.0751 0.6385 0.0241 0.0256 [6]Babu K R,Sunitha K V N.Image de-noising and enhancement for 5结论 salt and pepper noise using genetic algorithm-morphological opera- (1)针对采用单一结构元素无法实现多种形态 tions.Int J Signal Image Process,2013.4(1):36 ] Erccal T,Ozcan E,Asta S.Soft morphological filter optimization 目标的提取,和传统形态学结构元素形态单调固定 using a genetic algorithm for noise elimination /Proceedings of 的问题,本文借鉴生物免疫抗体与抗原间作用机理, 2014 14th UK Workshop on Computational Intelligence.Bradford, 利用免疫遗传算法来实现形态学结构元素根据图像 2014:1 本身信息的自适应改变 [8] Jiang D H,Hua G.Research on image enhancement method based (2)利用自适应生成的结构元素对视网膜OCT on adaptive immune genetic algorithm.J Comput Theor Nanosci 2015,12(1):119 图像进行形态学边缘检测滤波,实现目标边界提取. [9 Chen L A,Zhang P M.Realization of immune genetic algorithm in 通过与传统形态学方法,边缘检测算子,图理论等多 MATLAB.J Fuzhou Univ Nat Sci,2004,32(5)554 种方法的仿真对比,本文算法分割结果的Part品质 (陈丽安,张培铭.免疫遗传算法在MATLAB环境中的实现 因数和平均相对误差都是最优的,证明了算法在图 福州大学学报(自然科学版),2004,32(5):554) 像边界提取中的有效性 [10]Liu Y N,Zhang G C,An J.Noise-resistance in color image edge detection based on flexible morphology.J Lanzhou Unie Nat Sci, (3)在提取视网膜边界的基础上,本文还对眼 2016,52(1):135 科医师所关注的视网膜组织厚度和面积特征进行了 (刘燕妮,张贵仓,安静。基于柔性形态学的抗噪彩色图像 量化提取,为后续的计算机辅助诊断提供数值参考. 边缘检测.兰州大学学报(自然科学版),2016,52(1): 135) 参考文献 [11]Bhima K,Jagan A.Analysis of MRI based brain tumor identifi- Haralick R M,Stemnberg S R,Zhuang X H.Image analysis using cation using segmentation technique /Proceedings of 2016 Inter- mathematical morphology.IEEE Trans Pattern Anal Mach Intell, national Conference on Communication and Signal Processing. 1987,9(4):532 Melmaruvathur,2016:2109 Liu Y L.Gui Z G.Adaptive image enhancement algorithm with 12] Michikawa T,Suzuki H,Moriguchi M,et al.Automatic extrac- variable weighted matching based on morphology.J Electron In- tion of endocranial surfaces from CT images of crania.PloS One, form Technol,2014,36(6):1285 2017,12(4):c0168516 (刘艳莉,桂志国.基于形态学的可变权值匹配自适应图像增 [13]Xu D L,Tan R Q,Ding Q,et al.Screening ocular fundus mac- 强算法.电子与信息学报,2014,36(6):1285) ular diseases with OCT.Clin J Chin Med,2016,8(32):123 B]Zhou S B,Shen A Q,LiG F.Concrete image segmentation based (徐黛丽,谭荣强,丁琼,等.眼底黄斑部疾病筛查中OCT on multiscale mathematic morphology operators and Otsu method. 的应用.中医临床研究,2016,8(32):123) Ade Mater Sci Eng,2015,2015(11):208473 14]Li Y J,Zhang J W,Wang M N.Improved BM3D denoising 4]Lee S H,Lee C.Multiscale morphology based illumination nor- method.IET Image Process,2017,11(12)1197 malization with enhanced local textures for face recognition.Expert [15]Chiu S J,Allingham M J,Mettu P S,et al.Kernel regression Syst Appl,2016,62:347 based segmentation of optical coherence tomography images with [5]Wang JG.Gao D Y.Improved morphological TOP-HAT filter op- diabetic macular edema.Biomed Opt Exp,2015,6(4):1172 timized with genetic algorithm /Proceedings of the 2009 2nd In- [16]Fu D M,Tong H J,Zheng S,et al.Retinal status analysis meth- ternational Congress on Image and Signal Processing (CISP). od based on feature extraction and quantitative grading in OCT Tianjin,2009:1 images.Biomed Eng Online,2016,15(1):87童何俊等: 基于免疫遗传形态学的视网膜光学相干断层图像边缘检测方法 表 3 多种边界提取方法与专家结果量化平均相对误差比较( 以面积为例) Table 3 Comparison of the average relative errors determined by multiple boundary extraction methods and expert results ( as an example of area) 边界提取方法 Single_3 Single_5 Multi Canny GTDP IGM IGSM ARE 0. 0383 0. 1586 0. 0303 0. 0751 0. 6385 0. 0241 0. 0256 5 结论 ( 1) 针对采用单一结构元素无法实现多种形态 目标的提取,和传统形态学结构元素形态单调固定 的问题,本文借鉴生物免疫抗体与抗原间作用机理, 利用免疫遗传算法来实现形态学结构元素根据图像 本身信息的自适应改变. ( 2) 利用自适应生成的结构元素对视网膜 OCT 图像进行形态学边缘检测滤波,实现目标边界提取. 通过与传统形态学方法,边缘检测算子,图理论等多 种方法的仿真对比,本文算法分割结果的 Partt 品质 因数和平均相对误差都是最优的,证明了算法在图 像边界提取中的有效性. ( 3) 在提取视网膜边界的基础上,本文还对眼 科医师所关注的视网膜组织厚度和面积特征进行了 量化提取,为后续的计算机辅助诊断提供数值参考. 参 考 文 献 [1] Haralick R M,Sternberg S R,Zhuang X H. Image analysis using mathematical morphology. IEEE Trans Pattern Anal Mach Intell, 1987,9( 4) : 532 [2] Liu Y L,Gui Z G. Adaptive image enhancement algorithm with variable weighted matching based on morphology. J Electron In￾form Technol,2014,36( 6) : 1285 ( 刘艳莉,桂志国. 基于形态学的可变权值匹配自适应图像增 强算法. 电子与信息学报,2014,36( 6) : 1285) [3] Zhou S B,Shen A Q,Li G F. Concrete image segmentation based on multiscale mathematic morphology operators and Otsu method. Adv Mater Sci Eng,2015,2015( 11) : 208473 [4] Lee S H,Lee C. Multiscale morphology based illumination nor￾malization with enhanced local textures for face recognition. Expert Syst Appl,2016,62: 347 [5] Wang J G,Gao D Y. Improved morphological TOP--HAT filter op￾timized with genetic algorithm / / Proceedings of the 2009 2nd In￾ternational Congress on Image and Signal Processing ( CISP) . Tianjin,2009: 1 [6] Babu K R,Sunitha K V N. Image de-noising and enhancement for salt and pepper noise using genetic algorithm-morphological opera￾tions. Int J Signal Image Process,2013,4( 1) : 36 [7] Ercal T,zcan E,Asta S. Soft morphological filter optimization using a genetic algorithm for noise elimination / / Proceedings of 2014 14th UK Workshop on Computational Intelligence. Bradford, 2014: 1 [8] Jiang D H,Hua G. Research on image enhancement method based on adaptive immune genetic algorithm. J Comput Theor Nanosci, 2015,12( 1) : 119 [9] Chen L A,Zhang P M. Realization of immune genetic algorithm in MATLAB. J Fuzhou Univ Nat Sci,2004,32( 5) : 554 ( 陈丽安,张培铭. 免疫遗传算法在 MATLAB 环境中的实现. 福州大学学报( 自然科学版) ,2004,32( 5) : 554) [10] Liu Y N,Zhang G C,An J. Noise-resistance in color image edge detection based on flexible morphology. J Lanzhou Univ Nat Sci, 2016,52( 1) : 135 ( 刘燕妮,张贵仓,安静. 基于柔性形态学的抗噪彩色图像 边缘检测. 兰 州 大 学 学 报( 自 然 科 学 版) ,2016,52 ( 1 ) : 135) [11] Bhima K,Jagan A. Analysis of MRI based brain tumor identifi￾cation using segmentation technique / / Proceedings of 2016 Inter￾national Conference on Communication and Signal Processing. Melmaruvathur,2016: 2109 [12] Michikawa T,Suzuki H,Moriguchi M,et al. Automatic extrac￾tion of endocranial surfaces from CT images of crania. PloS One, 2017,12( 4) : e0168516 [13] Xu D L,Tan R Q,Ding Q,et al. Screening ocular fundus mac￾ular diseases with OCT. Clin J Chin Med,2016,8( 32) : 123 ( 徐黛丽,谭荣强,丁琼,等. 眼底黄斑部疾病筛查中 OCT 的应用. 中医临床研究,2016,8( 32) : 123) [14] Li Y J,Zhang J W,Wang M N. Improved BM3D denoising method. IET Image Process,2017,11( 12) : 1197 [15] Chiu S J,Allingham M J,Mettu P S,et al. Kernel regression based segmentation of optical coherence tomography images with diabetic macular edema. Biomed Opt Exp,2015,6( 4) : 1172 [16] Fu D M,Tong H J,Zheng S,et al. Retinal status analysis meth￾od based on feature extraction and quantitative grading in OCT images. Biomed Eng Online,2016,15( 1) : 87 · 545 ·
<<向上翻页
©2008-现在 cucdc.com 高等教育资讯网 版权所有