吉林大学学报(工学版) ›› 2021, Vol. 51 ›› Issue (2): 712-719.doi: 10.13229/j.cnki.jdxbgxb20200839

• 计算机科学与技术 • 上一篇    

基于自适应阈值的Canny算法在MRI边缘检测中的应用

李健1,2(),刘孔宇1,任宪盛3(),熊琦1,窦雪峰1   

  1. 1.吉林农业大学 信息技术学院,长春 130118
    2.吉林大学 吉林省生物信息学研究中心,长春 130118
    3.吉林大学第二医院 骨科,长春 130041
  • 收稿日期:2020-11-02 出版日期:2021-03-01 发布日期:2021-02-09
  • 通讯作者: 任宪盛 E-mail:liemperor@163.com;antren@163.com
  • 作者简介:李健(1981-),男,副教授,博士生导师.研究方向:人工智能,图像处理.E-mail:liemperor@163.com
  • 基金资助:
    国家自然科学基金项目(41671397);吉林省教育厅“十三五”科学技术项目(JJKH20200329KJ);吉林省科技发展计划项目(20191001008XH);吉林省发改委产业技术研究与开发项目(2020C037-7)

Application of canny algorithm based on adaptive threshold in MR Image edge detection

Jian LI1,2(),Kong-yu LIU1,Xian-sheng REN3(),Qi XIONG1,Xue-feng DOU1   

  1. 1.College of Information Technology,Jilin Agricultural University,Changchun 130118,China
    2.Jilin Province Bioinformatics Research Center,Jilin University,Changchun 130118,China
    3.Department of Orthopedic Surgery,Second Hospital of Jilin University,Changchun 130041,China
  • Received:2020-11-02 Online:2021-03-01 Published:2021-02-09
  • Contact: Xian-sheng REN E-mail:liemperor@163.com;antren@163.com

摘要:

Canny算法作为一种经典的多级优化算法广泛应用于核磁共振成像(MRI)边缘检测中,MRI具有灰度密度不均一且对比度低的局限性,本文以腰椎间盘MRI为例提出一种改进的Canny算法在边缘检测中进行优化。首先增强图像对比度,在此基础上引入中值滤波有效处理脉冲噪声进行预处理;针对边缘提取精度不足的问题,增加梯度方向模板求取梯度幅值和方向;针对假边缘数量过多及边缘间断等问题,采用梯度强度信息计算法实现阈值自适应;最后通过直方图正规化再次进行图像增强。本文采用峰值信噪比、结构相似性、均方误差及算法运行时间四方面评价准则对传统算法、现有算法以及本文所改进的算法进行验证,结果表明:改进后的Canny算法对MRI检测精度明显提高且算法的自适应性更强,伪边缘有效减少,本文结果对MRI在医学图像处理中有一定的借鉴意义。

关键词: 图像处理, 边缘检测, Canny算法, 核磁共振成像

Abstract:

As a classic multi-level optimization algorithm, the Canny algorithm is widely used in MRI edge detection. MRI has the limitations of uneven gray density and low contrast. This paper uses lumbar disc MRI as an example to propose an improved Canny algorithm for optimization in edge detection. First, the image contrast is enhanced, and on this basis, the median filtering is introduced to effectively process impulse noise for preprocessing. Then, for the problem of insufficient edge extraction accuracy, the gradient direction template is increased to obtain the gradient amplitude and direction. For the excessive number of false edges and edge discontinuities, the gradient intensity information calculation method is used to achieve threshold adaptation. Finally, the image enhancement is performed again through the histogram normalization. This paper uses four evaluation criteria of PSNR, SSIM, MSE and algorithm running time to verify the traditional algorithm, the existing algorithm and the improved algorithm in this paper. The results show that the improved Canny algorithm significantly improves the accuracy of MRI detection, effectively reduces the false edges, and it is adaptive. The results of this article have certain reference significance for MRI in medical image processing.

Key words: image processing, edge detection, Canny algorithm, MR image

中图分类号: 

  • TP391.41

图1

Canny算法流程图"

图2

传统Canny算法边缘图"

图 3

改进后的Canny算法流程图"

图4

不同滤波的去噪结果图"

图5

不同的自适应阈值算法比较"

图6

传统Canny算法和本文算法边缘提取图"

图7

Gamma变换对比图"

图8

直方图正规化结果"

图9

传统算法和改进Canny算法的对比结果"

图10

本文算法与其他算法对比图"

表1

性能评价对比表"

算法

峰值信噪比

(PSNR)

均方误差

(MSE)

结构相似性

(SSIM)

运行时间/s
Sobel算子11.3523523.310.60000.364
Laplacian算子11.4284679.290.51000.342
Otsu12.2413715.310.44000.447
传统Canny11.0315128.440.43000.064
文献[1]11.3076058.410.49290.331
文献[19]10.5826250.430.43108.288
本文13.5682860.170.75000.196
1 李健, 李赫宇, 姚汝婧, 等. 基于均值滤波的改进Canny算法在核磁共振图像边缘检测中的应用[J]. 吉林大学学报: 工学版, 2016, 46(5): 1704-1709.
Li Jian, Li He-yu, Yao Ru-jing,et al. Application of improved canny algorithm based on mean filtering in MRI Image edge detection[J].Journal of Jilin University(Engineering and Technology Edition), 2016, 46(5): 1704-1709.
2 吴倩倩, 周蕾蕾, 赵紫婷, 等. 图像分割在肿瘤放射治疗中的发展与应用[C]∥中国医学装备协会, 北京, 2020: 44-48.
3 宋志刚, 王龙山, 陈向伟. 利用数字图像处理技术检测锥螺纹[J]. 吉林大学学报: 工学版, 2004, 34(2): 248-251.
Song Zhi-gang, Wang Long-shan, Chen Xiang-wei.Using digital image processing technology to detect taper thread[J].Journal of Jilin University(Engineering and Technology Edition), 2004,34(2): 248-251.
4 朱家明, 李祥健, 徐婷宜. 基于改进的双水平集的MRI图像快速分割方法[J]. 无线电通信技术, 2020, 46(3): 345-350.
Zhu Jia-ming, Li Xiang-jian, Xu Ting-yi. Fast MRI image segmentation method based on improved bilevel set [J]. Radio Communication Technology, 2020, 46(3): 345-350.
5 Zhang X F, Zhang Y, Zheng R. Image edge detection method of combining wavelet lift with Canny operator[J]. Procedia Engineering, 2011, 15: 1335-1339.
6 Biswas R, Sil J. An improved canny edge detection algorithm based on type-2 fuzzy sets[J]. Procedia Technology, 2012, 4: 820-824.
7 杨娉娉, 武林会, 米红妹, 等. 改进的3D Canny算子在MRI乳腺图像分析中的应用[J]. 计算机测量与控制, 2017, 25(9): 143-145, 149.
Yang Ping-ping,Wu Lin-hui,Mi Hong-mei,et al.Application of improved 3D Canny operator in MRI breast image analysis[J]. Computer Measurement and Ccontrol, 2017, 25(9): 143-145, 149.
8 Al-Hafiz F, Al-Megren S, Kurdi H. Red blood cell segmentation by thresholding and Canny detector[J].Procedia Computer Science, 2018, 141: 327-334.
9 Cao J F, Chen L C, Wang M, et al. Implementing a parallel image edge detection algorithm based on the otsu-canny operator on the hadoop platform[J]. Comput Intell Neurosci, 2018(1): 3598284.
10 Iqbal B, Iqbal W, Khan N, et al. Canny edge detection and Hough transform for high resolution video streams using Hadoop and Spark[J]. Cluster Computing, 2020, 23(1): 397-408.
11 梁辰, 张文博, 高鑫. 基于混合滤波器的改进Canny算子图像边缘检测[J]. 物联网技术, 2020, 10(7): 28-30.
Liang Chen, Zhang Wen-bo, Gao Xin. Improved Canny operator image edge detection based on hybrid filter[J]. Internet of Things Technology, 2020, 10(7): 28-30.
12 郑健, 王继, 宋世铭. Canny双阈值算子在边缘提取中的优势[J]. 地理空间信息, 2019, 17(11): 128-130, 12.
Zheng Jian, Wang Ji, Song Shi-ming. The advantages of Canny double threshold operator in edge extraction[J]. Geospatial Information, 2019, 17(11): 128-130, 12.
13 张震, 马驷良, 张忠波, 等. 一种改进的基于Canny算子的图像边缘提取算法[J]. 吉林大学学报: 理学版, 2007, 45(2): 244-248.
Zhang Zhen, Ma Si-liang, Zhang Zhong-bo, et al.An improved image edge extraction algorithm based on Canny operator[J]. Journal of Jilin University(Science Edition), 2007,45(2): 244-248.
14 孙金岭, 庞娟, 张泽龙. 基于颜色特征和改进Canny算子的车牌图像定位[J]. 吉林大学学报: 理学版, 2015, 53(4): 693-697.
Sun Jin-ling, Pang Juan, Zhang Ze-long. License plate image localization based on color features and improved Canny operator[J]. Journal of Jilin University(Science Edition), 2015,53(4):693-697.
15 鲁瑞华, 杨明. 一种基于中值滤波的非线性图像处理优化算法[J]. 计算机科学, 2004(11): 224-226.
Lu Rui-hua,Yang Ming.A nonlinear image processing optimization algorithm based on median filtering[J]. Computer Science, 2004(11): 224-226.
16 刘丽霞, 李宝文, 王阳萍, 等. 改进Canny边缘检测的遥感影像分割[J]. 计算机工程与应用, 2019, 55(12): 54-58, 180.
Liu Li-xia, Li Bao-wen, Wang Yang-ping, et al.Remote sensing image segmentation with improved Canny edge detection[J]. Computer Engineering and Applications, 2019, 55(12): 54-58, 180.
17 尹奎英, 刘宏伟, 金林. 快速的Otsu双阈值SAR图像分割法[J]. 吉林大学学报: 工学版, 2011, 41(6): 760-765.
Yin Kui-ying, Liu Hong-wei, Jin Lin. Fast Otsu dual-threshold SAR image segmentation method[J]. Journal of Jilin University(Engineering and Technology Edition), 2011, 41(6): 760-765.
18 Li Z, Jia Z H, Liu L Y, et al.A method to improve the accuracy of SAR image change detection by using an image enhancement method[J]. ISPRS Journal of Photogrammetry and Remote Sensing, 2020, 163: 137-151.
19 李健, 李俊杰, 任宪盛, 等. 一类基于二维线性插值函数的改进Canny算法[J]. 东北师大学报: 自然科学版, 2015, 47(4): 79-83.
Li Jian, Li Jun-jie, Ren Xian-sheng, et al. An improved Canny algorithm based on two-dimensional linear interpolation function[J]. Journal of Northeast Normal University(Natural Science), 2015, 47(4): 79-83.
[1] 刘富,刘璐,侯涛,刘云. 基于优化MSR的夜间道路图像增强方法[J]. 吉林大学学报(工学版), 2021, 51(1): 323-330.
[2] 刘哲, 徐涛, 宋余庆, 徐春艳. 基于NSCT变换和相似信息鲁棒主成分分析模型的图像融合技术[J]. 吉林大学学报(工学版), 2018, 48(5): 1614-1620.
[3] 车翔玖, 王利, 郭晓新. 基于多尺度特征融合的边界检测算法[J]. 吉林大学学报(工学版), 2018, 48(5): 1621-1628.
[4] 梁士利, 柴宗谦, 张玲, 吴颜生, 曹春雷. 基于偏X型细胞自动机的图像加密方法[J]. 吉林大学学报(工学版), 2017, 47(5): 1653-1660.
[5] 车翔玖, 张孙旻. 基于异步更新策略的蚁群边缘提取算法[J]. 吉林大学学报(工学版), 2017, 47(5): 1577-1582.
[6] 何光, 张铭, 袁双石. 微机电系统后坐保险机构温度相关动态特性[J]. 吉林大学学报(工学版), 2017, 47(1): 145-150.
[7] 颜飞, 周长久, 田彦涛. 用于目标定位的图像边缘点检测算法[J]. 吉林大学学报(工学版), 2016, 46(6): 2103-2110.
[8] 李健, 李赫宇, 姚汝婧, 吴林. 基于均值滤波的改进 Canny 算法在核磁共振图像边缘检测中的应用[J]. 吉林大学学报(工学版), 2016, 46(5): 1704-1709.
[9] 肖钟捷. 基于小波空间特征谱熵的数字图像识别[J]. 吉林大学学报(工学版), 2015, 45(6): 1994-1998.
[10] 韩成, 张超, 秦贵和, 薛耀红, 杨帆, 范静涛, 刘文静. 大型正交多幕投影系统光辐射补偿算法[J]. 吉林大学学报(工学版), 2015, 45(4): 1266-1273.
[11] 张文杰, 熊庆宇, 石为人, 陈舒涵. 基于邻域加权的多层次模糊边缘检测算法[J]. 吉林大学学报(工学版), 2015, 45(3): 998-1004.
[12] 刘长英1, 蔡文静1, 王天皓2, 李机智1, 贾艳梅1, 宋玉河1. 汽车连杆裂解槽视觉检测技术[J]. 吉林大学学报(工学版), 2014, 44(4): 1076-1080.
[13] 张金果,郭海涛,吴君鹏,李依桐. 改进的最小交叉Tsallis熵的小目标声呐图像分割[J]. 吉林大学学报(工学版), 2014, 44(3): 834-839.
[14] 赵宏伟, 陈霄, 龙曼丽, 裴士辉. 基于Riesz变换的图像边缘检测[J]. 吉林大学学报(工学版), 2013, 43(增刊1): 133-137.
[15] 黄德天, 刘雪超, 吴志勇, 梁敏华. 基于CameraLink的高速图像采集处理系统设计[J]. 吉林大学学报(工学版), 2013, 43(增刊1): 309-312.
Viewed
Full text


Abstract

Cited

  Shared   
  Discussed   
No Suggested Reading articles found!