基于改进K-means聚类算法的金鱼阴影去除及图像分割方法
|
摘要
针对鱼类行为量化过程中运动阴影区域去除难的问题,以金鱼为研究对象,分别从去除噪点及孤立数据点、使用马氏距离作为距离度量方法、明确聚类个数以及初始聚类中心点选择等方面对传统K-means聚类算法进行了优化,提出了一种基于改进K-means聚类算法的金鱼阴影去除及图像分割方法。在室内正常环境下,使用相机采集玻璃鱼缸中金鱼图像,首先等比例压缩10倍,使用中值滤波方法对样本图像进行预处理,然后将其从RGB颜色空间转换到Lab颜色空间,最后提取a、b分量并使用改进的K-means算法进行聚类。试验结果显示:和传统K-means聚类算法及FCM(Fuzzy c-means)聚类算法进行比较,改进算法对于图像阴影去除及分割具有更好的效果,在200幅具有不同阴影的金鱼样本图像中,基于改进K-means聚类算法的平均误分类的像素比率和平均运行时间分别为2.48%和0.87 5s,能够满足离线鱼类行为量化过程中图像预处理的要求。
Aiming at the difficulty in removing motion shadow regions in the process of fish behavior quantification,with goldfish as research object,the method of goldfish shadow removal and image segmentation based on improved K-means clustering algorithm is proposed to optimize traditional K-means clustering algorithm in such aspects as removing noisy points and isolated data points,using mahalanobis distance as distance measurement method,defining the number of clustering and choosing the initial clustering center.In the normal indoor environment,the camera is used to collect the images of goldfish in the glass fish tank.First,after 10 times of uniform compression,we use the median filtering method to preprocess the sample images,and then the sample images are converted from RGB color space to Lab color space.Finally,the components a and b are extracted and the improved K-means algorithm is used for clustering.The test results show that compared with the traditional K-means clustering algorithm and FCM(Fuzzy c-means) clustering algorithm,the improved algorithm has better effect on image shadow removal and segmentation.The average misclassification pixel ratio and the average running time based on improved K-means clustering algorithm are 2.48% and 0.875 s respectively in 200 goldfish sample images with different shadows,which can satisfy the requirement of image preprocessing in the process of off-line fish behavior quantification.
Aiming at the difficulty in removing motion shadow regions in the process of fish behavior quantification,with goldfish as research object,the method of goldfish shadow removal and image segmentation based on improved K-means clustering algorithm is proposed to optimize traditional K-means clustering algorithm in such aspects as removing noisy points and isolated data points,using mahalanobis distance as distance measurement method,defining the number of clustering and choosing the initial clustering center.In the normal indoor environment,the camera is used to collect the images of goldfish in the glass fish tank.First,after 10 times of uniform compression,we use the median filtering method to preprocess the sample images,and then the sample images are converted from RGB color space to Lab color space.Finally,the components a and b are extracted and the improved K-means algorithm is used for clustering.The test results show that compared with the traditional K-means clustering algorithm and FCM(Fuzzy c-means) clustering algorithm,the improved algorithm has better effect on image shadow removal and segmentation.The average misclassification pixel ratio and the average running time based on improved K-means clustering algorithm are 2.48% and 0.875 s respectively in 200 goldfish sample images with different shadows,which can satisfy the requirement of image preprocessing in the process of off-line fish behavior quantification.
引文
[1] 徐建瑜,崔绍荣,苗香雯,等.计算机视觉技术在水产养殖中的应用与展望[J].农业工程学报,2005,21(8):174-178.
[2] CUCCHIARA R,GRANA C,PICCARDI M,et al.Improving shadow suppression in moving object detection with HSV color information[C]//Proceedings of 2001 IEEE Intelligent Transportation Systems.IEEE,2001:334-339.
[3] 徐少飞,刘政怡.基于颜色属性的车辆阴影去除方法[J].计算机应用与软件,2016,33(9):203-207.
[4] SUN B,LI S.Moving cast shadow detection of vehicle using combined color models[C]//2010 Chinese Conference on Pattern Recognition(CCPR).IEEE,2010:1-5.
[5] LEONE A,DISTANTE C,BUCCOLIERI F.Shadow detection for moving objects based on texture analysis[J].Pattern Recognition,2007,9(6):1222-1233.
[6] 郭春凤,何建农.彩色与纹理不变性的阴影消除新算法[J].图形、图像与多媒体,2013,32(5):38-41,45.
[7] 曹健,陈红倩,张凯,等.结合区域颜色和纹理的运动阴影检测方法[J].机器人,2011,33(5):628-633.
[8] ROCHA A,HAUAGGE D C,WAINER J,et al.Automatic fruit and vegetable classification from images[J].Computers and Electronics in Agriculture,2010,70(1):96-104.
[9] 巨志勇,李开亮,毛颖颖.基于K-means聚类与二次分水岭的果蔬图像分割方法[J].软件导刊,2018,17(6):217-223.
[10]龚劬,廖武忠,卢力,等.基于图论的快速FCM图像分割算法[J].计算机工程,2012,38(8):192-197.
[11]吴迪,刘伟峰,胡胜,等.基于Lab空间的K均值聚类彩色图像分割[J].电子科技,2017,30(10):29-32.
[12]谢永华,陈庆为,梁娇娇.基于改进K-means聚类的木材缺陷彩色图像分割算法研究[J].现代科学仪器,2014(3):197-207.
[13]吴庆岗,张卫国,李灿林,等.自然环境下基于Lab空间的成熟苹果图像分割[J].江苏农业科学,2017,45(9):177-179.
[14]邹秋霞,杨林楠,彭琳,等.基于Lab空间和K-Means聚类的叶片分割算法研究[J].农机化研究,2015(9):222-226.
[15]吕金娜.基于LAB空间和自适应聚类的害虫图像分割方法[J].河南科技学院学报(自然科学版),2016,44(1):57-61.
[16]郭晶晶,李庆武,程海粟,等.基于Lab颜色距离和GMM的树木图像分割算法[J].信息技术,2016(2):1-4.
[17] HE S,LIU Z,WANG L.Color calibration and color management in digital camera[C]// Future Communication,Computing,Control and Management.Springer Berlin Heidelberg,2012:579-585.
[18]王海丰,任洪娥,张鲲.基于Lab颜色空间的竹材横端面提取算法研究[J].新型工业化,2014,4(9):44-49.
[19]王礼,方陆明,陈珣,等.基于Lab颜色空间的花朵图像分割算法[J].浙江万里学院学报,2018,31(3):67-73.
[20]刘义红.一种改进的K-means聚类算法自然图像分割算法设计与实现[J].淮南师范学院学报,2018,20(2):120-125.
[21]任恒怡,贺松,陈文亮.一种改进的K-means聚类算法在图像分割中的应用[J].通信技术,2017,50(12):2704-2707.
[22]HAMIL P,GIORDANO M,WARD C,et al.An AERONET-based aerosol classification using the Mahalanobis distance [J].Atmospheric Environment,2016,140,213-233.
[23]许子杰,任光亮.基于马氏距离的相位噪声抑制算法[J].华中科技大学学报(自然科学版),2017,45(4):112-115.
[24]ALLAN M,ADRI?O D,JORGE D,et al.A new clustering separation measure based on negentropy [J].Journal of Control,Automation and Electrical Systems,20015,26(1):28-45.
[25]李金涛,艾萍,岳兆新,等.基于K-means聚类算法的改进[J].理论与方法,2017,36(6):9-21.
[2] CUCCHIARA R,GRANA C,PICCARDI M,et al.Improving shadow suppression in moving object detection with HSV color information[C]//Proceedings of 2001 IEEE Intelligent Transportation Systems.IEEE,2001:334-339.
[3] 徐少飞,刘政怡.基于颜色属性的车辆阴影去除方法[J].计算机应用与软件,2016,33(9):203-207.
[4] SUN B,LI S.Moving cast shadow detection of vehicle using combined color models[C]//2010 Chinese Conference on Pattern Recognition(CCPR).IEEE,2010:1-5.
[5] LEONE A,DISTANTE C,BUCCOLIERI F.Shadow detection for moving objects based on texture analysis[J].Pattern Recognition,2007,9(6):1222-1233.
[6] 郭春凤,何建农.彩色与纹理不变性的阴影消除新算法[J].图形、图像与多媒体,2013,32(5):38-41,45.
[7] 曹健,陈红倩,张凯,等.结合区域颜色和纹理的运动阴影检测方法[J].机器人,2011,33(5):628-633.
[8] ROCHA A,HAUAGGE D C,WAINER J,et al.Automatic fruit and vegetable classification from images[J].Computers and Electronics in Agriculture,2010,70(1):96-104.
[9] 巨志勇,李开亮,毛颖颖.基于K-means聚类与二次分水岭的果蔬图像分割方法[J].软件导刊,2018,17(6):217-223.
[10]龚劬,廖武忠,卢力,等.基于图论的快速FCM图像分割算法[J].计算机工程,2012,38(8):192-197.
[11]吴迪,刘伟峰,胡胜,等.基于Lab空间的K均值聚类彩色图像分割[J].电子科技,2017,30(10):29-32.
[12]谢永华,陈庆为,梁娇娇.基于改进K-means聚类的木材缺陷彩色图像分割算法研究[J].现代科学仪器,2014(3):197-207.
[13]吴庆岗,张卫国,李灿林,等.自然环境下基于Lab空间的成熟苹果图像分割[J].江苏农业科学,2017,45(9):177-179.
[14]邹秋霞,杨林楠,彭琳,等.基于Lab空间和K-Means聚类的叶片分割算法研究[J].农机化研究,2015(9):222-226.
[15]吕金娜.基于LAB空间和自适应聚类的害虫图像分割方法[J].河南科技学院学报(自然科学版),2016,44(1):57-61.
[16]郭晶晶,李庆武,程海粟,等.基于Lab颜色距离和GMM的树木图像分割算法[J].信息技术,2016(2):1-4.
[17] HE S,LIU Z,WANG L.Color calibration and color management in digital camera[C]// Future Communication,Computing,Control and Management.Springer Berlin Heidelberg,2012:579-585.
[18]王海丰,任洪娥,张鲲.基于Lab颜色空间的竹材横端面提取算法研究[J].新型工业化,2014,4(9):44-49.
[19]王礼,方陆明,陈珣,等.基于Lab颜色空间的花朵图像分割算法[J].浙江万里学院学报,2018,31(3):67-73.
[20]刘义红.一种改进的K-means聚类算法自然图像分割算法设计与实现[J].淮南师范学院学报,2018,20(2):120-125.
[21]任恒怡,贺松,陈文亮.一种改进的K-means聚类算法在图像分割中的应用[J].通信技术,2017,50(12):2704-2707.
[22]HAMIL P,GIORDANO M,WARD C,et al.An AERONET-based aerosol classification using the Mahalanobis distance [J].Atmospheric Environment,2016,140,213-233.
[23]许子杰,任光亮.基于马氏距离的相位噪声抑制算法[J].华中科技大学学报(自然科学版),2017,45(4):112-115.
[24]ALLAN M,ADRI?O D,JORGE D,et al.A new clustering separation measure based on negentropy [J].Journal of Control,Automation and Electrical Systems,20015,26(1):28-45.
[25]李金涛,艾萍,岳兆新,等.基于K-means聚类算法的改进[J].理论与方法,2017,36(6):9-21.