基于改进的最大类间方差法的水果图像识别研究
|
摘要
针对水果自动识别过程中特征信息提取不完整的问题,本文提出一种基于改进的最大类间方差法OTSU对水果图像进行分割。通过对图像中值滤波处理降低随机噪声的干扰,增大目标图像和背景之间像素值与最佳分割阈值之间的差值,使目标图像与背景图像与各自类间中心的距离尽可能相近,达到相对方差取代绝对方差实现图像分割,然后对目标图像提取颜色特征和形状特征实现不同种类的水果图像识别。实验结果表明,改进后的OTSU所得阈值能分割到更加清晰的图像,图像分割的运行时间明显缩短,水果图像识别的平均正确识别率提高了15%左右。该研究提高了水果识别的效率,具有一定的实际应用价值。
In view of solving the problem of incomplete feature information extraction in fruits recognition,this paper proposes an improved OTSU method to segment fruit images.First,the image processing median filtering is used to reduce the interference of random noise,and then increase the difference between target and background pixels and the best segmentation threshold,at the same time let the target image and background image with the two respective distance between center as close as possible,and finally achieve relative variance instead of absolute variance to achieve image segmentation.After image segmentation,color features and shape features of target images are extracted to complete image recognition of different kinds of fruits.The experimental results show that the threshold obtained by the improved OTSU can obtain clearer segmentation images.Meanwhile,the running time of the improved OTSU algorithm for image segmentation is significantly shortened,and the average correct recognition rate of fruit image recognition is increased by about 15%.This study improves the efficiency of fruit identification and has certain practical application value.
In view of solving the problem of incomplete feature information extraction in fruits recognition,this paper proposes an improved OTSU method to segment fruit images.First,the image processing median filtering is used to reduce the interference of random noise,and then increase the difference between target and background pixels and the best segmentation threshold,at the same time let the target image and background image with the two respective distance between center as close as possible,and finally achieve relative variance instead of absolute variance to achieve image segmentation.After image segmentation,color features and shape features of target images are extracted to complete image recognition of different kinds of fruits.The experimental results show that the threshold obtained by the improved OTSU can obtain clearer segmentation images.Meanwhile,the running time of the improved OTSU algorithm for image segmentation is significantly shortened,and the average correct recognition rate of fruit image recognition is increased by about 15%.This study improves the efficiency of fruit identification and has certain practical application value.
引文
[1]赵玲,周桂红.基于颜色特征的草莓成熟度识别技术研究[J].河北农业大学报,2017,40(2):97-101.
[2]王履程,谭筠梅,王小鹏,等.基于机器视觉的枸杞分级方法[J].计算机工程与应用,2013,49(24):16-18.
[3]李大华,赵相飞,许亮,等.基于纹理特征与HSI空间的苹果识别与标定[J].图学学报,2016,37(5):688-693.
[4]伍艳莲,赵力,姜海燕,等.基于改进均值漂移算法的绿色作物图像分割方法[J].农业工程学报,2014,32(24):161-167.
[5]赵胜男,王文剑.融合SVM和快速均值漂移的图像分割算法[J].小型微型计算机系统,2017,38(7):1614-1618.
[6]卫洪春.基于改进神经网络的图像边缘分割技术[J].现代电子技术,2018,41(16):112-115.
[7]冈萨雷斯.数字图像处理的MATLAB实现[M].阮秋奇等,译.2版.北京:电子工业出版社,2003.
[8]郭臻,陈远知.图像阈值分割算法研究[J].中国传媒大学学报:自然科学版,2008,15(2):77-82.
[9] Otsu N.A threshold selection method from gray-level histograms[J].IEEE Transaction on Systems,Man and Cybernetics,1979,9(1):62-66.
[10]张乾,冯夫健,林鑫,等.一种基于图论的图像分割算法[J].计算机工程,2012,38(18):194-197.
[11]李敏,罗洪艳,郑小林.等.一种改进的最大类间方差图像分割法[J].南京理工大学学报:自然科学版,2012,36(2):332-337.
[12]史佳晨,钱建平.一种改进的中值滤波算法的研究[J].电气电子教学学报,2010,32(2):43-45.
[13]曲杨,许卫东,杨骏堂,等.基于边缘信息和Otsu的红外图像分割方法[J].指挥控制与仿真,2017,39(6):130-133.
[14]周迪,夏哲雷.一种改进的Otsu阈值分割算法[J].中国计量学院学报,2016,27(3):319-323,344.
[15]张铮,倪红霞,苑春苗,等.精通Matlab数字图像处理与识别[M].北京:人民邮电出版社,2018.
[16]姚敏.数字图像处理[M].2版.北京:机械工程出版社,2015.
[17] Wang X H,Huang W,Jin C,et al.Fruit recognition based on multi-feature and multi-decision[C]∥2014IEEE 3rd International Conference on Cloud Computing and Intelligence Systems.Shenzhen,China,IEEE,2014:113-117.
[18]王飞云.图像识别在水果分类中的应用研究[D].南京:东南大学,2014.
[19]杜晓晨,张幸,陆国权.基于图像处理的甘薯种类识别方法研究[J].中国粮油学报,2014,29(11):118-122,128.
[20]霍志林,吴洪潭,华享,等.灰度共生矩阵在蔬菜种类识别中的应用研究[J].中国计量学院学报,2015,26(1):105-109.
[2]王履程,谭筠梅,王小鹏,等.基于机器视觉的枸杞分级方法[J].计算机工程与应用,2013,49(24):16-18.
[3]李大华,赵相飞,许亮,等.基于纹理特征与HSI空间的苹果识别与标定[J].图学学报,2016,37(5):688-693.
[4]伍艳莲,赵力,姜海燕,等.基于改进均值漂移算法的绿色作物图像分割方法[J].农业工程学报,2014,32(24):161-167.
[5]赵胜男,王文剑.融合SVM和快速均值漂移的图像分割算法[J].小型微型计算机系统,2017,38(7):1614-1618.
[6]卫洪春.基于改进神经网络的图像边缘分割技术[J].现代电子技术,2018,41(16):112-115.
[7]冈萨雷斯.数字图像处理的MATLAB实现[M].阮秋奇等,译.2版.北京:电子工业出版社,2003.
[8]郭臻,陈远知.图像阈值分割算法研究[J].中国传媒大学学报:自然科学版,2008,15(2):77-82.
[9] Otsu N.A threshold selection method from gray-level histograms[J].IEEE Transaction on Systems,Man and Cybernetics,1979,9(1):62-66.
[10]张乾,冯夫健,林鑫,等.一种基于图论的图像分割算法[J].计算机工程,2012,38(18):194-197.
[11]李敏,罗洪艳,郑小林.等.一种改进的最大类间方差图像分割法[J].南京理工大学学报:自然科学版,2012,36(2):332-337.
[12]史佳晨,钱建平.一种改进的中值滤波算法的研究[J].电气电子教学学报,2010,32(2):43-45.
[13]曲杨,许卫东,杨骏堂,等.基于边缘信息和Otsu的红外图像分割方法[J].指挥控制与仿真,2017,39(6):130-133.
[14]周迪,夏哲雷.一种改进的Otsu阈值分割算法[J].中国计量学院学报,2016,27(3):319-323,344.
[15]张铮,倪红霞,苑春苗,等.精通Matlab数字图像处理与识别[M].北京:人民邮电出版社,2018.
[16]姚敏.数字图像处理[M].2版.北京:机械工程出版社,2015.
[17] Wang X H,Huang W,Jin C,et al.Fruit recognition based on multi-feature and multi-decision[C]∥2014IEEE 3rd International Conference on Cloud Computing and Intelligence Systems.Shenzhen,China,IEEE,2014:113-117.
[18]王飞云.图像识别在水果分类中的应用研究[D].南京:东南大学,2014.
[19]杜晓晨,张幸,陆国权.基于图像处理的甘薯种类识别方法研究[J].中国粮油学报,2014,29(11):118-122,128.
[20]霍志林,吴洪潭,华享,等.灰度共生矩阵在蔬菜种类识别中的应用研究[J].中国计量学院学报,2015,26(1):105-109.
© 2004-2018 中国地质图书馆版权所有 京ICP备05064691号 京公网安备11010802017129号 地址：北京市海淀区学院路29号 邮编：100083 电话：办公室：(+86 10)66554848；文献借阅、咨询服务、科技查新：66554700 |