| 627 | 24 | 31 |
| Downloads | Citas | Reads |
To solve the problem of complex background,weak boundary,and connectivity in plant image segmentation,an improved bi-convex fuzzy variational image segmentation model was proposed. Firstly,the color image was divided into two parts by RGB color space model. The target part of the plant image was kept in the original color. The other part was set to the color background with large difference from the target object. The extracted object contour was used as an initial contour. Secondly,the log edge detection operator was used to improve the robustness of noise,and performed the image enhancement on the plant image. Finally,a new segmentation model was proposed based on the blurring fuzzy variational model. The experimental results showed that the average JS value of the method was improved to95. 68%. The accurate extraction of edge contour of the target object in the rosette plant image was realized. It also effectively solved the problem of the complex background and the connectivity between pixels.
[1] WANG X H,WAN Y,LI R,et al. A multi-object image segmentation CV model based on region division and gradient guide[J]. Journal of visual communication and image representation,2016,39:100-106.
[2]刘洪普,杨乐,侯向丹,等.一种改进的模糊C均值图像分割算法[J].郑州大学学报(理学版),2017,49(2):66-71.
[3] CHAN T,VESE L. An active contour model without edges[C]∥Proceedings of the 2nd International Conference on Scale-space Theories in Computer Vision. London:Springer-Verlag,1999:141-151.
[4] ZHANG K H,ZHANG L,SONG H H,et al. Reinitialization-free level set evolution via reaction diffusion[J]. IEEE transactions on image processing,2013,22(1):258-271.
[5]田杰,胡秋霞,马孝义.基于高斯分布改进C-V模型的植物病斑彩色图像分割[J].农业工程学报,2013,29(16):166-173.
[6]王萍,王立地.自然场景下植物叶片图像分割方法研究[J].农业科技与装备,2011(2):48-51.
[7] GONG M G,TIAN D Y,SU L Z,et al. An efficient bi-convex fuzzy variational image segmentation method[J]. Information sciences,2015(293):351-369.
[8] ZHOU X W,HUANG X J,DUNCAN J S,et al. Active contours with group similarity[C]∥IEEE Conference on Computer Vision and Pattern Recognition. Oregon,2013:2969-2976.
[9] XIE X H. Active contouring based on gradient vector interaction and constrained level set diffusion[J]. IEEE transactions on image processing,2010,19(1):154-164.
[10] ORDEVIC'S S. A note on a multiplicative parameters gradient method[J]. Applied mathematics and computation,2016,283(20):90-107.
[11]王大凯,侯榆青,彭进业.图像处理的偏微分方程方法[M].北京:科学出版社,2008.
[12]罗志宏,冯国灿.一种新变分方法在图像分割中的应用[J].计算机科学,2011,38(12):263-265.
[13]蒋东升.基于数学形态学的边缘检测算法研究[D].成都:电子科技大学,2012.
[14] LI C M,KAO C Y,GORE J C,et al. Minimization of region-scalable fitting energy for image segmentation[J]. IEEE transactions on image processing,2008,17(10):1940-1949.
[15] SCHARR H,MINERVINI M,FISCHBACH A,et al. Annotated image datasets of rosette plants[R]. Forschungszentrum julich,(2014-07-08)[2017-09-16]. http:∥hdl. handle. net/2128/5848.
[16]元昌安,郑彦,覃晓,等.改进RSF主动轮廓模型的医学图像分割方法[J].郑州大学学报(理学版),2017,49(1):34-38.
[17] EVERINGHAM M,GOOL L V,WILLIAMS C K I,et al. The pascal visual object classes(VOC)challenge[J]. International journal of computer vision,2010,88(2):303-338.
Basic Information:
DOI：10.13705/j.issn.1671-6841.2018006
China Classification Code:TP391.41
Citation Information:
[1]LIU Guoqi,DENG Ming,LI Chenjing ,et al.Plant Image Segmentation Model Based on RGB Color Space[J].Journal of Zhengzhou University(Natural Science Edition),2019,51(01):18-23.DOI:10.13705/j.issn.1671-6841.2018006.
Fund Information:
国家自然科学基金项目(U1404603);; 河南省教育厅科学技术重点研究项目(13A520522)
2018-01-03
2018
2018-02-22
2018-03-01
2018
1
2018-04-27
2018-04-27
2018-04-27