Please wait a minute...
Journal of Integrative Agriculture  2018, Vol. 17 Issue (08): 1800-1814    DOI: 10.1016/S2095-3119(18)61915-X
Special Issue: 智慧植保合辑Smart Plant Protection
Plant Protection Advanced Online Publication | Current Issue | Archive | Adv Search |
Automatic image segmentation method for cotton leaves with disease under natural environment
ZHANG Jian-hua1, KONG Fan-tao1, WU Jian-zhai1, HAN Shu-qing1, ZHAI Zhi-fen2 
1 Agricultural Information Institute, Chinese Academy of Agricultural Sciences/Key Laboratory of Agricultural Big Data, Ministry of Agriculture, Beijing 100081, P.R.China
2 Chinese Academy of Agricultural Engineering, Beijing 100125, P.R.China
Download:  PDF (31718KB) ( )  
Export:  BibTeX | EndNote (RIS)      
摘要  Received  25 July, 2017    Accepted  19 February, 2018
 

Abstract  
In order to improve the image segmentation performance of cotton leaves in natural environment, an automatic segmentation model of diseased leaf with active gradient and local information is proposed.  Firstly, a segmented monotone decreasing edge composite function is proposed to accelerate the evolution of the level set curve in the gradient smooth region.  Secondly, canny edge detection operator gradient is introduced into the model as the global information.  In the process of the evolution of the level set function, the guidance information of the energy function is used to guide the curve evolution according to the local information of the image, and the smooth contour curve is obtained.  And the main direction of the evolution of the level set curve is controlled according to the global gradient information, which effectively overcomes the local minima in the process of the evolution of the level set function.  Finally, the Heaviside function is introduced into the energy function to smooth the contours of the motion and to increase the penalty function ?(x) to calibrate the deviation of the level set function so that the level set is smooth and closed.  The results showed that the model of cotton leaf edge profile curve could be obtained in the model of cotton leaf covered by bare soil, straw mulching and plastic film mulching, and the ideal edge of the ROI could be realized when the light was not uniform.  In the complex background, the model can segment the leaves of the cotton with uneven illumination, shadow and weed background, and it is better to realize the ideal extraction of the edge of the blade.  Compared with the Geodesic Active Contour (GAC) algorithm, Chan-Vese (C-V) algorithm and Local Binary Fitting (LBF) algorithm, it is found that the model has the advantages of segmentation accuracy and running time when processing seven kinds of cotton disease leaves images, including uneven lighting, leaf disease spot blur, adhesive diseased leaf, shadow, complex background, unclear diseased leaf edges, and staggered condition.  This model can not only conduct image segmentation of cotton leaves under natural conditions, but also provide technical support for the accurate identification and diagnosis of cotton diseases.
Keywords:  local binary fitting model        natural environment        cotton        disease leaves        image segmentation  
Received: 25 July 2017   Accepted:
Fund: This work is supported by the National Natural Science Foundation of China (31501229), the Chinese Academy of Agricultural Sciences Innovation Project (CAAS-ASTIP-2017-AII), and the Special Research Funds for Basic Scientific Research in Central Public Welfare Research Institutes, China (JBYW-AII-2017-05).
Corresponding Authors:  Correspondence KONG Fan-tao, Tel: +86-10-82105507, Fax: +86-10-82106875, E-mail: kongfantao@caas.cn    
About author:  ZHANG Jian-hua, Tel: +86-10-82106590, E-mail: zhangjianhua@caas.cn;

Cite this article: 

ZHANG Jian-hua, KONG Fan-tao, WU Jian-zhai, HAN Shu-qing, ZHAI Zhi-fen. 2018. Automatic image segmentation method for cotton leaves with disease under natural environment. Journal of Integrative Agriculture, 17(08): 1800-1814.

Barbedo J G A. 2013. Digital image processing techniques for detecting, quantifying and classifying plant diseases. SpringerPlus, 2, 660–672.
Barbedo J G A. 2016. A review on the main challenges in automatic plant disease identification based on visible range images. Biosystems Engineering, 144, 52–60.
Barbedo J G A, Tibola C S, Fernandes J M C. 2015. Detecting Fusarium head blight in wheat kernels using hyperspectral imaging. Biosystems Engineering, 131, 65–76.
Bhogal A K, Singla N, Kaur M. 2011. Color image segmentation based on color and texture properties. International Journal of Advanced Engineering Sciences and Technologies, 8, 152–159.
Bhoyar K K, Kakde O G. 2010. Color image segmentation based on JND color histogram. International Journal of Image Processing, 3, 282–293.
Biswas R, Sil J. 2012. An improved Canny Edge detection algorithm based on Type-2 fuzzy sets. Procedia Technology, 4, 820–824.
Bock C H, Poole G H, Parker P E. 2010. Plant disease severity estimated visually, by digital photography and image analysis, and by hyperspectral imaging. Critical Reviews in Plant Sciences, 29, 59–107.
Brown E S, Chan T F, Bresson X. 2012. Completely convex formulation of the Chan-Vese image segmentation model. International Journal of Computer Vision, 98, 103–121.
Camargo A, Smith J S. 2009. An image-processing based algorithm to automatically identify plant disease visual symptoms. Biosystems Engineering, 102, 9–21.
Chan T, Vese L. 2001. Active contours without edges. IEEE Transactions on Image Processing, 10, 266–277.
Fang Z, Lu W, Lisi F. 2014. Segmentation method for cucumber disease leaf images under complex background. Acta Agriculturae Zhejiangensis, 26,1346–1355. (in Chinese)
Fu K, Gong C, Gu I, Yang J. 2015. Normalized cut-based saliency detection by adaptive multi-level region merging. IEEE Transactions on Image Processing, 24, 5671–5683.
Ilea D E, Whelan P F. 2011. Image segmentation based on the integration of colour-texture descriptors - A review. Pattern Recognition, 44, 2479–2501.
Jung M, Kang M. 2015. Effident nonsmooth noneoiwex optimization for image restoration and segmentation. Journal of Sdentific Computing, 65, 336–370.
Kruse O M O, Prats-Montalbán J M, Indahl U G. 2014. Pixel classification methods for identifying and quantifying leaf surface injury from digital images. Computers and Electronics in Agriculture, 108, 155–165.
Li C, Kao C Y, Gore J C. 2008. Minimization of region-scalable fitting energy for image segmentation. IEEE Transactions on Image Processing A Publication of the IEEE Signal Processing Society, 17, 1940–1949.
Li C, Kao C Y, Gore J C, Ding Z. 2007. Implicit active contours driven by local binary fitting energy. In: 2007 Computer Vision & Pattern Recognition. IEEE Conference, Minneapolis. pp. 1–7.
Liu T, Chen W, Wu W. 2016. Detection of aphids in wheat fields using a computer vision technique. Biosystems Engineering, 141, 82–93.
Phadikar S, Sil J, Das A K. 2013. Rice diseases classification using feature selection and rule generation techniques. Computers and Electronics in Agriculture, 90, 76–85.
Ren S, Lu H, Yuan P. 2016. Segmentation algorithm of cucumber leaf disease image based on saliency detection. Transactions of the Chinese Society of Agricultural Machinery, 47, 11–16.
Tian J, Han D, Hu Q. 2014. Segmentation of wheat rust lesion image using PCA and Gaussian mix model. Transactions of the Chinese Society of Agricultural Machinery, 45, 267–271.
Vese L A, Chan T F. 2002. A multiphase level set framework for image segmentation using the Mumford and Shah model. International Journal of Computer Vision, 50, 271–293.
Wang H. 2013. Cucumber image segmentation based on weighted connection coefficient pulse coupled neural network. Transactions of the Chinese Society of Agricultural Machinery, 44, 204–208.
Wang J, He J, Han Y. 2013. An adaptive thresholding algorithm of field leaf image. Computers and Electronics in Agriculture, 96, 23–39.
Wang N, Li X, Chen X H. 2010. Fast three-dimensional Otsu thresholding with shuffled frog-leaping algorithm. Pattern Recognition Letters, 31, 1809–1815.
Wang Z, Li H, Zhu Y. 2016. Review of plant identification based on image processing. Archives of Computational Methods in Engineering, 1, 1–18.
Wu N, Li M Chen S. 2014. Automatic segmentation of plant disease images based on graph cuts fusing multiple features. Transactions  of  the  Chinese  Society  of  Agricultural  Engineering, 30, 212–219.
Wu Y L, Zhao L, Jiang H Y. 2014. Image segmentation method for green crops using improved mean shift. Transactions of the Chinese Society of Agricultural Engineering, 30, 161–167.
Yuan Y, Li M, Chen S, Jiang H. 2013. Segmentation of cucumber leaf disease images with complex background. Transactions of the Chinese Society of Agricultural Machinery, 44, 233–237.
Zhang C, Tao Z, Wei X. 2015. A flexible framework of adaptive method selection for image saliency detection. Pattern Recognition Letters, 63, 66–70.
Zhang J H, Qi L J, Ji R H. 2012. Cotton diseases identification based on rough sets and BP neural network.Transactions of the Chinese Society of Agricultural Engineering, 28, 161–167.
Zhang W, Huang S, Wang J. 2015. A segmentation method for wheat leaf images with disease in complex background. Computer Engineering and Science, 37, 1349–1354.
Zheng L, Zhang J, Wang Q. 2009. Mean-shift-based color segmentation of images containing green vegetation. Computers and Electronics in Agriculture, 65, 93–98.
[1] Yunze Wen, Peng He, Xiaohan Bai, Huizhi Zhang, Yunfeng Zhang, Jianing Yu.

Strigolactones modulate cotton fiber elongation and secondary cell wall thickening [J]. >Journal of Integrative Agriculture, 2024, 23(6): 1850-1863.

[2] HE Peng, ZHANG Hui-zhi, ZHANG Li, JIANG Bin, XIAO Guang-hui, YU Jia-ning. The GhMAX2 gene regulates plant growth and fiber development in cotton[J]. >Journal of Integrative Agriculture, 2022, 21(6): 1563-1575.
[3] LUO Hong-hai, WANG Qiang, ZHANG Jie-kun, WANG Lei-shan, LI Ya-bing, YANG Guo-zheng.
One-time fertilization at first flowering improves lint yield and dry matter partitioning in late planted short-season cotton
[J]. >Journal of Integrative Agriculture, 2020, 19(2): 509-517.
[4] Maryam KOLAHI, Elham FAGHANI, Andrea GOLDSON-BARNABY, Borhan SOHRAB. Physiological traits and anatomic structures of the seed for two short cotton season genotypes (Gossypium hirsutum L.) under water stress[J]. >Journal of Integrative Agriculture, 2020, 19(1): 89-98.
[5] GUO Hui-hui, WU Jian-fei, CHEN Cui-xia, WANG Hong-mei, ZHAO Yun-lei, ZHANG Chao-jun, JIA Yin-hua, LIU Fang, NING Tang-yuan, CHU Zhao-hui, ZENG Fan-chang. Identification and characterization of cell cultures with various embryogenic/regenerative potential in cotton based on morphological, cytochemical, and cytogenetical assessment[J]. >Journal of Integrative Agriculture, 2019, 18(1): 1-8.
[6] ZHANG Shuai, LUO Jun-yu, WANG Li, WANG Chun-yi, Lü Li-min, ZHANG Li-juan, ZHU Xiang-zhen, CUI Jin-jie. The biotypes and host shifts of cotton-melon aphids Aphis gossypii in northern China[J]. >Journal of Integrative Agriculture, 2018, 17(09): 2066-2073.
[7] FAN Yin-jun, LI Fen, Abd Allah A. H. Mohammed, YI Xiao-qin, ZHANG Min, Nicolas Desneux, GAO Xi-wu. The damage risk evaluation of Aphis gossypii on wheat by host shift and fitness comparison in wheat and cotton[J]. >Journal of Integrative Agriculture, 2018, 17(03): 631-639.
[8] MA Guang-min, SHI Xue-yan, KANG Zhi-jiao, GAO Xi-wu. The influence of Tetranychus cinnabarinus-induced plant defense responses on Aphis gossypii development[J]. >Journal of Integrative Agriculture, 2018, 17(01): 164-172.
[9] ZHANG Xiao-bing, TANG Qiao-ling, WANG Xu-jing, WANG Zhi-xing. Development of glyphosate-tolerant transgenic cotton plants harboring the G2-aroA gene[J]. >Journal of Integrative Agriculture, 2017, 16(03): 551-558.
[10] MIN Wei, GUO Hui-juan, ZHANG Wen, ZHOU Guang-wei, MA Li-juan, YE Jun, HOU Zhen-an. Irrigation water salinity and N fertilization: Effects on ammonia oxidizer abundance, enzyme activity and cotton growth in a drip irrigated cotton fild[J]. >Journal of Integrative Agriculture, 2016, 15(05): 1121-1131.
No Suggested Reading articles found!