FOREX Press I. J. of Electrical & Electronics Research
Support Open Access
  • Home/
  • IJEER-100326

Research Article |

Directional Shape Feature Extraction Using Modified Line Filter Technique for Weed Classification

Author(s): Seri Mastura Mustaza1, Mohd Faisal Ibrahim2, Mohd Hairi Mohd Zaman3, Noraishikin Zulkarnain4, Nasharuddin Zainal5 and Mohd Marzuki Mustafa6

Published In : International Journal of Electrical and Electronics Research (IJEER)        Volume 10, Issue 3

Publisher : FOREX Publication

Published : 07 September 2022

e-ISSN : 2347-470X

Page(s) : 564-571

DOI: https://doi.org/10.37391/IJEER.100326

Abstract

Precision agriculture is gaining attention as it employs modern technologies and intelligence for automation in agricultural practices. In the area of weed management, automation is advantageous to select the appropriate herbicide and manage the amount used, which consequently reduced the cost and minimizes the environmental impact. Selective spraying using a sprayer boom can be implemented using automatic detection of weed type. This paper presents a weed classification method based on a modified line filter image analysis technique that can effectively detect the morphological differences, mainly directional shape features, between two types of weeds. After the result for binary classification has been verified, a third dataset is introduced which is mixed leaves which consists of an approximately balanced amount of broadleaves and narrow leaves. The weed images were pre-processed using the adaptive histogram method and difference of Gaussian to improve the image contrast and delineate the edges of the weed. The images were then processed using the proposed modified line filter feature extraction technique. The filter is based on the evaluation of pixel response that corresponds to the pre-defined lines at different orientations from 0o to 360o. The pixel strength of each line was compared to determine the overall response of the filter. The proposed method achieved around 97% classification, superior compared to previously reported methods such as Gabor wavelet as well as a combination of Gabor and Gradient Field Distribution (GFD).

Keywords: Weed classification, precision agriculture, line filter, image processing




Seri Mastura Mustaza, Department of Electric, Electronic and Systems Engineering, Faculty of Engineering and Built Environment, Universiti Kebangsaan Malaysia, 43600 UKM Bangi, Selangor, Malaysia; Email: seri.mastura@ukm.edu.my

Mohd Faisal Ibrahim, Department of Electric, Electronic and Systems Engineering, Faculty of Engineering and Built Environment, Universiti Kebangsaan Malaysia, 43600 UKM Bangi, Selangor, Malaysia; Email: faisal.ibrahim@ukm.edu.my

Mohd Hairi Mohd Zaman, Department of Electric, Electronic and Systems Engineering, Faculty of Engineering and Built Environment, Universiti Kebangsaan Malaysia, 43600 UKM Bangi, Selangor, Malaysia; Email: hairizaman@ukm.edu.my

Noraishikin Zulkarnain, Department of Electric, Electronic and Systems Engineering, Faculty of Engineering and Built Environment, Universiti Kebangsaan Malaysia, 43600 UKM Bangi, Selangor, Malaysia; Email: shikinzulkarnain@ukm.edu.my

Nasharuddin Zainal, Department of Electric, Electronic and Systems Engineering, Faculty of Engineering and Built Environment, Universiti Kebangsaan Malaysia, 43600 UKM Bangi, Selangor, Malaysia; Email: nasharuddin@ukm.edu.my

Mohd Marzuki Mustafa, Department of Electric, Electronic and Systems Engineering, Faculty of Engineering and Built Environment, Universiti Kebangsaan Malaysia, 43600 UKM Bangi, Selangor, Malaysia; Email: marzuki@ukm.edu.my

    [1] D. Slaughter, D. Giles, D. Downey, K. Gillis, R. Zarghami, and et.al., “Intelligent herbicide application system for reduced herbicide vegetation control phase ii - commercialization,” California Department of Transportation - Division of Research and Innovation, Tech. Rep. CA08-0279, Dec. 2008.[Cross Ref]
    [2] R. B. Mohamad, W. Wibawa, M. G. Mohayidin, A. B.Puteh, A. S. Juraimi, Y. Awang, and M. B. M. Lassim, “Management of mixed weeds in young oil-palm plantation with selected broad-spectrum herbicides,” Pertanika J. Trop. Agric. Sci, vol. 33, no. 2, pp. 193–203, 2010.[Cross Ref]
    [3] A. J. Ishak, A. Hussain, and M. M. Mustafa, “Weed image classification using Gabor wavelet and gradient field distribution,” Computers and Electronics in Agriculture, vol. 66, no. 2009, pp. 53–61, Dec. 2008.[Cross Ref]
    [4] X. P. Burgos-Artizzu, A. Ribeiro, M. Guijarro, and G. Pajares, “Real-time image processing for crop/weed discrimination in maize fields,” Computers and Electronics in Agriculture, vol. 75, no. 2, pp. 337–346, 2011. [Online]. Available: https://www.sciencedirect.com/science/article/pii/S0168169910002620[Cross Ref]
    [5] R. R. Shamshiri, I. A. Hameed, S. K. Balasundram, D. Ahmad, C. Weltzien, and M. Yamin, Fundamental Research on Unmanned Aerial Vehicles to Support Precision Agriculture in Oil Palm Plantations. Intech Open, Nov. 2018.[Cross Ref]
    [6] G. N., L. L. R., and T. Anurada, “Weed classification in maize field using Gabor filter,” International Journal of Innovative Research in Science, Engineering and Technology, vol. 6, no. 4, pp. 2347–6710, 2017.[Cross Ref]
    [7] M. A. and M. M., “Development of a real-time site sprayer system for specific weeds using Gabor wavelets and neural networks model,” in Malaysia Science and Technology Congress, Apr. 2005, pp. 406–413.[Cross Ref]
    [8] Z. Wu, Y. Chen, B. Zhao, X. Kang, and Y. Ding, “Review of weed detection methods based on computer vision,” Sensors, vol. 21, no. 11, p. 3647, May 2021.[Cross Ref]
    [9] Y. Chen, Z. Wu, B. Zhao, C. Fan, and S. Shi, “Weed and corn seedling detection in the field based on multi-feature fusion and support vector machine,” Sensors, vol. 21, no. 1, p. 212, Jan. 2021.[Cross Ref]
    [10] J. Chaki, R. Parekh, and S. Bhattacharya, “Plant leaf recognition using texture and shape features with neural classifiers,” Pattern Recognition Letters, vol. 58, pp. 61–68, 2015. [Online]. Available: https://www.sciencedirect.com/science/article/pii/S0167865515000586[Cross Ref]
    [11] Z. Tang, Y. Su, M. J. Er, F. Qi, L. Zhang, and J. Zhou, “A local binary pattern-based texture descriptors for classification of tea leaves,” Neurocomput., vol. 168, no. C, p. 10111023, Nov. 2015. [Online]. Available: https://doi.org/10.1016/j.neucom.2015.05.024[Cross Ref]
    [12] J. Behmann, A. Mahlein, and T. Rumpf, “A review of advanced machine learning methods for the detection of biotic stress in precision crop protection,” Precision Agriculture, vol. 16, p. 239260, 2015.[Cross Ref]
    [13] P. Lottes, M. Hoeferlin, S. Sander, M. Mter, P. Schulze, and L. C. Stachniss, “An effective classification system for separating sugar beets and weeds for precision farming applications,” in 2016 IEEE International Conference on Robotics and Automation (ICRA), 2016, pp. 5157–5163.[Cross Ref]
    [14] M.Thanjaivadivel, R.Suguna. Leaf Disease Prediction Using Fast Enhanced Learning Method International Journal of Engineering Trends and Technology, vol. 69 no. 9, pp. 34-44[Cross Ref]
    [15] G. Azzopardi, N. Strisciuglio, M. Vento, and N. Petkov, “Trainable cosfire filters for vessel delineation with application to retinal images,” Medical Image Analysis, vol. 19, no. 1, pp. 46–57, 2015. [Online]. Available: https://www.sciencedirect.com/science/article/pii/S1361841514001364[Cross Ref]
    [16] E. Ricci and R. Perfetti, “Retinal blood vessel segmentation using line operators and support vector classification,” IEEE Transactions on Medical Imaging, vol. 26, no. 10, pp. 1357–1365, 2007.[Cross Ref]
    [17] L. Tang, L. Tian, and B. L. Steward, “Classification of broadleaf and grass weeds using Gabor wavelets and an artificial neural network,” American Society of Agricultural and Biological Engineers, vol. 46, no. 4, p. 12471254, 2003.[Cross Ref]
    [18] F. Akram, M. Garcia, and D. Puig, “Active contours driven by the difference of Gaussians,” Sci Rep, vol. 7, p. 14984, 2017.[Cross Ref]
    [19] N. Islam, M. M. Rashid, S. Wibowo, C.-Y. Xu, A. Morshed, S. A. Wasimi, S. Moore, and S. M. Rahman, “Early weed detection using image processing and machine learning techniques in an Australian chili farm,” Agriculture, vol. 11, no. 5, p. 387, Apr. 2021.[Cross Ref]
    [20] M. H. M. Zaman, S. M. Mustaza, M. F. Ibrahim, M. A. Zulkifley and M. M. Mustafa, "Weed Classification Based on Statistical Features from Gabor Transform Magnitude," 2021 International Conference on Decision Aid Sciences and Application (DASA), 2021, pp. 147-151[Cross Ref]

Seri Mastura Mustaza, Mohd Faisal Ibrahim, Mohd Hairi Mohd Zaman, Noraishikin Zulkarnain, Nasharuddin Zainal and Mohd Marzuki Mustafa (2022), Directional Shape Feature Extraction Using Modified Line Filter Technique for Weed Classification. IJEER 10(3), 564-571. DOI: 10.37391/IJEER.100326.