Recognition of weeds at asparagus fields using multi-feature fusion and backpropagation neural network

Yafei Wang, Xiaodong Zhang, Guoxin Ma, Xiaoxue Du, Naila Shaheen, Hanping Mao

Abstract


In order to solve the problem of low recognition rates of weeds by a single feature, a method was proposed in this study to identify weeds in Asparagus (Asparagus officinalis L.) field using multi-feature fusion and backpropagation neural network (BPNN). A total of 382 images of weeds competing with asparagus growth were collected, including 135 of Cirsium arvense (L.) Scop., 138 of Conyza sumatrensis (Retz.) E. Walker, and 109 of Calystegia hederacea Wall. The grayscale images were extracted from the RGB images of weeds using the 2G-R-B factor. Threshold segmentation of the grayscale image of weeds was applied using Otsu method. Then the internal holes of the leaves were filled through the expansion and corrosion morphological operations, and other interference targets were removed to obtain the binary image. The foreground image was obtained by masking the binary image and the RGB image. Then, the color moment algorithm was used to extract weeds color feature, the gray level co-occurrence matrix and the Local Binary Pattern (LBP) algorithm was used to extract weeds texture features, and seven Hu invariant moment features and the roundness and slenderness ratio of weeds were extracted as their shape features. According to the shape, color, texture, and fusion features of the test samples, a weed identification model was built. The test results showed that the recognition rate of Cirsium arvense (L.) Scop., Calystegia hederacea Wall. and Conyza sumatrensis (Retz.) E. Walker were 82.72% (color feature), 72.41% (shape feature), 86.73% (texture feature) and 93.51% (fusion feature), respectively. Therefore, this method can provide a reference for the study of weeds identification in the asparagus field.
Keywords: weeds recognition, image processing, feature extraction, multi-feature fusion, BP neural network, asparagus field
DOI: 10.25165/j.ijabe.20211404.6135

Citation: Wang Y F, Zhang X D, Ma G X, Du X X, Shaheen N, Mao H P. Recognition of weeds at asparagus fields using multi-feature fusion and backpropagation neural network. Int J Agric & Biol Eng, 2021; 14(4): 190–198.

Keywords


weeds recognition, image processing, feature extraction, multi-feature fusion, BP neural network, asparagus field

Full Text:

PDF

References


Guo Q B, Wang N F, Liu H H, Li Z, Lu L F, Wang C L. The bioactive compounds and biological functions of Asparagus officinalis L.– A review. Journal of Functional Foods, 2020; 65: 103727. doi: 10.1016/ j.jff.2019.103727.

Lwin W W, Srilaong V, Boonyaritthongchai P, Wongs A C, Pongprasert N. Electrostatic atomized water particles reduce postharvest lignification and maintain saparagus quality. Scientia Horticulturae, 2020; 271: 109487. doi: 10.1016/j.scienta.2020.109487.

Zhang J, Zhang F, Li D R, Liu Y C, Liu B J, Meng X H. Characterization of metabolite profiles of white and green spears of Asparagus officinalis L. from Caoxian, East China. Food Research International, 2020; 128: 108869. doi: 10.1016/j.foodres.2019.108869.

Siomos A S. The quality of asparagus as affected by preharvest factors. Scientia Horticulturae, 2018; 233: 510–519.

Pahikkala T, Kari K, Mattila H, Lepisto A, Teuhola J, Nevalainen O S, et al. Classification of plant species from images of overlapping leaves. Computers and Electronics in Agriculture, 2015; 118: 186–192.

Miao R H, Tang J L, Chen X Q. Classification of farmland images based on color features. J. Visual Commun. Image Represent, 2015; 29: 138–146.

Rehman T U, Zaman Q U, Chang Y K, Schumann A W, Corscadden K W, Esau T J. Optimising the parameters influencing performance and weed (goldenrod) identification accuracy of colour co-occurrence matrices. Biosystems Engineering, 2018; 170: 85–95.

Li H, Travlos I, Qi L J, Kanatas P, Wang P. Optimization of herbicide use: Study on spreading and evaporation characteristics of glyphosate-organic silicone mixture droplets on weed leaves. Agronomy-Basel, 2019; 9(9): 547. doi: 10.3390/agronomy9090547.

Van Bruggen A H C, He M M, Shin K, Mai V, Jeong K C, Finckh M R, et al. Environmental and health effects of the herbicide glyphosate. Science of the Total Environment, 2018; 616-617: 255–268.

Zhu J W, Wang J, DiTommaso A, Zhang C X, Zheng G P, Liang W, et al. Weed research status, challenges, and opportunities in China. Crop Protection, 2020; 134: 104449. doi: 10.1016/j.cropro.2018.02.001.

Ullah R, Aslam Z, Maitah M, Zaman Q, Bashir S, Hassan W, et al. Sustainable weed control and enhancing nutrient use efficiency in crops through Brassica (Brassica compestris L.) allelopathy. Sustainability, 2020; 12(14): 5763. doi:10.3390/su12145763.

MacLaren C, Storkey J, Menegat A, Metcalfe H, Dehnen-Schmutz K. An ecological future for weed science to sustain crop production and the environment. A review. Agronomy for Sustainable Development, 2020; 40(4): 24. doi: 10.1007/s13593-020-00631-6.

Caser M, Demasi S, Caldera F, Dhakar N K, Trotta F, Scariot V. Activity of Ailanthus altissima (Mill.) swingle extract as a potential bioherbicide for sustainable weed management in horticulture. Agronomy, 2020; 10(7): 965. doi: 10.3390/agronomy10070965.

Pannacci E, Farneselli M, Guiducci M, Tei F. Mechanical weed control in onion seed production. Crop protection, 2020; 135: 105221. doi: 10.1016/j.cropro.2020.105221.

Molinari F A, Blanco A M, Vigna M R, Chantre G R. Towards an integrated weed management decision support system: A simulation model for weed-crop competition and control. Computers and Electronics in Agriculture, 2020; 175: 105597. doi: 10.1016/j.compag.2020.105597.

Nichols V, Verhulst N, Cox R, Govaerts B. Weed dynamics and conservation agriculture principles: A review. Field Crops Research, 2015; 183: 56–68.

Qiao X, Li Y Z, Su G Y, Tian H K, Zhang S, Sun Z Y, et al. MmNet: Identifying Mikania micrantha Kunth in the wild via a deep Convolutional Neural Network. Journal of Integrative Agriculture, 2020; 19(5): 1292–1300.

Borja E G, Nikos M, Loukas A, Spyros F, Ioannis V. Towards weeds identification assistance through transfer learning. Computers and Electronics in Agriculture, 2020; 171: 105306. doi: 10.1016/j.compag.2020.105306.

Favreliere E, Ronceux A, Pernel J, Meynard J M. Nonchemical control of a perennial weed, Cirsium arvense, in arable cropping systems. A review. Agronomy for Sustainable Development, 2020; 40(4): 31. doi: 10.1007/s13593-020-00635-2.

Zhang Q, Zeng S N, Zhang B B. Initial investigation of different classifiers for plant leaf classification using multiple features. In: Proceedings of Eleventh International Conference on Digital Image Processing (ICDIP), Guangzhou, 2019; pp.256–264. doi: 10.26914/c.cnkihy.2019.007593.

Zeng S N, Zhang B B, Du Y. Joint distances by sparse representation and locality-constrained dictionary learning for robust leaf recognition. Computers and Electronics in Agriculture, 2017; 142(Part B): 563–571.

Sajad S, Yousef A G, Ginés G M. A fast and accurate expert system for weed identification in potato crops using metaheuristic algorithms. Computers in Industry, 2018; 98: 80–89.

Radhika K, Mamatha B, Srikanth P. Crop and weed discrimination using Laws' texture masks. Int J Agric & Biol Eng, 2020; 13(1): 191-197.

Gai J Y, Tang L, Stewad B L. Automated crop plant detection based on the fusion of color and depth images for robotic weed control. Journal of Field Robotics, 2020; 37(1): 35–52.

Farooq A, Jia X P, Hu J K, Zhou J. Multi-resolution weed classification via convolutional neural network and superpixel based local binary pattern using remote sensing image. Remote Sensing, 2019; 11(14): 1692. doi: 10.3390/rs11141692.

Dadashzadeh M, Abbaspour-Gilandeh Y, Mesri-Gundoshmian T, Sabzi S, Hernandez-Hernandez J L, Hernandez-Hernandez M, et al. Weed classification for site-specific weed management using an automated stereo computer-vision machine-learning system in rice fields. Plants-basel, 2020; 9(5): 559. doi: 10.3390/plants9050559.

Tang J L, Wang D, Zhang Z G, He L J, Xin J, Xu Y. Weed identification based on K-means feature learning combined with convolutional neural network. Computers and Electronics in Agriculture, 2017; 135: 63-70.

Wang X, Du W K, Hu S M. Leaf recognition based on elliptical half Gabor and maximum gap local line direction pattern. IEEE Access, 2020; 8: 39175–39183.

Aakif A, Khan M F. Automatic classification of plants based on their leaves. Biosystems Engineering, 2015; 139: 66–75.

Bester T M, Timothy D, Saliou N, Emily K, Tobias L, Zeyaur K, et al. Is it possible to discern Striga weed (Striga hermonthica) infestation levels in maize agro-ecological systems using in-situ spectroscopy? Int J Appl Earth Obs Geoinformation, 2020; 85: 102008. doi: 10.1016/j.jag.2019.102008.

Wang A C, Zhang W, Wei X H. A review on weed detection using ground-based machine vision and image processing techniques. Computers and Electronics in Agriculture, 2019; 158: 226–240.

Bosili P, Duckett T, Cielniak G. Analysis of morphology-based features for classification of crop and weeds in precision agriculture. IEEE Robotics and Automation Letters, 2018; 3(4): 295–1956.

Wang Y F, Du X X, Ma G X, Liu Y, Wang B, Mao H P. Classification methods for airborne disease spores from greenhouse crops based on multifeature fusion. Applied Science, 2020; 10(21): 7850. doi: 10.3390/app10217850.

Deng X W, Qi L, Ma X, Jiang Y, Chen X S, Liu H Y, et al. Recognition of weeds at seedling stage in paddy fields using multi-feature fusion and deep belief networks. Transactions of the CSAE, 2018; 34(14): 165–172. (in Chinese)

Bhunia A K, Bhattacharyya A, Banerjee P. A noval feature descriptor for image retrieval by combining modified color histogram and diagonally symmetric co-occurrence texture pattern. Pattern Analysis and Applications, 2020; 23: 703–723.

Liu L, Fieguth P, Guo Y L, Wang X G, Pietikäinen M. Local binary features for texture classification: Taxonomy and experimental study. Pattern Recognition, 2017; 62: 135–160.

Kou Q Q, Cheng D Q, Chen L L, Zhao K. A multiresolution gray-scale and rotation invariant descriptor for texture classification. IEEE Access, 2018; 6: 30691–30701.

Lauwers M, Cauwer B D, Nuyttens D, Cool S R, Pieters J G. Hyperspectral classification of Cyperus esculentus clones and morphologically similar weeds. Sensors, 2020; 20(9): 2504. doi: 10.3390/s20092504.

Deng X W, Qi L, Ma X, Jiang Y, Chen X S, Liu H Y, et al. Recognition of weeds at seedling stage in paddy fields using multi-feature fusion and deep belief networks. Transactions of the CSAE, 2018; 34(14): 165–172. (in Chinese)

Xu K, Li H M, Cao W X, Zhu Y, Chen R J, Ni J. Recognition of weeds in wheat fields based on the fusion of RGB images and depth images. IEEE Access, 2020; 8: 110362–110370.

Thyagharajan K K, Raji I K. A review of visual descriptors and classification techniques used in leaf species identification. Archives of Computational Methods in Engineering, 2019; 26: 933–960.




Copyright (c) 2021 International Journal of Agricultural and Biological Engineering

Creative Commons License
This work is licensed under a Creative Commons Attribution 4.0 International License.

2023-2026 Copyright IJABE Editing and Publishing Office