Evaluation of support vector machine and artificial neural networks in weed detection using shape features

Abstract Weed detection is still a challenging problem for robotic weed removal. Small tolerance between the cutting tine and main crop position requires highly precise discrimination of the weed against the main crop. Close similarities between the shape features of sugar beet and common weeds make it impossible to define an exclusive feature to be able to efficiently detect all the weeds with acceptable accuracy. Therefore in this study, it was tried to integrate several shape features to establish a pattern for each variety of the plants. To enable the vision system in the detection of the weeds based on their pattern, support vector machine and artificial neural networks were employed. Four species of common weeds in sugar beet fields were studied. Shape feature sets included Fourier descriptors and moment invariant features. Results showed that the overall classification accuracy of ANN was 92.92%, where 92.50% of weeds were correctly classified. Higher accuracies were obtained when the SVM was used as the classifier with an overall accuracy of 95.00% whereas 93.33% of weeds were correctly classified. Also, 93.33% and 96.67% of sugar beet plants were correctly classified by ANN and SVM respectively.

[1]  Muhammed Salman Shamsi,et al.  Student performance prediction using classification data mining techniques , 2016, ArXiv.

[2]  A. J. S. McDonald,et al.  Weed and crop discrimination using image analysis and artificial intelligence methods , 2003 .

[3]  Lipo Wang.  Support vector machines : theory and applications , 2005 .

[4]  Dong Wang,et al.  Weed detection using image processing under different illumination for site-specific areas spraying , 2016, Comput. Electron. Agric..

[5]  Hans Jørgen Andersen,et al.  Detecting creeping thistle in sugar beet fields using vegetation indices , 2015, Comput. Electron. Agric..

[6]  Gonzalo Pajares,et al.  Automatic expert system for weeds/crops identification in images from maize fields , 2013, Expert Syst. Appl..

[7]  Chun-Chieh Yang,et al.  Development of an Image Processing System and a Fuzzy Algorithm for Site-Specific Herbicide Applications , 2003, Precision Agriculture.

[8]  Vladimir Vapnik,et al.  Statistical learning theory , 1998 .

[9]  Min Huang,et al.  Maize and weed classification using color indices with support vector data description in outdoor fields , 2017, Comput. Electron. Agric..

[10]  Faisal Ahmed,et al.  Classification of crops and weeds from digital images: A support vector machine approach , 2012 .

[11]  Chih-Jen Lin,et al.  Training and Testing Low-degree Polynomial Data Mappings via Linear SVM , 2010, J. Mach. Learn. Res..

[12]  J. Endler,et al.  The Relative Success of Some Methods for Measuring and Describing the Shape of Complex Objects , 1998 .

[13]  Hans Jørgen Andersen,et al.  Exploiting affine invariant regions and leaf edge shapes for weed detection , 2015, Comput. Electron. Agric..

[14]  Adam C. Winstanley,et al.  Using moment invariants for classifying shapes on large-scale maps , 2001 .

[15]  G. Polder,et al.  A Mobile Field Robot with Vision-Based Detection of Volunteer Potato Plants in a Corn Crop1 , 2006, Weed Technology.

[16]  Ole Green,et al.  Weed identification using an automated active shape matching (AASM) technique , 2011 .

[17]  F. Truchetet,et al.  Crop/weed discrimination in perspective agronomic images , 2008 .

[18]  Zhang Zhiyong,et al.  Distance-based separability criterion of ROI in classification of farmland hyper-spectral images , 2017 .

[19]  Dimitrios Moshou,et al.  Active learning system for weed species recognition based on hyperspectral sensing , 2016 .

[20]  Takashi Kataoka,et al.  Image Segmentation between Crop and Weed using Hyperspectral Imaging for Weed Detection in Soybean Field , 2008 .

[21]  Maria C. Garcia-Alegre,et al.  Development of an image analysis system for estimation of weed pressure. , 2005 .

[22]  Guojun Lu,et al.  A comparative study of curvature scale space and Fourier descriptors for shape-based image retrieval , 2003, J. Vis. Commun. Image Represent..

[23]  Jordi Freixenet,et al.  Segmentation and description of natural outdoor scenes , 2007, Image Vis. Comput..

[24]  Xavier P. Burgos-Artizzu,et al.  utomatic segmentation of relevant textures in agricultural images , 2010 .

[25]  Francisco Garcia-Ruiz,et al.  Sugar beet (Beta vulgaris L.) and thistle (Cirsium arvensis L.) discrimination based on field spectral data , 2015 .

[26]  Edward Jones,et al.  Automatic crop detection under field conditions using the HSV colour space and morphological operations , 2017, Comput. Electron. Agric..

[27]  D. Bulanon,et al.  A Segmentation Algorithm for the Automatic Recognition of Fuji Apples at Harvest , 2002 .

[28]  João Paulo Papa,et al.  Aquatic weed automatic classification using machine learning techniques , 2012 .

[29]  Tang Jiali,et al.  Identification of crop weed based on image texture features , 2014 .

[30]  Dongjian He,et al.  Decision support of farmland intelligent image processing based on multi-inference trees , 2015, Comput. Electron. Agric..

[31]  D. Peddle,et al.  Weed and crop discrimination using hyperspectral image data and reduced bandsets , 2014 .

[32]  S. Christensen,et al.  Colour and shape analysis techniques for weed detection in cereal fields , 2000 .

[33]  Ming-Kuei Hu,et al.  Visual pattern recognition by moment invariants , 1962, IRE Trans. Inf. Theory.

[34]  S. Shouche,et al.  Shape analysis of grains of Indian wheat varieties , 2001 .

[35]  G. Meyer,et al.  Verification of color vegetation indices for automated crop imaging applications , 2008 .

[36]  Xiaofeng Wang,et al.  Shape Recognition Based on Radial Basis Probabilistic Neural Network and Application to Plant Species Identification , 2005, ISNN.

[37]  Yang Xu,et al.  Weed identification based on K-means feature learning combined with convolutional neural network , 2017, Comput. Electron. Agric..

[38]  Sakshi Pandey,et al.  Detection of Weeds in a Crop Row Using Image Processing , 2016 .

[39]  A. Samal,et al.  Plant species identification using Elliptic Fourier leaf shape analysis , 2006 .

[40]  Jung Liu,et al.  Shape-based image retrieval using support vector machines, Fourier descriptors and self-organizing maps , 2007, Inf. Sci..

[41]  Adel Bakhshipour,et al.  Weed segmentation using texture features extracted from wavelet sub-images , 2017 .

[42]  Joachim Hertzberg,et al.  Plant classification with In-Field-Labeling for crop/weed discrimination using spectral features and 3D surface features from a multi-wavelength laser line profile system , 2017, Comput. Electron. Agric..