Genetic Algorithm Optimization and Feature Selection for a Support Vector Machine Weed Recognition System in Malaysia at Critical Stage of Development

In row spot spraying technology has been in the constant development as a means to reduce the application of herbicide. This will enable higher efficiency in chemical usage and reduce impact on environment. A vision system was developed for a spot spraying mechanism on an autonomous ground vehicle to autonomously detect and eliminate weeds using selective herbicide. Currently, only six species are being trained and tested for recognition. However the classifier is required to be fine tune and the tested features selected for classifier training. In this research, an autonomous fine tuning and feature selection using Genetic Algorithm (GA) was proposed and tested with the assumption that the weeds are young and non-occluded. The results show a feasible means to distinguished the weeds using the selected features (which are a combination of fractal, shape features and HU moment invariants, average color pixel values and elliptical fourier. The results show 100% recognition rates for all 6 species being tested.

[1]  Cheng-Lung Huang,et al.  A GA-based feature selection and parameters optimizationfor support vector machines , 2006, Expert Syst. Appl..

[2]  M. F. Kocher,et al.  Textural imaging and discriminant analysis for distinguishing weeds for spot spraying , 1998 .

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

[4]  Agus Buono,et al.  Weeds and plants recognition using fuzzy clustering and fractal dimension methods for automatic weed control , 2010 .

[5]  T. F. Burks,et al.  Evaluation of Neural-network Classifiers for Weed Species Discrimination , 2005 .

[6]  Wu Lanlan,et al.  Weed/corn seedling recognition by support vector machine using texture features , 2009 .

[7]  George E. Meyer,et al.  Shape features for identifying young weeds using image analysis , 1994 .

[8]  Xien Liu,et al.  Support vector data description for weed/corn image recognition , 2010 .

[9]  Lei Tian,et al.  CLASSIFICATION OF BROADLEAF AND GRASS WEEDS USING GABOR WAVELETS AND AN ARTIFICIAL NEURAL NETWORK , 2003 .

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

[11]  Muralindran Mariappan,et al.  Co-occurrence matrix with neural network classifier for weed species classification: a comparison between direct application of co-occurrence matrix (GLCM) and haralick features as inputs , 2013 .

[12]  Chun-Chieh Yang,et al.  Weed recognition in corn fields using back-propagation neural network models , 2002 .

[13]  A. Jafari,et al.  Crop Detection and Positioning in the Field Using Discriminant Analysis and Neural Networks Based on Shape Features , 2012 .

[14]  S. Kamgar,et al.  Application of Co-occurrence Matrix on Wavelet Coefficients for Crop-weed Discrimination , 2011 .

[15]  Bidyut Baran Chaudhuri,et al.  An efficient approach to estimate fractal dimension of textural images , 1992, Pattern Recognit..

[16]  S. Prasher,et al.  Application of support vector machine technology for weed and nitrogen stress detection in corn , 2006 .

[17]  Abdul Shukor Juraimi,et al.  Management of mixed weeds in young oil-palm plantation with selected broad-spectrum herbicides , 2010 .