Weed Classification Analysis Using Localized Multiple Kernel Learning (LMKL)

Shahrani Shahbudin, Noor Fithratul Ain Ishak, Hasmaini Mohamad, Murizah Kassim


Weed classification is a need in the agricultural research to improve the weed control system. There are many kernel-based learning algorithms to identify weed images proposed in the literature; however, most of the weed classification technique proposed a single kernel-based algorithm. Recently, the Localized Multiple Kernel Learning (LMKL) instead of using a single kernel has been proposed for the classification technique that can enhance the interpretability of the decision function and improve performances. LMKL is composed of a kernel-based learning algorithm and a parametric gating model to assign local weights to kernel functions. These two components are trained in a coupled manner using a two-step alternating optimization algorithm. The learning algorithm is derived from three different gating models (softmax, sigmoid, and Gaussian), which applies the LMKL framework on the machine learning problems of binary classification. Therefore, in this work, feature vectors of weed images extracted using the Gabor Wavelet and the Fast Fourier Transform (FFT) were employed to analyze weed pattern images using LMKL algorithms. The result with the aid of gating model are visualized and discussed to prove the performance of LMKL classifier. The results showed the visualization using six types of combinations kernels for all set feature vectors are different for each weed dataset.


Fast Fourier Transform; Gabor Wavelet; Localized Multiple Kernel Learning; Weed Classification;

Full Text:



Sorlini, F.C.a.C., Applied and Environmental Microbiology. 2008.

S.Shahbudin, A.H., S. A. Samad, M.M.Mustafa, A.J. Ishak, Optimal Feature Selection for SVM based weed Classification via Visual Analysis. 2010.

Rumpf, T.R., Christoph Weis, Martin Sökefeld, Markus Gerhards, Roland Plümer, Lutz, Sequential support vector machine classification for small-grain weed species discrimination with special regard to Cirsium arvense and Galium aparine. Computers and Electronics in Agriculture, 2012. 80(0): p. 89-96.

De Rainville, F.-M., et al., Bayesian classification and unsupervised learning for isolating weeds in row crops. Pattern Analysis and Applications, 2014. 17(2): p. 401-414.

Alain Rakotomamonjy, F.B., Stephane Canu, Yves Grandvalet., SimpleMKL. Journal of Machine Learning Research, Microtome Publishing, 2008, 9,, 8 Sep 2008.

G¨onen, M., Multiple Kernel Learning Algorithms. Journal of Machine Learning Research 12 2011.

G¨onen, M., Localized Multiple Kernel Learning Algorithms 2008.

Yina Han, K.Y., Yuanliang Ma, Guizhong Liu Localized Multiple Kernel Learning via Sample-wise Alternating Optimization. IEEE Transactions On Cybernetics, 2014. 44.

Asnor Juraiza Ishak, M.M.M.a.A.h., Weed Feature Extraction Using Gabor Wavelet and fast Fourier Transform International Symposium on information & Communication Technologies, Nov 2006.

Alain Rakotomamonjy, F.B., Stephane Canu, Yves Grandvalet., More Efficiency in Multiple Kernel Learning. 2004: p. 8.

Gönen, M.a.E.A., Localized algorithms for multiple kernel learning. Pattern Recognition, 2013: p. 46(3): 795-807.

Gonen, M., Localized Multiple Kernel Learning. 2010. URL : http://users.ics.aalto.fi/gonen/icml08.php.

Razavi-Far, R., Palade, V. & Zio, E. Invasive weed classification.Neural Comput & Applic , 2015, 26: 525. doi:10.1007/s00521-014-1656-3

A Tannouche, K Sbai, Y Ounejjar, M Rahmoune, A Rahmani, A Fast and Efficient Approach for Weeds Identification Using Haar-Like Features, American-Eurasian Journal of Sustainable Agriculture, 2015, 9 (4), 44-48

MH Siddiqi, SW Lee, AM Khan, Weed Image Classification using Wavelet Transform, Stepwise Linear Discriminant Analysis, and Support Vector Machines for an Automatic Spray Control System.J. Inf. Sci. Eng. 2014, 30 (4), 1227-1244.


  • There are currently no refbacks.

Creative Commons License
This work is licensed under a Creative Commons Attribution 3.0 License.

ISSN: 2180-1843

eISSN: 2289-8131