Maize Leaf Disease Image Classification Using Bag Of Features

Main Article Content

Wahyudi Setiawan Mohammad Syarief Novi Prastiti

Abstract

Image classification is a grouping of images based on specific categories. This study discussed the maize leaf disease image classification using Bag-Of-Features (BOF) approach, which is a collection of methods stages to perform feature extraction and classification of the images. The methods we used were Speeded-Up Robust Features (SURF) for feature extraction,  k-means clustering and Support Vector Machine for classification. The maize leaf images used in this research are from the PlantVillage-Dataset. The data consists of 3 types of images: RGB, gray scale and segmentation images. Each type includes 4 disease classes: healthy, cercospora, common rust, and northern leaf blight. There are 50 images for each class. We used 2 scenarios of testing for each type of the data: training and validation; 60 images for training, and the rests (140 images) for validation. Experi-mental results showed that the training accuracies of RGB, gray scale, and segmentation images were 98.25%, 95%, and 74.75% respectively; and the validation accuracies were 72%, 72.75%, and 80.5%.

Downloads

Download data is not yet available.

Article Details

How to Cite
SETIAWAN, Wahyudi; SYARIEF, Mohammad; PRASTITI, Novi. Maize Leaf Disease Image Classification Using Bag Of Features. JURNAL INFOTEL, [S.l.], v. 11, n. 2, july 2019. ISSN 2460-0997. Available at: <http://ejournal.st3telkom.ac.id/index.php/infotel/article/view/428>. Date accessed: 22 july 2019. doi: https://doi.org/10.20895/infotel.v11i2.428.
Section
Articles

References

[1] M. Chafid, “Outlook Komoditas Pertanian Subsektor Pangan Jagung,” Pus. Data dan Sist. Inf. Pertan., p. 82, 2015.
[2] C. A. Blanco et al., “Maize Pests in Mexico and Challenges for the Adoption of Integrated Pest Management Programs,” J. Integr. Pest Manag., vol. 5, no. 4, p. DOI: http://dx.doi.org/10.1603/IPM14006, 2013.
[3] H. Al Hiary, S. Bani Ahmad, M. Reyalat, M. Braik, and Z. ALRahamneh, “Fast and Accurate Detection and Classification of Plant Diseases,” Int. J. Comput. Appl., vol. 17, no. 1, pp. 31–38, 2011.
[4] L. Cao, X. San, Y. Zhao, and G. Chen, “Application of machine vision technology in the diagnosis of maize disease,” IFIP Adv. Inf. Commun. Technol., vol. 370 AICT, no. PART 3, pp. 188–194, 2012.
[5] E. Alehegn, “Maize Leaf Diseases Recognition and Classification Based on Imaging and Machine Learning Techniques,” 2017.
[6] S. P. Mohanty, D. Hughes, and M. Salathé, “Using Deep Learning for Image-Based Plant Disease Detection,” Front. Plant Sci., vol. 7, no. 10, pp. 1–7, 2016.
[7] K. R. Aravind, P. Raja, K. V Mukesh, R. Aniirudh, R. Ashiwin, and C. Szczepanski, “Bag of Features and Multiclass Support Vector Machine,” 2018 2nd Int. Conf. Inven. Syst. Control, no. Icisc, pp. 1191–1196, 2018.
[8] A. Foncubierta-Rodríguez, A. de Herrera, and H. Müller, “Medical image retrieval using bag of meaningful visual words: unsupervised visual vocabulary pruning with PLSA,” Proc. 1st ACM Int. Work. Multimed. Index. Inf. Retr. Healthc., pp. 75–82, 2013.
[9] M. R. Zare, W. C. Seng, and A. Mueen, “Automatic classification of medical X-ray images,” Malaysian J. Comput. Sci., vol. 26, no. 1, pp. 9–22, 2013.
[10] Y. Hu, Z. Li, P. Li, Y. Ding, and Y. Liu, “Accurate and Fast Building Detection Using Binary Bag-of-Features,” ISPRS - Int. Arch. Photogramm. Remote Sens. Spat. Inf. Sci., vol. XLII-1/W1, no. June, pp. 613–617, 2017.
[11] L. Weizman and J. Goldberger, “Detection of Urban Zones in Satellite Images using Visual Words,” IGARSS 2008 - 2008 IEEE Int. Geosci. Remote Sens. Symp., pp. V-160-V–163, 2008.
[12] D. Q. Xiao, J. Z. Feng, T. Y. Lin, C. H. Pang, and Y. W. Ye, “Classification and recognition scheme for vegetable pests based on the BOF-SVM model,” Int. J. Agric. Biol. Eng., vol. 11, no. 3, pp. 190–196, 2018.
[13] K. Venugoban and A. Ramanan, “Image Classification of Paddy Field Insect Pests Using Gradient-Based Features,” Int. J. Mach. Learn. Comput., vol. 4, no. 1, pp. 1–5, 2014.
[14] H. Bay, T. Tuytelaars, and L. Van Gool, “SURF: Speeded up robust features,” Lect. Notes Comput. Sci. (including Subser. Lect. Notes Artif. Intell. Lect. Notes Bioinformatics), vol. 3951 LNCS, pp. 404–417, 2006.
[15] M. Zhang and R. Askin, “Small Blob Detection in Medical Images,” no. May, 2015.
[16] A. Ming and H. Ma, “A blob detector in color images,” Proc. 6th ACM Int. Conf. Image video Retr. - CIVR ’07, pp. 364–370, 2007.
[17] R. Lakemond, C. Fookes, and S. Sridharan, “Affine adaptation of local image features using the Hessian matrix,” 6th IEEE Int. Conf. Adv. Video Signal Based Surveillance, AVSS 2009, no. September, pp. 496–501, 2009.
[18] D.-C. Cheng, “Haar Wavelet Analysis Haar Wavelets,” pp. 1–17, 2011.
[19] L. February, “Chapter 1 Overview,” 2010.
[20] S. Ehsan, A. F. Clark, N. ur Rehman, and K. D. McDonald-Maier, “Integral images: Efficient algorithms for their computation and storage in resource-constrained embedded vision systems,” Sensors (Switzerland), vol. 15, no. 7, pp. 16804–16830, 2015.
[21] K. S. Sujatha, G. M. Karthiga, and B. Vinod, “Evaluation of Bag of Visual Words for Category Level Object Recognition,” Int. J. Electron. Signals Syst., vol. 1, no. 4, pp. 104–110, 2012.
[22] A. Kowalczyk, Support Vector Machine. Morrisville, North Carolina: syncfusion, 2017.
[23] Burhanuddin, “preferensi penyakit karat daun ( puccinia polysora undrew ) pada tanaman jagung,” Pros. Semin. Nas. Serelia, pp. 395–405, 2015.