Beetles and bugs are most common harmful pests that affect plants easily and can damage entire plant. Most of the beetles and bugs bruise the front surface of leaves to lay eggs so and some of the bugs feed on the extract of leaves. So, the leaves get damaged often and it is essential to detect pest affected leaves as early as possible to take further precautions. In this paper, an automated approach based on digital image processing and machine learning is used to classify three vulnerable pests - blue mint beetle, white mealy bug and red lily beetle from affected leaf images. Image pre-processing methods like noise removal and contrast enhancement followed by color space transformation and k-means clustering is used to segment affected parts of leaves, after that both texture and color features are extracted from segmented leaves and based on extracted features support vector machine classification method is used to classify the pests.

Bugs, Beetles, Machine learning, k-means clustering, Feature Extraction, Support Vector Machine

[1] Faithpraise Fina1, Philip Birch2, Rupert Young3, J. Obu4,Bassey Faithpraise5 and Chris Chat, “Automatic Plant Pest Detection And Recognition Using K-Means Clustering Algorithm And Correspondence Filters”, International Journal of Advanced Biotechnology and Research ISSN 0976-2612, Online ISSN 2278–599X, Vol 4, Issue 2, 2013, pp 189-199
[2] Kanesh Venugoban and Amirthalingam Ramanan,” Image Classification of Paddy Field Insect Pests Using Gradient-Based Features”,in the journal of International Journal of Machine Learning and Computing, Vol. 4, No. 1, February 2014
[3] Rajeswary .B1, Divya .S2,” Identification and Classification of Pests in Greenhouse Using Advanced SVM in Image Processing”, in the journal of International Journal of Scientific Engineering and Research (IJSER).
[4] Prathibha G P, T G Goutham, Tejaswini M V, Rajas P R, Mrs Kamalam Balasubramani ,”Early Pest Detection in Tomato Plantation using Image Processing ”, in the journal of International Journal of Computer Applications (0975 – 8887) Volume 96– No.12, June 2014
[5] Gaurav Kandalkar, A.V.Deorankar , P.N.Chatur,” Classification of Agricultural Pests Using DWTand Back Propagation Neural Networks”,in the journal of (IJCSIT) International Journal of Computer Science and Information Technologies, Vol. 5 (3) , 2014, 4034-4037.
[6] M.Manoja, 2Mrs.J.Rajalakshmi,” Early Detection of Pests on Leaves Using Support Vector Machine”, in the journal of International Journal of Electrical and Electronics Research ISSN 2348-6988 (online) Vol. 2, Issue 4, pp: (187-194), Month: October - December 2014
[7] Robert M. Haralick , K. Shanmugam and Its’hak Dinstein “Textural Features For Image Classification”; IEEE Transactions on System man and cybernetics Vol. SMC-3 , No-6,November 1973,PP. 610-621 (1973)
[8] Nameirakpam Dhanachandra, Khumanthem Manglem and Yambem Jina Chanu;” Image Segmentation using K-means Clustering Algorithm and Subtractive Clustering Algorithm”; Eleventh International Multi-Conference on Information Processing-2015 (IMCIP-2015), Procedia Computer Science 54, PP.764 – 771 (2015)
[9] Jagadeesh D. Pujari, Rajesh Yakkundimath and Abdulmunaf S. Byadgi,” Classification of Fungal Disease Symptoms affected on Cereals using Color Texture Features “, International Journal of Signal Processing, Image Processing and Pattern Recognition Vol.6, No.6, PP.321-330 ISSN: 2005-4254 (2013)
[10] Vincent Arvis, Christophe Debain, Michel Berducat And Albert Benassi , “ Generalization Of The Cooccurrence Matrix For Colour Images: Application To Colour Texture Classification”; Image Anal Stereol 2004;23:PP. 63-72 (2004)
[11] J. A. Hartigan and M. A. Wong, “A K-Means Clustering Algorithm”, Journal of the Royal Statistical Society. Series C (Applied Statistics), Vol. 28, No. 1, PP. 100-108 (1979)
[12] Chih-Wei Hsu, Chih-Chung Chang, and Chih-Jen Lin; “A Practical Guide to Support Vector Classification”, Department of Computer Science National Taiwan University, Taipei 106, Taiwan.
[13] Chih-Wei Hsu and Chih-Jen Lin,” A Comparison of Methods for Multi-class Support Vector Machines”;IEEE TRANSACTIONS ON NEURAL NETWORKS, VOL. 13, NO. 2 (2002)