With the entry of huge databases and the resulting prerequisites for excellent machine learning frameworks, new issues emerge and novel feature extraction methods are in demand.Basic feature reduction methods are feature selection and feature extraction. Feature selection find the subset of those prime features in a given initial set and helps in finding optimal solution. Feature extraction method transform original set of features into new subsets which are smaller number of dimensions. Generally features contain information about the target and more features indicate more information and better discrimination power. In this paper we have proposed a novel feature extraction method for feature extraction of maize and paddy dataset. Global thresholding Otsu method is used for segmentation and Error Correcting Output Codes (ECOC) classifier is used for identification of healthy and diseased maize and paddy leaves and found a success rate of 91.32% for paddy leaves and 92.56% for maize leaves. In this experimentation the similarity difference of Gray with Cb Component has given highest accuracy for both data sets.

Disease, ECOC Classifier, Maize, Paddy, Texture Features

[1] S N.Hashim, S E. Adebayo & K. Abdan, M. Hanafi, “Comparative study of transform-based image texture analysis for the evaluation of banana quality using an optical backscattering system”, Postharvest Biology and Technology, Vol.135, pp.38-50, 2018.
[2] Y. Liang, M. Zhang, & W N. Browne, “ Image feature selection using genetic programming for figure-ground segmentation”, Engineering Applications of Artificial Intelligence, Vol.62, pp.96-108, 2017.
[3] L D. Vignolo, D H. Milone & J Scharcanski, “Feature selection for face recognition based on multi-objective evolutionary wrappers”, Expert Systems with Applications, Vol.40,Issue.13,pp. 5077-5084, 2013.
[4] S A. Medjahed, “A Comparative Study of Feature Extraction Methods in Images Classification”, International Journal of Image, Graphics and Signal Processing,Vol.7, pp.16-23, 2015.
[5] S M. Mohammadi, M S. Helfroush & K. Kazemi, “Novel shape-texture feature extraction for medical x-ray image classification” , Int J Innov Comput Inf Control,Vol.8, pp.659-76,2012.
[6] C H. Satyanarayana, S. Anuradha, “A Review of Recent Texture Classification Methods”, October 2013
[7] S. Liao, M W, A C. Chung, “ Dominant local binary patterns for texture classification”, IEEE transactions on image processing, Vol.18,Issue.5, pp.1107-1118, 2009.
[8] J. Dong, Y. Duan, Z. Yang, “Three-dimensional surface texture classification based on support vector machines and wavelet packets”, In Intelligent Information Technology Application, 2008. IITA`08. Second International Symposium Vol. 3, pp. 124-127. IEEE, 2008.
[9] M. Crosier, L D. Griffin, “ Texture classification with a dictionary of basic image features”, In Computer Vision and Pattern Recognition, IEEE Conference. pp. 1-7. 2008.
[10] A. Kumar, V. Patidar & D. Khazanchi, P. Saini, “ Role of Feature Selection on Leaf Image Classification”, Journal of Data Analysis and Information Processing,Vol. 3 Issue.04, pp.175-183, 2015.
[11] K. Chaiyakhan, N. Kerdprasop & K. Kerdprasop, “ Feature selection techniques for breast cancer image classification with support vector machine”, In Proc Int Multi Conf Eng Comp Sci Hong Kong, 2016
[12] J. Novaković, “ Toward optimal feature selection using ranking methods and classification algorithms”, Yugoslav Journal of Operations Research,Vol. 21,Issue.1, 2016.
[13] L D. Vignolo, D H. Milone & J. Scharcanski, “ Feature selection for face recognition based on multi-objective evolutionary wrappers”, Expert Systems with Applications, Vol.40,Issue.13,pp. 5077-5084, 2013.
[14] R D. Gupta, J K. Dash & M. Sudipta, “ Rotation invariant textural feature extraction for image retrieval using eigen value analysis of intensity gradients and multi-resolution analysis”, Pattern Recognition,Vol. 46,Issue.12,pp. 3256-3267, 2013.
[15] B. Lee, “ A new method for classification of structural textures”, International Journal of Control, Automation, and Systems,Vol. 2,Issue.1,pp. 125-133, 2004.
[16] A. Halimi, A. Roukhe & Ouhamd, “ Defect Detection and Identification in Textile Fabric by SVM Method”, IOSR Journal of Engineering (IOSRJEN) ,Vol. 04, PP.69-77, 2014.
[17] Shreekanth K N , Suresha M , " Identification of Healthy and Diseased Paddy Leaves using Texture Features with ECOC Classifier" , IPASJ INTERNATIONAL JOURNAL OF COMPUTER SCIENCE(IIJCS) , Vol. 6, Issue.2, pp. 034-038, 2018.