Adaptive Features Fusion and Fast Recognition of Potato Typical Disease Images
Abstract
In view of the difficulty in region location and classification of potato typical diseases under natural conditions, a new adaptive features fusion and fast recognition method of potato typical disease images was proposed. The segmented disease image, processing object of the proposed method, could be obtained as following two steps. Firstly, by using K-means, Hough transform and superpixels segmentation algorithms, the whole potato blade containing disease region was located in complicated background. Secondly, the disease region was separated from green blade by combining with two-dimensional Otsu and morphology method. On the basis of the segmented disease image, totally 124 potato disease features, including 18 color features, 21 shape features and 85 texture features were extracted. As thus, the color, shape and texture features were fused adaptively based on principal component analysis (PCA) algorithm and weighted formulation, and used to potato diseases recognition by support vector machine (SVM). According to features fusion and SVM recognition, totally 13 weighted principal components were gained as following three steps. Firstly, color, shape and texture features were automatically divided into many feature blocks, including RGB and HSV, geometric statistics (GS), central moments and Hu moments, Gray-level co-occurrence matrix (GLCM), high frequency low order moments and low frequency low order moments (HMLM), and high frequency covariance matrix eigenvalues and low frequency lower order moments (HELM). By comparison of recognition rates and features dimension, RGB, GS and HELM feature blocks were selected from color, shape, texture feature blocks, respectively. Secondly, five RGB, five GS and three HELM principal components were acquired by PCA algorithm. Thirdly, RGB, GS and HELM were weighted based on their recognition rates of principal components, and each principal component was also weighted based on weight distribution formulation. The recognition test of three kinds of typical potato samples showed that the proposed method had an obvious advantage. By using the same SVM recognition model, and compared with recognition rates of traditional adaptive methods, including PCA descending dimension, feature sorting selection, and so on, the proposed adaptive feature fusion algorithm had high average recognition rate which was increased by at least 1.8 percentage points. By using the same 13 adaptive fusion features, average recognition rate of the proposed recognition method was 95.2%, which were increased by 3.8 percentage points and 8.5 percentage points than those of ANN and Bayes, respectively, and run time of the proposed recognition method was 0.600s, which was 3s faster than that of ANN. Therefore, the proposed method could be used to greatly improve the recognition speed based on effectively ensuring the recognition accuracy.
Keywords: potato typical diseases, Hough transform, principal component analysis, weighted fusion, support vector machine
Download Full Text:
PDFReferences
LU Jinqing, SHANG Qinqin, YANG Ying, et al. Design optimization and experiment on potato haulm cutter [J/OL]. Transactions of the Chinese Society for Agricultural Machinery, 2016, 47(5) : 106 - 114. (in Chinese)
ZHANG H, FRITTS J E, GOLDMAN S A. Image segmentation evaluation: a survey of unsupervised methods [ J ]. Computer Vision & Image Understanding, 2008, 110(2) : 260 -280.
CHEN Li, WANG Lanving. Research on application of probability neural network in maize leaf disease identification[ J ] . Journalof Agricultural Mechanization Research, 201 1 , 33(6) ; 145 - 148. (in Chinese)
http:// WWW. j-csam. org/jcsam/ch/reader/ view_abstract. aspx? flag = l&file_no = 20131036&journal_id = jcsam. DOI: 10. 6041/ j. issn. 1000-1298.2013. 10.036. HUO Yingqiu, TANG Jinglei, YIN Xiuzhen, et al. Apple disease recognition based on compressive sensing[ J/OL] . Transactions of the Chinese Society for Agricultural Machinery, 2013, 44( 10) ; 227 -232. (in Chinese)
TIAN Kai, ZHANG Liankuan, XIONG Meidong, et al. Recognition of phomopsis vexans in solanum melongena based on leaf disease spot features [J ]. Transactions of the CSAE, 2016, 32(Supp. 1): 184 - 189. (in Chinese)
http://www.j-csam.org/jcsam/ch/reader/ view_abstract. aspx? flag = l&file_no = 20160241 &journal_id = jcsam. DOI: 10. 6041/j. issn. 1000-1298.2016.02.041. LIANG Kun, DU Yingying, LU Wei, et al. Identification of fusarium head blight wheat based on hyperspectral imaging technology [ J/OL]. Transactions of the Chinese Society for Agricultural Machinery, 2016, 47(2) ; 309 -315. (in Chinese)
PUJARI J D, YAKKUNDIMATH R, BYADGI A S. Automatic fungal disease detection based on wavelet feature extraction and PCA analysis in commercial crops [ J]. International Journal of Image Graphics & Signal Processing, 2013, 6( 1 ) ; 24-31.
PECHENIZKIY M, PUURONEN S, TSYMBAL A. The impact of sample reduction on PCA-based feature extraction for supervised learning[ C] // ACM Symposium on Applied Computing, DBLP, 2006: 553 -558.
GULHANE V A, KOLEKAR M II. Diagnosis of diseases on cotton leaves using principal component analysis classifier С]//2014 Annual IEEE India Conference, 2014; 1 -5.
ZHAI Zhifen, XU Zhe, ZHOU Xinqun, et al. Recognition of hazard grade for cotton blind stinkbug based on naive bayesian classifier [J] ]. Transactions of the CSAE, 2015, 31(1): 204 -211. (in Chinese)
PU Yongxian. Image searching method of tobacco disease based on disease spot feature fusion [J ]. Journal of Henan Agricultural Sciences, 2015 , 44(2 ) ; 71 - 76. (in Chinese)
CHEN D, CUI D W, W ANG С X. W eighted fuzzy С-means clustering based on double coding genetic algorithm [С ] //International Conference on Intelligent Computing, ICIC 2006, Springer Berlin Heidelberg, 2006: 622 -633.
LI Chao, PENG Jinye, ZHANG Shanwen. Apple leaf disease recognition based on feature fusion and local discriminant projection [J]. Guangdong Agricultural Sciences, 2016, 43( 10) : 134 -139. (in Chinese)
LUO Y, ZHANG T, ZHANG Y. A novel fusion method of PCA and LDP for facial expression feature extraction [J ]. OptikInternational Journal for Light and Electron Optics, 2016, 127(2); 718-721.
http; //www. j-csam. org/jcsam/ch/reader/view_abstract. aspx? flag = l&file_no = 20141108&journal_id = jcsam. DOI; 10.6041/j. issn. 1000-1298.2014. 11.008. HUO Yingqiu, QIN Renbo, XING Caivan, et al. CUDA-based parallel К-means clustering algorithm [ J/OL ]. Transactions of the Chinese Society for Agricultural Machinery, 2014, 45(11); 47 —53. (in Chinese)
GOPALAKRISHNAN A, ALMAZROA A, RAAHEMIFAR K, et al. Optic disc segmentation using circular Hough transform and curve fitting [ С ] // International Conference on Opto-Electronics and Applied Optics, IEEE, 2015; 1 -4.
W ANG II Y, PAN D L, XIA D S. A fast algorithm for two-dimensional Otsu adaptive threshold algorithm [J ]. Journal of Image &Graphics, 2005, 33(9) : 968 -971.
YU X, LIU S, DONG W , et al. Image retrieval method based on fusion of edge features and RGB color component [J ].International Journal of Multimedia & Ubiquitous Engineering, 2014, 9( 10) ; 243 -250.
CHAKI J, PAREKH R, BHATTACHARYA S. Recognition of whole and deformed plant leaves using statistical shape features and neuro-fuzzy classifier [С] // International Conference on Recent Trends in Information Systems, IEEE, 2015; 189 - 194.
ANBARJAFARI G, DEMIREL H. Image super resolution based on interpolation of wavelet domain high frequency subbands and the spatial domain input image [J] . ETRI Journal, 2010, 32(3) ; 390 -394.
VALLIAMMAL N, GEETHALAKSHMI S N. Efficient feature fusion, selection and classification technique for plant leaf image retrieval system С // International Conference on Computational Science, Engineering and Information Technolog)-, ACM , 2012; 132 - 137.
ABDILLAH A A, SUW ARNO. Diagnosis of diabetes using support vector machines with radial basis function kernels [J ]. International Journal of Technology, 2016, 7(5) ; 849 -858.
JIANG J. BP neural network algorithm optimized by genetic algorithm and its simulation [ J ]. International Journal of Computer Science Issues, 2013, 10(2); 516 - 520.
CARLIN В P, LOUIS T A. Bayes and empirical Bayes methods for data analvsis[J]. Statistics and Computing, 1997, 7(2) ; 153 - 154.
Refbacks
- There are currently no refbacks.