Identification of diseases for soybean seeds by computer vision applying BP neural network

Tan Kezhu, Chai Yuhua, Song Weixian, Cao Xiaoda

Abstract


The use of computer vision for estimating quality in agriculture products has become wide spread in recent years and the composition, variety, or ripeness can be estimated. On the other hand, the appearance is one of the most worrying issues for producers due to its influence on quality. In this research, computer vision technology combined with BP artificial neural network (ANN) was developed to identify soybean frogeye, mildewed soybean, worm-eaten soybean and damaged soybean. Thirty-nine characteristic parameters from color, texture and shape characteristics were computed after preprocessing the acquired soybean images. The dimensionality of the characteristic parameters was reduced from 39 dimensionalities to 12 dimensionalities using the method of principal component analysis (PCA). MALAB software was used to build a prediction model according to 12 characteristic parameters. The identification accuracies of soybean frogeye, mildewed soybean, damaged soybean and worm-eaten soybean are 96%, 95%, 92%, and 92%, respectively. And the accuracy for heterogeneous soybean seeds with several diseases is 90%. The results show that the prediction model constructed by BP neural network can identify the diseases of soybean seeds. And it is useful to estimate appearance quality of soybean by computer vision applying BP neural network.
Keywords: soybean seed, disease identification, computer vision, BP neural network, characteristic parameters, data reduction
DOI: 10.3965/j.ijabe.20140703.006

Citation: Tan K Z, Chai Y H, Song W X, Cao X D. Identification of diseases for soybean seeds by computer vision applying BP neural network. Int J Agric & Biol Eng, 2014; 7(3): 43－50.

Keywords


soybean seed, disease identification, computer vision, BP neural network, characteristic parameters, data reduction

Full Text:

PDF

References


Feng X. Research on the development strategy of soybean industry in Heilongjiang Province. Beijing: China Science Press, 2011.

Wang J F, Zhao X M, Song Y F, Bao D H, Chen G Y. Effects of appearance quality on the chemical quality of soybean. Heilongjiang Agricultural Sciences, 2006; (5): 23－24. (In Chinese with English abstract)

Hernández-Hierro J M, Valverde J, Villacreces S, Reilly K, Gaffney M, González-Miret M L, et al. Feasibility study on the use of visible-near-infrared spectroscopy for the screening of individual and total glucosinolate contents in broccoli. Journal of Agricultural and Food Chemistry, 2012; (60): 7352－7358.

Fernández-Vázquez R, Stinco C, Meléndez-Martínez A J, Heredia F J, Vicario I M. Visual and instrumental evaluation of orange juice color: a consumers’ preference study. Journal of Sensory Studies, 2011; (26): 436－444.

Zhao D T, Chai Y H, Zhang C L. Research on detection technology of soybean frogeye based on image processing technology. Journal of Northeast Agricultural University, 2010; 41(4): 119－123. (In Chinese with English abstract)

Li C, Wang B, Wang J, Li F. Extracting vein of leaf image based on K-means clustering. Transactions of the CSAE, 2012; (28): 157－162. (In Chinese with English abstract)

Arzate-Vázquez I, Chanona-Pérez J J, de Perea-Flores M J, Calderón-Domínguez G, Moreno-Armendériz M A, Calvo H, et al. Image processing applied toclassification of avocado variety hass (Persea americana Mill.) during theripening process. Food and Bioprocess Technology, 2011; (4): 1307－1313.

ElMasry G, Sun D W. Meat quality assessment using a hyperspectral imaging system. In: Sun, P.D.-W. (Ed.), Hyperspectral Imaging for Food Quality Analysis and Control. Academic Press, San Diego, 2010; 175－240.

Mathiassen J R, Misimi E, Bond M, Veliyulin E, tvik S O. Trends in application of imaging technologies to inspection of fish and fish products. Trends in Food Science and Technology, 2011; (22): 257－275.

Ling Y, Wang Y M, Sun M, Sun H, Zhang X C. Rice appearance quality detection device based on machine vision. Transactions of the CSAM, 2005; 36(9): 89－92. (In Chinese with English abstract)

Yang F, Zhu S P, Qui Q M. Chinese prickly ash appearance quality detection based on computer vision and MATLAB. Transactions of the CSAE, 2008; 24(1): 198－202. (In Chinese with English abstract)

Xu L, Qian M J, Fang R M. Rice processing precision identification method. Transactions of the CSAE,, 1996; 12(3): 34－38. (In Chinese with English abstract)

Jarimopas B. An experimental machine vision system for sorting sweet tamarind. Journal of Food Engineering, 2008; (89): 291－297.

Blasco J, Aleixos N, Moltó E. Machine vision system for auto-matic quality grading of fruit. Biosystems Engineering, 2003; 85(4): 415－423.

Alireza Yadollahinia, Mehdi Jahangiri. Shrinkage of potato slice during drying. Journal of Food Engineering, 2009; (1): 52－58.

Zhan H, Li X Y, Wang W. Chestnut hierarchical detection method based on machine vision. Transactions of the CSAE,, 2010; 26(4): 327－331. (In Chinese with English abstract)

He M, Ma S S, He X D. Potato shape detection based on the Zernike moment. Transactions of the CSAE, 2010; 26(2): 347－350. (In Chinese with English abstract)

Guan Z X, Kang J, Yang B J. Research on rice disease recognition method based on image. The Chinese Rice Science, 2010; 24(5): 497－502. (In Chinese with English abstract)

Xiong Kai, Li Xianghong, Li Yanzhao. Characteristics of corn varieties analysis and recognition based on ANN and PCA. Grain and Oil Food Science and Technology, 2010; 18(4): 1－5. (In Chinese with English abstract)

Han Z Z, Zhao Y G. Study on the detection of peanut quality grading based on computer vision. Agricultural Sciences in China, 2010; 43(18): 3882－3891. (In Chinese with English abstract)

Yang J H, Liu J. Segmentation algorithm based on watershed and automatic seeded region growing image. China Journal of Image and Graphics, 2010; 1(15): 63－68. (In Chinese with English abstract)

Piotr Zapotoczny. Discrimination of wheat grain varieties using image analysis and neural network. Part I. Single kernel texture. Journal of Cereal Science, 2011; (54): 60－80.

W Medina, Skurtys O, Aguilera J M. Study on image analysis application for identification Quinoa seeds (Chenopodium quinoa Willd) geographical provenance. Food Science and Technology, 2010; (43): 238－246.

Siriluk Sansomboonsuk, Nitin Afzulpurkar. Machine vision for rice quality evaluation. Technology and Innovation for sustainable development conference, 2008; 343－346.




Copyright (c)



2023-2026 Copyright IJABE Editing and Publishing Office