Measurement of total viable count on chilled mutton surface based on hyperspectral imaging technique

ZHENG Caiying; GUO Zhonghua; JIN Ling

doi:10.7510/jgjs.issn.1001-3806.2015.02.029

In order to obtain non-destructive assessment of total viable count (TVC) on chilled mutton surface, different kinds of recognition models were established based on different wavelength range hyperspectral imaging systems, then theoretical analysis and experiments were carried out. The hyperspectral imaging information of chilled mutton samples were collected in the region of 400nm~1100nm and 900nm~1700nm. The predictive models were established by partial least squares (PLS) and artificial neural network (back propagation artificial neural network and radial basis function artificial neural network (RBF-ANN)). The results show that the model which is on the basis of artificial neural network is better than PLS to predict TVC of chilled mutton surface. The best prediction result is based on the RBF-ANN model, the correlation coefficient and the root mean square error of prediction are 0.9872, 0.9988 and 0.8210, 0.2507 in the region of 400nm~1100nm and 900nm~1700nm. Meanwhile, the region of 900nm~1700nm is the best modeling wavelength. Therefore, hyperspecctral imaging technique can be used for the non-destructive detection of total viable count on chilled mutton surface.

Measurement of total viable count on chilled mutton surface based on hyperspectral imaging technique

Corresponding author: GUO Zhonghua, guozhh@nxu.edu.cn;

1. School of Physics and Electronic Information Engineering, Ningxia University, Yinchuan 750021, China;

2. Ningxia Key Laboratory of Intelligent Sensing for Desert Information, Yinchuan 750021, China

Received Date: 2014-02-20

Accepted Date: 2014-05-04

Available Online: 2015-03-25

Abstract: In order to obtain non-destructive assessment of total viable count (TVC) on chilled mutton surface, different kinds of recognition models were established based on different wavelength range hyperspectral imaging systems, then theoretical analysis and experiments were carried out. The hyperspectral imaging information of chilled mutton samples were collected in the region of 400nm~1100nm and 900nm~1700nm. The predictive models were established by partial least squares (PLS) and artificial neural network (back propagation artificial neural network and radial basis function artificial neural network (RBF-ANN)). The results show that the model which is on the basis of artificial neural network is better than PLS to predict TVC of chilled mutton surface. The best prediction result is based on the RBF-ANN model, the correlation coefficient and the root mean square error of prediction are 0.9872, 0.9988 and 0.8210, 0.2507 in the region of 400nm~1100nm and 900nm~1700nm. Meanwhile, the region of 900nm~1700nm is the best modeling wavelength. Therefore, hyperspecctral imaging technique can be used for the non-destructive detection of total viable count on chilled mutton surface.

HTML

Reference (16)

[1]	WU D, SHAO K , DA L, et al. Current production and research development of foreign and domestic meat goats industry [J].Animal Husbandry and Feed Science, 2010, 31(6):124-126(in Chinese).
[2]	ZHOU J, YIN J J, HOU Y Z, et al. Development of methods for rapid detection technology of total bacteria in food[J]. Food Research and Development, 2010, 31(12):276-280(in Chinese).
[3]	TAO F F ,WANG W, LI Y Y, et al. A rapid nondestructive measurement method for assessing the total plate count on chilled pork surface[J]. Spectroscopy and Spectral Analysis, 2010, 30(12):3405-3409(in Chinese).
[4]	ZHANG Y,CHENG Y,YAN Y T, et al. Study on characteristics of fluorescent spectra of several kinds of heated common edible oil [J].Laser Technology, 2013,37(1):109-113(in Chinese).
[5]	ZHU R G, MA B X , GAO Z J, et al. Research progress in nondestructive detection of livestock product quality based on hyperspectral imaging[J]. Laser & Infrared, 2011, 41(10):1067-1071(in Chinese).
[6]	PARK B, LAWRENCE K C, WINDHAM W R. Performance of hyperspectral imaging system for poultry surface fecal contaminant detection [J]. Journal of Food Engineering, 2006, 75(3): 340-348.
[7]	CHEN Q S, ZHANG Y H, WAN X M, et al. Study on detection of pork tenderness using hyperspectral imaging technique [J]. Acta Optica Sinica, 2010,30(9):2602-2607(in Chinese).
[8]	QIAO J, NGADI M, WANG N, et al. Pork quality and marbling level assessment using ahyperspectral imaging system [J]. Journal of Food Engineering, 2007, 83(1): 10-16.
[9]	WU J H, PENG Y K, JIANG F C, et al. Hyperspectral scattering profiles for prediction of beef tenderness[J]. Transactions of the Chinese Society for Agricultural Machinery, 2009, 40(12): 135-138(in Chinese).
[10]	PENG Y K, ZHANG J, WANG W, et al. Potential prediction of the microbial spoilage of beef using spatially resolved hyperspectral scattering profiles [J]. Journal of Food Engineering, 2011, 102(2): 163-169.
[11]	WANG W, PENG Y K, ZHANG X L, et al. Study on modeling method of total viable count of fresh pork meat based on hyperspectral imaging system.Spectroscopy and Spectral Analysis, 2010, 30(2): 411-415(in Chinese).
[12]	WEI B L, CHEN G X, XU J C, et al. Recognition of alcohol-free beer by fluorescent spectroscopy and probabilistic neural network[J]. Laser Technology, 2010, 34(6):794-797(in Chinese).
[13]	XUE L, LI J, LIU M H. Detecting pesticide residue on navel orange surface by using hyperspectral imaging [J].Acta Optica Sinica, 2008, 28(12):2277-2280(in Chinese).
[14]	GAMAL E, SUN D W, PAUL A. Near-infrared hyperspectral imaging for predicting colour, pH and tenderness of fresh beef[J]. Journal of Food Engineering, 2012, 110(1):127-140.
[15]	BARBIN D F, ELMASRY G, SUN D W, et al. Non-destructive assessment of microbial contamination in porcine meat using NIR hyperspectral imaging[J]. Innovative Food Science and Emerging Technologies, 2013,17(1):180-191.
[16]	FU X B. Short-wave near infrared detection technology under complex conditions [D].Changchun:Jinlin University, 2012:62-69(in Chinese).

Measurement of total viable count on chilled mutton surface based on hyperspectral imaging technique

Abstract

References

Proportional views

通讯作者: 陈斌, bchen63@163.com

Proportional views