Nondestructive inspect of apple quality with hyperspectral imaging

Sun Mei; Chen Xinghai; Zhang Heng; Chen Haixia

Image cubes containing continuous spectral waveband information, in which the image information could be used for external attribute inspection while the spectral information could be applied to the internal attribute inspection,could be obtained from implementing a hyperspectral image technology which combines the advantages of computer vision and spectroscopy． Apples were adopted as the experimental object. A hyperspectral imaging system with the wavelength range of 400-1 000 nm was built for detecting bruises. The hyperspectral imaging system was used as a powerful tool to determine the effective wavelengths that could be used for the detection of bruises on apples. The optimal wavelength region 550-950 nm for bruise detection was selected by the Principal component analysis (PCA), which is a very effective method for data dimension reduction and feature extraction of the hyperspectral data cube. The effective wavelengths 714 nm with weighing coefficients at peaks was determined using the loading coefficients of the PC4 image of PCA on 400-1 000 nm.

1. School of Computer and Information Engineering,Beijing Technology and Business University,Beijing 100048,China;

2. Zolix Instruments Co.,Ltd,Beijing 101102,China

Received Date: 2013-08-05

Rev Recd Date: 2013-09-03

Publish Date: 2014-04-25

Key words:

Abstract: Image cubes containing continuous spectral waveband information, in which the image information could be used for external attribute inspection while the spectral information could be applied to the internal attribute inspection,could be obtained from implementing a hyperspectral image technology which combines the advantages of computer vision and spectroscopy． Apples were adopted as the experimental object. A hyperspectral imaging system with the wavelength range of 400-1 000 nm was built for detecting bruises. The hyperspectral imaging system was used as a powerful tool to determine the effective wavelengths that could be used for the detection of bruises on apples. The optimal wavelength region 550-950 nm for bruise detection was selected by the Principal component analysis (PCA), which is a very effective method for data dimension reduction and feature extraction of the hyperspectral data cube. The effective wavelengths 714 nm with weighing coefficients at peaks was determined using the loading coefficients of the PC4 image of PCA on 400-1 000 nm.

HTML

Reference (29)

[1]
[2]	The Ministry of Agriculture. The international apple trade situation and China apple export situation of [J]. Chinese Fruit Industry Information, 2006(4): 6-8. (in Chinese) 农业部. 国际苹果贸易概况与我国苹果出口情况[J]. 中国果业信息, 2006(4): 6-8.
[3]	Mo Runyang. Nondestructive testing technology in fruit quality evaluation in the application of [J]. In Physics and Technology, 2004, 33 (11): 848-851. (in Chinese) 莫润阳. 无损检测技术在水果品质评价中的应用[J]. 物理学和高新技术, 2004, 33 (11): 848-851.
[4]
[5]
[6]	Zhang Xiang, Zhang Jianqi, Qin Hanlin, et al. Anomaly detection for hyperspectral image based on multiresolution decomposition [J]. Infrared and Laser Engineering, 2011, 40(3): 570-575. (in Chinese) 张翔, 张建奇, 秦翰林, 等. 用多分辨率分解的高光谱图像异常检测[J]. 红外与激光工程, 2011, 40(3): 570-575.
[7]	Liu Y, Chen Y R, Wang C Y, et a1. Development of hyperspectral imaging technique for the detection of chilling injury on cucumbers spectral and image analysis [J]. Applied Engineering in Agriculture, 2006, 22(1): 101-111．
[8]
[9]	Xu Hong, Wang Xingjun. Applications of multi spectral hyperspectral imaging technologies in military [J]. Infrared and Laser Engineering, 2007, 36(1): 13-17. (in Chinese) 许洪, 王向军. 多光谱、超光谱成像技术在军事上的应用[J]. 红外与激光工程, 2007, 36(1): 13-17.
[10]
[11]	Wang Jingli. Mamimum band screening and its application to hyperspectral target dection[J]. Infrared and Laser Engineering, 2012, 41(6): 1514-1518. (in Chinese) 王静荔. 波段最大筛选法及其在高光谱目标探测中的应用[J]. 红外与激光工程, 2012, 41(6): 1514-1518.
[12]
[13]	Liu Y, Ying Y. Use of FT-NIR spectrometry in non-invasive measurements of internal quality of 'Fuji'apples[J]. Postharvest Biology and Technology, 2005, 37: 65-71.
[14]
[15]
[16]	He Yuanlei, Liu Daizhi, Wang Jingli, et al. Independent component analysis-based band selection for hyperspectral imagery [J]. Infrared and Laser Engineering, 2012, 41 (3): 818-824. (in Chinese) 何元磊, 刘代志, 王静荔, 等. 利用独立成分分析的高光谱图像波段选择方法[J]. 红外与激光工程, 2012, 41 (3): 818-824.
[17]	Polder G, Van der Heijden G W A M, Young I T. Spectral image analys is for measuring ripeness of tomatoes [J]. American Society of Agricultural Engineers, 2002, 45 (4): 1155-1161.
[18]
[19]
[20]	Lu R． Detection of bruises on apples using near-infrared hyperspectral imaging [J]． Transactions of ASAE, 2003, 46 (2): 523-530.
[21]
[22]	Hong Tiansheng, Qiao Jun, Ning Wang, et al. Non-destructive inspection of Chinese pear quality based on hyperspectral imaging technique [J]. Transactions of the Chinese Society of Agricultural Engineering, 2007, 23 (2): 151-155. (in Chinese) 洪添胜, 乔军, 王宁, 等. 基于高光谱图像技术的雪花梨品质无损检测[J]. 农业工程学报, 2007, 23(2): 151-155.
[23]	Masry E G． Hyperspectral imaging for nondestructive deterruination of some quality at tributes for straw berry [J]． Journal of Food Engineering, 2007, 81: 98-107．
[24]
[25]
[26]	NagataM, Tallada J G, Kobayashi T, et al. Predictingm aturity quality parameters of strawberries using hyperspectral imaging [C]//American Society of Agricultural Engineers Annual Meeting, 2004: 043033.
[27]	Sivakumar S S, Qiao J, Gariepy Y, et al. Detectingm aturity parameters of mango using hyperspectral imag ing techology[C]//American Society of Agricultural Engineers Annual Meeting, 2006: 066183.
[28]
[29]	Guo Enyou, Liu Muhua, Zhao Jienwen, et al. Nondestructive detection of sugar content on Navel orange with hyperspectral imaging[J]. Transactions of the CSAM, 2008, 39(5): 91-93, 103. (in Chinese) 郭恩有, 刘木华, 赵杰文, 等. 脐橙糖度的高光谱图像无损检测技术[J]. 农业机械学报, 2008, 39(5): 91-93, 103.

Nondestructive inspect of apple quality with hyperspectral imaging

Abstract

References

Proportional views

通讯作者: 陈斌, bchen63@163.com

Article Metrics

Related

Proportional views