Detection of navel oranges canker based on hyperspectral imaging technology

被引：0

作者：

Li J. ^{[1
]}

Rao X. ^{[1
]}

Ying Y. ^{[1
]}

Wang D. ^{[1
]}

机构：

[1] College of Biosystems Engineering and Food Science, Zhejiang University

来源：

Nongye Gongcheng Xuebao/Transactions of the Chinese Society of Agricultural Engineering | 2010年 / 26卷 / 08期

关键词：

Canker; Defects inspection; Dual-band ratio; Hyperspectral imaging; Image recognition; Navel oranges; Principal component analysis;

D O I：

10.3969/j.issn.1002-6819.2010.08.038

中图分类号：

学科分类号：

摘要：

Feature bands principal component analysis method and band ratio algorithm were proposed to fast differentiate citrus canker from normal fruit skin and other surface defects based on hyperspectral imaging technology. Navel oranges with cankerous, normal and other nine kinds of common defects were studied. First, region of interests (ROIs) spectral features of various defected peel areas were analyzed and combined with principal component analysis method to determined five optimal bands (i.e. 630, 685, 720, 810 and 875 nm). Next, principal component analysis was again performed based on feature wavelengths and the fifth principal component (PC-5) was used to classify and identify canker lesions on navel oranges. The overall classification success rate was 80% regardless of the presence of other confounding defects. In order to improve classification success rate, feature bands principal component analysis method and band ratio algorithm were combined to detect canker on the surface of navel oranges with an accuracy of 95.4%. The study results show that the hyperspectral imaging technology can be used to effectively classify and identify navel oranges with canker lesions.

引用

页码：222 / 228

页数：6

共 15 条

[1]

(2007)

[2]

Schubert T.S., Rizvi S.A., Sun X., Et al., Meeting the challenge of eradicating citrus canker in Florida-Again, Plant Disease, 85, 4, pp. 340-356, (2001)

[3]

Ying Y., Rao X., Zhao Y., Et al., Application of machine vision technique to quality automatic identification of agricultural products, Transection of the CSAE, 16, 1, pp. 103-108, (2000)

[4]

Li P., Zhu J., Liu Y., Et al., Application and developing trend of computer vision technology in detection and classification of agricultural products, Acta Agriculturae Universitatis Jiangxiensis, 27, 5, pp. 796-800, (2005)

[5]

He X., Yuan H., Research advances on the occurrence and resistance of citrus bacterial canker disease, Chinese Agricultural Science Bulletin, 23, 8, pp. 409-412, (2007)

[6]

Aleixos N., Blasco J., Navarron F., Et al., Multispectral inspection of citrus in real-time using machine vision and digital signal processors, Computers and Electronics in Agriculture, 33, 2, pp. 121-137, (2002)

[7]

Blasco J., Aleixos N., Gomez J., Et al., Citrus sorting by identification of the most common defects using multispectral computer vision, Journal of Food Engineering, 83, 3, pp. 384-393, (2007)

[8]

Gomez-Sanchis J., Gomez-Chova L., Aleixos N., Et al., Hyperspectral system for early detection of rottenness caused by Penicillium digitatum in mandarins, Journal of Food Engineering, 89, 1, pp. 80-86, (2008)

[9]

Xue L., Li J., Liu M., Detecting pesticide residue on navel orange surface by using hyperspectral imaging, Acta Optica Sinica, 28, 12, pp. 2277-2280, (2008)

[10]

Cai J., Wang J., Chen Q., Et al., Detection of rust in citrus by hyperspectral imaging technology and band ratio algorithm, Transactions of the CSAE, 25, 1, pp. 127-131, (2009)

← 1 2 →