首页 > 论文 > 光谱学与光谱分析 > 31卷 > 3期(pp:767-770)

基于SVD的苹果粉质化高光谱散射图像特征提取

Feature Extraction of Hyperspectral Scattering Image for Apple Mealiness Based on Singular Value Decomposition

  • 摘要
  • 论文信息
  • 参考文献
  • 被引情况
  • PDF全文
分享:

摘要

粉质化是影响苹果等级的重要口感参数。 采用高光谱散射图像进行了苹果粉质化的无损检测研究。 利用奇异值分解方法对样本600~1 000 nm共81个波长20 mm范围内的散射图像进行奇异值分解, 将获得的奇异值作为粉质化表征参数, 结合偏微分最小二乘判别分析建立苹果粉质化分类模型。 结果显示, 对不同产地和不同储藏条件下的样本, 其两分类模型(粉质化和非粉质化)的分类精度为76.1%~80.6%, 优于平均值特征提取方法(75.3%~76.5%)。 分析表明, 奇异值分解可以有效地提取高光谱散射图像的特征, 用此特征建立粉质化分类模型可以区分粉质化和非粉质化的苹果, 但分类精度有待于进一步提高。

Abstract

Apple mealiness is an important sensory parameter for classification of apple quality. Hyperspectral scattering technique was investigated for noninvasive detection of apple mealiness. A singular value decomposition (SVD) method was proposed to extract the feature/ or singular values of the hyperspectral scattering images between 600 and 1 000 nm for 20 mm distance including 81 wavelengths. As characteristic parameters of apple mealiness, singular values were applied to develop the classification model coupled with partial least squares discriminant analysis (PLSDA) using the samples from different origin and different storage conditions. The classification accuracies for the two-class (“mealy” and “non-mealy”) model were between 76.1% and 80.6% better than mean method (75.3%~76.5%). The results indicated that SVD method was potentially useful for the feature extraction of hyperspectral scattering images and the model developed with these features can detect the mealy and non-mealy apple, but the classification accuracies need to be improved.

中国激光微信矩阵
补充资料

中图分类号:O657.3

基金项目:国家自然科学基金项目(60805014)和中央高校基本科研业务费专项资金项目(JUSRP20913)资助

收稿日期:2010-05-10

修改稿日期:2010-08-20

网络出版日期:--

作者单位    点击查看

黄敏:江南大学通信与控制工程学院, 江苏 无锡 214122
朱启兵:江南大学通信与控制工程学院, 江苏 无锡 214122

联系人作者:黄敏(huangmzqb@163.com)

备注:黄敏, 1974年生, 江南大学通信与控制工程学院副教授

【1】Barreiro P, Ortiz C, Ruiz-Altisent M, et al. Food and Nutrition Press, 1998, 29(5): 509.

【2】Barreiro P, Ruiz-Cabello J, Ortiz C, et al. Magnetic Resonance Imaging, 1999, 17(2): 275.

【3】Arana I, Jaren C, Arazuri S. Journal of Food Engineering, 2004, 62(4): 399.

【4】Mehinagic E, Royer G, Bertrand D, et al. Postharvest Biology and Technology, 2004, 34(3): 257.

【5】Bechar A, Mizrach A, Barreiro P, et al. Biosystems Engineering, 2005, 91(3): 329.

【6】Valero C, Barreiro P, Ruiz-altisent M, et al. Journal of Texture Studies, 2005, 36(4): 439.

【7】Lu R, Peng Y. Biosystems Engineering, 2006, 93(2): 161.

【8】Lu R. Sens.& Instrumen. Food Qual., 2007, 1(1): 19.

【9】Peng Y, Lu R. Posthavest Biol. Technol., 2008, 48(1): 52.

【10】Qin J, Lu R. Postharvest. Biol. Technol., 2008, 49(3): 355.

【11】Lu R, Huang M, Qin J. Sensing for Agriculture and Food Quality and Safety, 2009, 7315: 291.

引用该论文

HUANG Min,ZHU Qi-bing. Feature Extraction of Hyperspectral Scattering Image for Apple Mealiness Based on Singular Value Decomposition[J]. Spectroscopy and Spectral Analysis, 2011, 31(3): 767-770

黄敏,朱启兵. 基于SVD的苹果粉质化高光谱散射图像特征提取[J]. 光谱学与光谱分析, 2011, 31(3): 767-770

您的浏览器不支持PDF插件,请使用最新的(Chrome/Fire Fox等)浏览器.或者您还可以点击此处下载该论文PDF