高光谱的有监督Isomap-SVM苹果粉质化分类

赵桂林; 朱启兵; 黄敏

doi:doi:10.3788/lop48.101002

激光与光电子学进展, 2011, 48 (10): 101002, 网络出版: 2011-08-22

高光谱的有监督Isomap-SVM苹果粉质化分类

Apple Mealiness Detection Using Supervised Isometric Feature Mapping and Support Vector Machine Based on Hyperspectral Scattering Image

论文大纲

赵桂林 ^*朱启兵黄敏

作者单位

江南大学物联网工程学院，江苏无锡 214122

摘要

苹果粉质化程度是衡量其内部品质的一个重要因素，粉质化造成苹果质量的降低以及商业价值的贬值。高光谱图像技术结合了光谱技术和图像技术的优点，能够无损检测苹果内部品质。提出了有监督等距映射（S-Isomap）和支持向量机（SVM）相结合的用于检测苹果粉质化的新分类方法。S-Isomap-SVM分类方法首先用S-Isomap对高光谱数据作非线性降维，再用SVM对降维后的数据进行分类。对于未知类别的测试样本，采用BP神经网络建模输出的方法，而后结合SVM得到对应的测试精度。这里将S-Isomap-SVM分类方法与SVM以及Isomap-SVM分类方法比较。结果表明，对高光谱数据而言，用S-Isomap-SVM得到的检测精度最高。

Abstract

Apple mealiness is a symptom of internal fruit disorder. Mealiness degrades the quality of apples and reduces their commercial value. Hyperspectral scattering, as a promising technique, combines the advantages of spectroscopy technology and image technology, and can make noninvasive measurement of apple mealiness. A supervised isometric feature mapping (S-Isomap) coupled with support vector machine (SVM) is proposed to detect the mealiness in the apple. S-Isomap is a nonlinear lowering dimension method classifying the dimension reduction of hyperspectral data by SVM. For the unknowned category of the test samples, BP neural network model combined with SVM is used to get the corresponding testing precision. The classification results from S-Isomap-SVM are compared with those obtained using the traditional SVM and Isomap-SVM. The results show that the accuracy of the calibration models obtained with the S-Isomap is higher than that of others.

参考文献

[1] 赵桂林, 朱启兵, 黄敏. 基于高光谱图像技术的苹果粉质化LLE-SVM分类［J］. 光谱学与光谱分析, 2010, 30(10): 2739～2743

Zhao Guilin, Zhu Qibing, Huang Min. LLE-SVM classification of apple mealiness based on hyperspectral scattering image technique［J］. Spectroscopy and Spectral Analysis, 2010, 30(10): 2739～2743

[2] Min Huang, Renfu Lu. Apple mealiness detection using hyperspectral scattering technique［J］. Postharvest Biol. Technol., 2010, 58(3): 168～175

[3] 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): 91～94

Guo Enyou, Liu Muhua, Zhao Jiewen et al.. Nondestructive detecting of sugar content on navel orange with hyperspectral imaging［J］. Transactions of the Chinese Society for Agricultural Machinery, 2008, 39(5): 91～94

[4] 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

Hong TianSheng, Qiao Jun, Wang Ning et al.. Nondestructive inspection of chinese pear quality based on hyperspectral imaging technique［J］. Transactions of the Chinese Society for Agricultural Engineering, 2007, 23(2): 151～155

[5] 陈全胜, 张燕华, 万新民等. 基于高光谱成像技术的猪肉嫩度检测研究［J］. 光学学报, 2010, 30(9): 2602～2607

Chen Quansheng, Zhang Yanhua, Wan Xinmin et al.. Study on detection of pork tenderness using hyperspectral imaging technique［J］. Acta Optica Sinica, 2010, 30(9): 2602～2607

[6] 刘小刚, 赵慧洁, 李娜. 基于多重分形谱的高光谱数据特征提取［J］. 光学学报, 2009, 29(3): 844～847

Liu Xiaogang, Zhao Huijie, Li Na. Feature extraction based on multifractal spectrum for hyperspectral data［J］. Acta Optica Sinica, 2009, 29(3): 844～847

[7] 王泽杰. 两类非线性降维流形学习算法的比较分析［J］. 上海工程技术大学学报, 2008, 22(1): 54～59

Wang Zejie. Comparison and analysis of two categoriesof manifold learning algorithms for nonlinear dimensionality reduction［J］. J. Shanghai University of Engineering Science, 2008, 22(1): 54～59

[8] Jianwei Qin, Renfu Lu, Yankun Peng. Internal quality evaluation of apples using spectral absorption and scattering properties［C］. SPIE, 2007, 6761: 67610M

[9] Renfu Lu. Nondestructive measurement of firmness and soluble solids content for apple fruit using hyperspectral scattering images［J］. Sensing Inst. Food Quality & Safety, 2007, 1(1): 19～27

[10] Renfu Lu, Min Huang, Jianwei Qin. Analysis of hyperspectral scattering characteristics for predicting apple fruit firmness and soluble solids content［C］. SPIE, 2009, 7315: 73150I

[11] Renfu Lu, Yankun Peng. Hyperspectral scattering for assessing peach fruit firmness［J］. Biosystems Engineering, 2006, 93(2): 161～171

[12] 杨辉华, 覃锋, 王义明等. NIR光谱的Isomap-PLS非线性建模方法［J］. 光谱学与光谱分析, 2009, 29(2): 322～326

Yang Huihua, Qin Feng, Wang Yiming et al.. Isomap-PLS nonlinear modeling method for near infrared spectroscopy［J］. Spectroscopy and Spectral Analysis, 2009, 29(2): 322～326

[13] 朱明旱, 罗大庸, 王一军. 基于监督式等距映射的人脸和表情识别［J］. 光电工程, 2009, 36(1): 146～150

Zhu Minghan, Luo Dayong, Wang Yijun. Face and expression recognition based on supervised isomap［J］. Opto-Electronic Engineering, 2009, 36(1): 146～150

[14] 陈秀丽, 王桂文, 陶站华等. 基于PCA和BP神经网络的地中海贫血红细胞拉曼光谱判别［J］. 中国激光, 2009, 36(9): 2448～2454

Chen Xiuli, Wang Guiwen, Tao Zhanhua et al.. Raman spectral discrimination of thalassemia erythrocytes based on PCA arithmetic and BP network model［J］. Chinese J. Lasers, 2009, 36(9): 2448～2454

赵桂林, 朱启兵, 黄敏. 高光谱的有监督Isomap-SVM苹果粉质化分类[J]. 激光与光电子学进展, 2011, 48(10): 101002. Zhao Guilin, Zhu Qibing, Huang Min. Apple Mealiness Detection Using Supervised Isometric Feature Mapping and Support Vector Machine Based on Hyperspectral Scattering Image[J]. Laser & Optoelectronics Progress, 2011, 48(10): 101002.

高光谱的有监督Isomap-SVM苹果粉质化分类

关于本站 Cookie 的使用提示

全站搜索

高光谱的有监督Isomap-SVM苹果粉质化分类

相关论文

相关资讯

关于本站 Cookie 的使用提示

全站搜索