FUDT在苹果近红外光谱分类中的应用.pdf

Computer Engineering and Applications 计算机工程与应用 FUDT 在苹果近红外光谱分类中的应用 1 2 2 武斌 , 马桂香 , 武小红 1 2 2 WU Bin , MA Guixiang , WU Xiaohong 1. 滁州职业技术学院 信息工程系，滁州 239000 2. 江苏大学电气信息工程学院, 镇江 212013 1. Department of Information Engineering, ChuZhou Vocational Technology College, ChuZhou 239000,China 2. School of Electrical and Information Engineering, Jiangsu University, Zhenjiang 212013, China WU Bin, MA Guixiang, WU Xiaohong, Classification of apples using near infrared spectroscopy with FUDT. Computer Engineering and Applications Abstract ： Classification of apples is an important link in postharvest commercialization processing. To realize the non-destructive, rapid and effective discrimination of apple fruits, the near infrared reflectance spectra of four varieties of apples were collected using near infrared spectroscopy, reduced by principal component analysis (PCA) and used to extract the discriminant information by linear discriminant analysis (LDA), quadratic discriminant analysis (QDA), fuzzy uncorrelated discriminant transformation (FUDT) and Foley-Sammon discriminant analysis. Finally k-nearest neighbor finished the classification. The classification results showed that FUDT could extract the discriminant information of NIR spectra more effectively, and achieved the highest classification accuracy. Key words ：Classification of Apples; Near Infrared Spectroscopy; Linear Discriminant Analysis; Quadratic Discriminant analysis; Fuzzy Discriminant Analysis; Foley-Sammon Discriminant Analysis 摘 要：苹果的分类是苹果采收后商品化处理的重要环节。为了快速、无损和有效地实现苹果的分类，该文利用近 红外光谱技术采集四种苹果的近红外反射光谱，用主成分分析对高维的近红外光谱进行降维处理，然后分别运行 线性判别分析，二次判别分析，模糊非相关判别转换和Foley-Sammon 判别分析提取鉴别信息，最后用k-近邻分 类器进行分类。分类结果表明，模糊非相关判别转换能更好地提取苹果近红外光谱的品种鉴别信息，达到了最高 的分类准确率。 关键词：苹果分类; 近红外光谱; 线性判别分析; 二次判别分析; 模糊非相关判别转换; Foley-Sammon 判别分析 doi:10.3778/j.issn.1002-8331.1411-0203