利用高光谱近红外波段的腊肠品质分级研究  

Study on the Quality Classification of Sausage with Hyperspectral Infrared Band

作　　者：龚爱平[1] 王琦[2] 邵咏妮[2] 

机构地区：[1]深圳信息职业技术学院机电学院,广东深圳518172 [2]浙江大学生物系统工程与食品科学学院,浙江杭州310058

出　　处：《光谱学与光谱分析》2017年第8期2556-2559,共4页Spectroscopy and Spectral Analysis

基　　金：深圳市战略新兴产业发展专项(JCYJ20150417094158023);国家自然科学基金项目(31402318);浙江省公益性项目(2016C32055)资助

摘　　要：高光谱图像作为一种快速无损的分析技术在食品行业中得到广泛应用。腊肠(sausage)是一个非常古老的食物生产和肉食保存技术,中国的腊肠有着悠久的历史。我国商业行业标准SB/T10003—92按腊肠的理化特征,将腊肠分为优级,一级,二级。针对腊肠在近红外(NIR)波段的高光谱信息,采用连续投影算法(SPA)进行特征波段的提取,分别建立了腊肠等级判别模型PLSR(基于全波段的模型)与SPA-MLR(基于特征波段的模型)。其中,基于特征波长的SPA-MLR模型的预测决定系数达到0.929,判别正确率100%。表明采用高光谱图像的近红外波谱信息能够实现腊肠品质的快速、无损分析。Hyperspectral image is a kind of rapid and nondestructive analysis technology widely used in the food industry.Chinese sausage has a long history,which is a very ancient carnivorous food production and preservation technology.According to the physicochemical characteristics of sausage,Chinese commercial industry standard divided sausage into top-class,first-class and second-class.The near infrared（NIR）hyperspectral band information of sausage applied the successive projection algorithm（SPA）to extract the characteristic bands,and then respectively established grading model of PLSR（all band）and SPA-MLR（characteristic band）.The decision coefficient of the SPA-MLR model based on the characteristic wavelength was 0.929,and the correct rate was 100%.The results showed that the near infrared spectral information of hyperspectral image could be used for fast and nondestructive analysis of sausage.

关 键 词：广式腊肠 近红外(NIR)波谱信息 连续投影算法(SPA) 偏最小二乘法算法(PLSR) 

分 类 号：TS251.6[轻工技术与工程—农产品加工及贮藏工程]