基于高光谱图像技术的固态发酵中芽孢杆菌的快速识别.pdfVIP

现代食品科技 Modern Food Science and Technology 2016, Vol.32, No.4 基于高光谱图像技术的固态发酵中芽孢杆菌的 快速识别 邹小波，申婷婷，石吉勇，朱瑶迪，胡雪桃，周煦成 （江苏大学食品与生物工程学院，江苏镇江 212013） 摘要：利用高光谱图像技术结合模式识别方法，研究了镇江香醋固态发酵中产酸芽孢杆菌的快速识别方法。筛选 3 种芽孢杆菌 为标准菌,以标准菌生长 12 h 的菌落为研究对象，利用高光谱成像系统采集图像：提取感兴趣区域（20×20 ）单菌落平均光谱共 120 条，并 SNV 预处理，采用主成分分析（PCA ）从每幅图像优选3 幅特征图像，并从每幅特征图像提取4 个基于灰度共生矩阵的纹理 特征变量；对光谱和图像纹理的特征变量均进行 PCA ，分别提取合适的主成分构建BP-ANN 和 KNN 识别模型。其中，光谱模型识 别效果优于图像模型，且BP-ANN 光谱模型识别效果最优，对校正集和预测集样本的识别率分别为 98.70%和 97.78%，主成分因子数 为 5。研究表明，菌落内部特征是识别菌种属的关键，且利用高光谱图像技术识别细菌具有可行性，且快速简便。 关键词：镇江香醋；芽孢杆菌；高光谱图像技术；菌种鉴定；光谱分析；快速识别 文章篇号：1673-9078(2016)4-235-240 DOI: 10.13982/j.mfst.1673-9078.2016.4.037 Quick Identification of Bacillus in the Solid-state Fermentation Based on Hyperspectral Imaging Technology ZOU Xiao-bo, SHEN Ting-ting, SHI Ji-yong, ZHU Yao-di, HU Xue-tao, ZHOU Xu-cheng (School of Food and Biological Engineering, Jiangsu University, Zhenjiang 212013, China) Abstract: Hyperspectral imaging technology combined with pattern recognition methods were used to rapidly identify the types of acid-producing Bacillus in the solid-state fermentation for the production of Zhenjiang balsamic vinegar. First, three species of Bacillus were screened as standard bacteria. After 12 h of growth, the standard bacterial colonies were used as study objects and images were collected using a hyperspectral imaging system. Next, a total of 120 average spectra of an area of interest (20 × 20) in a single colony were extracted and processed by standard normal variate transform. Principal component analysis (PCA) was used to select three images with a