摘要： 感兴趣区域(regions of interest, ROIs)的选择及其光谱提取是高光谱图像无损检测分析的关键一步。为快速准确检测羊肉pH，在473～1 000 nm波段，开展了两种不同提取ROIs方法对羊肉pH高光谱检测模型的影响研究。采用“矩形区域法”和“图像分割法”两种ROIs方法分别获得相应的122条羊肉光谱，对比了不同预处理方法对建模效果的影响，并比较了两种ROIs方法下逐步多元线性回归(SMLR)、主成分回归(PCR)和偏最小二乘回归(PLSR)的模型精度。结果表明，提取光谱数据建模中SMLR和PLSR模型效果分别最优。“矩形区域法”提取ROIs对应的SMLR模型校正集的相关系数(Rcal)和均方根误差(RMSEC)分别为0.85和0.085，预测集的相关系数(Rp)和均方根误差(RMSEP)分别为0.82和0.097。“图像分割法”提取ROIs对应的PLSR模型校正集的Rcal和RMSEC分别为0.95和0.050，预测集的Rp和RMSEP分别为0.91和0.071。其次通过比较“矩形区域法”和PCR, SMLR和PLSR三个模型中，“图像分割法”提取的ROIs光谱数据建模效果较优。表明，应用高光谱图像技术结合“图像分割法”提取ROIs快速无损准确检测羊肉pH具有可行性。
关键词：高光谱图像;感兴趣区域(ROIs);羊肉;pH;快速无损检测
Abstract：Selection of Regions of interest (ROIs) and subsequent spectral extraction was a key step of non-destructive detection and analysis based on hyperspectral imaging (HSI). For the rapid and accurate detection of mutton pH, the study on the effects of 2 different ROIs on mutton pH models was carried out in the visible-near infrared region of 473～1 000 nm. 2 ROIs methods of Rectangle Regions (RR) and Image Segmentation (IS) were adopted to extract 122 corresponding representative spectra respectively. The influence of different preprocessing methods and ROIs methods on 3 pH models, including stepwise multiple linear regression (SMLR), principal component regression (PCR) and partial least squares regression (PLSR), was compared and analyzed. The results indicated that SMLR and PLSR model performance was optimal in 3 models established with spectral data extracted from Rectangle Regions (RR) and Image Segmentation (IS) respectively. As for the SMLR model, corresponding to the RR ROIs method, the correlation coefficient (Rcal) and root mean square error (RMSEC) of calibration set was 0.85 and 0.085 respectively, and the correlation coefficient (Rp) and root mean square error (RMSEP) of prediction set was 0.82 and 0.097 respectively. As for the PLSR model, corresponding to the IS ROIs method, the correlation coefficient(Rcal) and root mean square error (RMSEC) of calibration set was 0.95 and 0.050 respectively, and the correlation coefficient (Rp) and root mean square error (RMSEP) of prediction set was 0.91 and 0.071 respectively. By comparing the modeling results of spectral data extracted from 2 ROIs methods, the modeling performances of Image Segmentation (IS) were always better than Rectangle Regions (RR) in all the 3 modeling methods. The study shows that it is feasible to apply hyperspectral imaging technology combined with the ROIs method of Image Segmentation (IS) to accurate, fast and non-destructive detection of mutton pH.
Key words：Hyperspectral imaging (HSI);Regions of interest (ROIs);Mutton;pH;Fast and non-destructive detection
段宏伟，朱荣光*，王 龙，许卫东，马本学 . 感兴趣区域对羊肉pH高光谱检测模型的影响研究 [J]. 光谱学与光谱分析, 2016, 36(04): 1145-1149.
DUAN Hong-wei, ZHU Rong-guang*, WANG Long, XU Wei-dong, MA Ben-xue . Effects of Regions of Interest (ROIs) on Detection Models of Mutton pH Based on Hyperspectral Imaging . SPECTROSCOPY AND SPECTRAL ANALYSIS, 2016, 36(04): 1145-1149.
[1] Feng Y Z, ElMasry G, Sun D W, et al. Food Chemistry, 2013, 138(2-3): 1829. [2] Talens P, Mora L, Morsy N. Journal of Food Engineering, 2013, 117(3): 272. [3] ElMasry G, Sun D W, Allen P. Food Research International, 2011, 44(9): 2624. [4] Kamruzzaman M, ElMasry G, Sun D W, et al. Innovative Food Science and Emerging Technologies, 2012, 16(4): 218. [5] Wu D, Sun D W, He Y. Innovative Food Science and Emerging Technologies, 2012, 16(4): 361. [6] CAI Jian-rong, WAN Xin-min, CHEN Quan-sheng(蔡健荣，万新民，陈全胜). Acta Optica Sinica(光学学报), 2009, 29(10): 2808. [7] ZHU Rong-guang, YAO Xue-dong, GAO Guang-di, et al(朱荣光，姚雪东，高广娣, 等). Transactions of the Chinese Society for Agricultural Machinery(农业机械学报), 2013, 44(7): 165. [8] SONG Yu-lin, PENG Yan-kun, GUO Hui, et al(宋育霖，彭彦昆，郭 辉，等). Spectroscopy and Spectral Analysis(光谱学与光谱分析), 2014, 34(3): 741. [9] Liu D, Pu H, Sun D W, et al. Food Chemistry, 2014, 160(4): 330. [10] Kamruzzaman M, ElMasry G, Sun D W, et al. Food Chemistry, 2013, 141(1): 389. [11] ZHAO Jie-wen, HUI Zhe, HUANG Lin, et al(赵杰文，惠 喆，黄 林，等). Laser & Optoelectronics Progress(激光与光电子学进展), 2013, 50(7): 154. [12] Wang W, Li C, Tollner E W, et al. Journal of Food Engineering, 2012, 109(1): 38.
