Caballero Daniel, Antequera Teresa, Caro Andrés, Ávila María Del Mar, G Rodríguez Pablo, Perez-Palacios Trinidad
Food Technology, Meat and Meat Products Research Institute, University of Extremadura, 10003, Cáceres, Spain.
Department of Computer Science, Meat and Meat Products Research Institute, University of Extremadura, 10003, Cáceres, Spain.
J Sci Food Agric. 2017 Jul;97(9):2942-2952. doi: 10.1002/jsfa.8132. Epub 2016 Dec 7.
Magnetic resonance imaging (MRI) combined with computer vision techniques have been proposed as an alternative or complementary technique to determine the quality parameters of food in a non-destructive way. The aim of this work was to analyze the sensory attributes of dry-cured loins using this technique. For that, different MRI acquisition sequences (spin echo, gradient echo and turbo 3D), algorithms for MRI analysis (GLCM, NGLDM, GLRLM and GLCM-NGLDM-GLRLM) and predictive data mining techniques (multiple linear regression and isotonic regression) were tested.
The correlation coefficient (R) and mean absolute error (MAE) were used to validate the prediction results. The combination of spin echo, GLCM and isotonic regression produced the most accurate results. In addition, the MRI data from dry-cured loins seems to be more suitable than the data from fresh loins.
The application of predictive data mining techniques on computational texture features from the MRI data of loins enables the determination of the sensory traits of dry-cured loins in a non-destructive way. © 2016 Society of Chemical Industry.
磁共振成像（MRI）与计算机视觉技术相结合，已被提议作为一种以非破坏性方式确定食品质量参数的替代或补充技术。这项工作的目的是使用该技术分析干腌猪腰的感官属性。为此，测试了不同的MRI采集序列（自旋回波、梯度回波和涡轮3D）、MRI分析算法（灰度共生矩阵、归一化灰度共生矩阵、灰度游程长度矩阵和灰度共生矩阵 - 归一化灰度共生矩阵 - 灰度游程长度矩阵）以及预测性数据挖掘技术（多元线性回归和保序回归）。
使用相关系数（R）和平均绝对误差（MAE）来验证预测结果。自旋回波、灰度共生矩阵和保序回归的组合产生了最准确的结果。此外，干腌猪腰的MRI数据似乎比新鲜猪腰的数据更合适。
将预测性数据挖掘技术应用于猪腰MRI数据的计算纹理特征，能够以非破坏性方式确定干腌猪腰的感官特性。© 2016化学工业协会。
