【摘要】 该研究旨在探讨手机数字图像信息与甘薯β-胡萝卜素含量间的关系。采用智能手机采集甘薯块根切片的图像,对图像的RGB信息与甘薯β-胡萝卜素含量间的关系进行了研究,并建立了预测模型。研究发现,甘薯β-胡萝卜素含量与甘薯切片图像的绿值(G)间呈极强的负相关,与蓝值(B)呈中等强度负相关,红值(R)与β-胡萝卜素含量之间无相关性。采用对数函数对G值与β-胡萝卜素含量间的关系进行拟合,模型的拟合确定系数(R~2)达到0. 947,模型的预测相关系数(r_p)、预测均方误差(RMSEP)和标准偏差比(SDR)分别为0. 983、0. 819和5. 269。结果表明,手机数字图像可以反映甘薯β-胡萝卜素含量间的差异,使用图像的颜色值信息可以较为精确地估计甘薯β-胡萝卜素含量,为甘薯品质快速检测提供了新的思路。更多还原

【Abstract】 The aim of this study was to explore the relationship between mobile phone digital images and β-carotene content in sweet potato. A smart phone was used to collect the image of sweet potato slices. Moreover,the relationship between the RGB information of the images and the content of β-carotene in sweet potato was studied,and predict models were calibrated. The results showed that the content of β-carotene in sweet potato had a strong negative correlation with green(G) value,and a moderate negative correlation with blue(B) value. There was no correlation betweenβ-carotene content and red(R) value of sweet potato slice images. The logarithmic function was used to fit the relationship between G value and β-carotene content. The coefficient of determination(R~2) of the model reached 0. 947,the predicted correlation coefficients(r_p),root mean square error of prediction(RMSEP) and standard deviation ratio(SDR) of the model were 0. 983,0. 819 and 5. 269,respectively. Overall,digital images of mobile phone can reflect the differences of β-carotene content in sweet potato,and the RGB information of digital image can accurately estimate the β-carotene content of sweet potato,which provides a new idea for rapid detection of sweet potato quality.更多还原