手机数字图像与甘薯β-胡萝卜素含量间相关性

Correlation analysis of mobile phone digital images and β-carotene content in sweet potato

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(R2)达到0.947,模型的预测相关系数(rp)、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。

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 ofβ-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.