Open AccessNondestructive determination of soluble solids content and pH in red bayberry (Myrica rubra) based on color space
Author(s) -
Jie Feng,
Lingling Jiang,
Jialei Zhang,
Hong Zheng,
Yanfang Sun,
Shaoning Chen,
Meilan Yu,
Wei Hu,
Shi De-fa,
Xiaohong Sun,
Hongfei Lü
Publication year - 2020
Publication title -
journal of food science and technology/journal of food science and technology
Language(s) - English
Resource type - Journals
SCImago Journal Rank - 0.656
H-Index - 68
eISSN - 0975-8402
pISSN - 0022-1155
DOI - 10.1007/s13197-020-04493-4
Subject(s) - myrica rubra , ycbcr , color space , mathematics , mean squared error , partial least squares regression , artificial intelligence , chemistry , botany , statistics , computer science , color image , image processing , image (mathematics) , biology
Color has strong relationship with food quality. In this paper, partial least square regression (PLSR) and least square-support vector machine (LS-SVM) models combined with six different color spaces (NRGB, CIELAB, CMY, HSI, I1I2I3, and YCbCr) were developed and compared to predict pH value and soluble solids content (SSC) in red bayberry. The results showed that PLSR and LS-SVM models coupled with color space could predict pH value in red bayberry (r = 0.93-0.96, RMSE = 0.09-0.12, MAE = 0.07-0.09, and MRE = 0.04-0.06). In addition, the minimum errors (RMSE = 0.09, MAE = 0.07, and MRE = 0.04) and maximum correlation coefficient value (r = 0.96) were found with the PLSR based on CMY, I1I2I3, and YCbCr color spaces. For predicting SSC, PLSR models based on CIELAB color space (r = 0.90, RMSE = 0.91, MAE = 0.69 and MRE = 0.12) and HSI color space (r = 0.89, RMSE = 0.95, MAE = 0.73 and MRE = 0.13) were recommended. The results indicated that color space combined with chemometric is suitable to non-destructively detect pH value and SSC of red bayberry.