OBJECTIVE

2

To explore the discrimination of processing degree of

Zingiber officinale

charcoal and the correlation between color and component content based on machine vision system， and provide reference for quality evaluation and processing degree control of

Z. officinale

charcoal.

METHODS

2

High-performance liquid chromatography method was used to determine the contents of 5 components in

Z. officinale

charcoal and its different processed products， such as 6-gingerol， 8-gingerol， 10-gingerol， 6-shogaol， gingerone. Machine vision system was used to obtain the image of the decoction pieces and extract the color features of the decoction pieces in RGB， L

*

a

*

b

*

and HSV color spaces. Machine learning methods， such as principal component analysis （PCA）， linear discriminant analysis （LDA）， partial least squares-discriminant analysis （PLS-DA） and support vector machine （SVM）， were used to establish qualitative identification model for

Z. officinale

charcoal processed products of different processing degree. The correlation between the color eigenvalues and the contents of measured 5 components were analyzed， and the color-component content prediction model was established.

RESULTS

2

With the deepening of processing， gingerone was produced after processing and the content firstly increased and then decreased， and the content of gingerone in standard carbon was the highest； the contents of 6-gingerol， 8-gingerol and 10-gingerol decreased gradually； the content of 6-shogaol increased firstly and then decreased. The prediction accuracy of qualitative discriminant model， which was established on the basis of objective quantization of image and color combined with LDA and SVM of supervised discriminant pattern recognition method， reached 100% in cross-validation training and 95.83% in the external validation. Content prediction model of 5 components was established on the basis of objective quantization of image and color combined with SVM， the RPD values were all greater than 2， the

R

2

P

and

R

2

C

values of gingerone were 0.633 9 and 0.683 3， and the values of other components were all greater than 0.75， indicating SVM had good prediction ability for the contents of 4 components except for gingerone.

CONCLUSIONS

2

The machine vision system is excellent for the discrimination of the processing degree of

Z. officinale

charcoal and the content prediction， which can provide a reference for the quality control of

Z. officinale

charcoal decoction pieces and the judgment of the processing d

egree.