Quality evaluation of Hanyuan Zanthoxylum bungeanum Maxim. Using computer vision system combined with artificial neural network: A novel method

ABSTRACT

A novel technology based on computer vision system (CVS) and artificial neural network (ANN) was developed for the quality evaluation of Hanyuan Zanthoxylum bungeanum Maxim (HZB). The quality evaluation of HZB mainly depended on its colour, odour substances, and impurities. In this study, the contents of volatile oil (VOC), total alkylamides (TALC) and impurities (IMC) were determined and used as indices for quality control of HZB. Furthermore, CVS was also performed to determine the colour parameters (RGB values) and further transforms to CIE L*, a^*, and b*. Then, ANN was carried out to analyse the correlations between colour values obtained by CVS and quality parameters of HZB (VOC, TALC, and IMC). Higher performance and stability were presented by using CVS for determining the coloristic values of HZB. In addition, the present results also showed that the established method based on ANN could be used to predict the VOC, TALC, and IMC of HZB with the R² values of 0.9991, 0.9995, and 0.9998, respectively. This novel technology based on CVS combined with ANN could be used for the rapid, non-destructive, and effective evaluation of the quality of HZB.

KEYWORDS:

• Hanyuan Zanthoxylum bungeanum Maxim (HZB)
• Computer vision system (CVS)
• Colour
• Artificial neural network (ANN)
• Quality Evaluation

Acknowledgements

The authors are greatly thankful to the government (Hanyuan County, Sichuan, China) for providing different grades of HZB samples.

Funding

This work was supported by provincial horizontal issues “Chinese Hanyuan prickly ash deep processing of key generic technologies and industrialization” (Project SEQ ID no: 2014PT048).

Additional information

Funding

This work was supported by provincial horizontal issues “Chinese Hanyuan prickly ash deep processing of key generic technologies and industrialization” (Project SEQ ID no: 2014PT048).