Seven commercial Chinese chrysanthemum tea products were classified by computer vision combined with deep learning. Without the need of building any specific hardware, the image acquisition and deep learning was achieved by both a bench top gel imager and a regular smartphone. The deep neural network was applied directly on the raw image, yielded 96% and 89% correct identifications when classifying flowering stage and tea type, respectively. In comparison, multivariate classification models including k-nearest neighbor, multiple linear perceptron and support vector machine were built after morphological feature extraction of the image. The best prediction accuracies when classifying flowering stages and tea types were only 90% and 63%, respectively. The result indicated that computer vision, especially when combined with deep learning or other machine learning techniques can be a convenient and versatile method in the evaluation of food quality. The model can be applied for rapid and automatic quality determination of other related foods.

Image classification by deep learning to the quality control of chrysanthemum teas

ACS Spring Meeting 2021

The official archive and repository for all ACS Meetings & Expositions abstracts and select posters or presentations.