Validation of Multispectral Imaging for The Detection of Sugar Adulteration in Black Tea

Black tea is known to be one of the most popular beverages enjoyed by two-thirds of the world’s population. In 2020, over six billion kg of tea was produced all over the world, of which 278.5 million kg was produced in Sri Lanka. The tea industry plays a huge role in the Sri Lankan economy and employs over one million people in Sri Lanka. With the increasing consumption of tea, quality control of tea becomes more and more important nowadays, for example, many national and international authorities are setting criteria for quality factors. Sugar adulteration is one such major issue faced by the tea industry which badly affects the brand name “Ceylon Tea”. In this study, a reflectance based multispectral imaging system was introduced to detect sugar adulteration level in black tea instead of conventional methods including colourimetric and titrimetric methods which are destructive, time-consuming, and expensive. The multispectral imaging system only uses nine narrow-band off-the-shelf LEDs emitting wavelengths ranging from 405 nm to 950 nm. The study consists of five stages; dark current subtraction and adaptive Wiener filtering stage to mitigate camera sensory defects and random noise, PCA (Principal Component Analysis) based dimension reduction, FDA (Fisher’s Discriminant Analysis) based dimension reduction, k-NN (k-Nearest Neighbors) based classification and CNN (Convolutional Neural Network) based classification.