Monitoring Fermentation of Black Tea with Image Processing Techniques

Abstract

Attached

The possibility to use digital images of tea particles as a tool to monitor fermentation of black tea processing is studied in this project. Copper green color is the predicted color used to measure the degree of fermentation; therefore, determining the fermentation level by observing the copper green using naked eye is error prone and affects the complete product outcome. Tea particles of a certain batch after rolling step are categorized in to three difrent groups as dhool 1-3 based upon paricle size.Therefore, the duration of fermentation is varied by dhool number of a given batch due to varied sizes of tea particles. The method used in this project is divided into three main phases, image preprocessing, identification of the dhool number, and prediction of the fermentation level. Image processing techniques are used to extract features of tea leaves and Support Vector Machine (SVM) is used as the classifier to train the system and obtain accuracy in each stage. The results indicate higher accuracy in predicting the dhool 1 which is over 77% accurate while dhools 2 and 3 indicated accuracy levels of 69% and 73% respectively. The fermentation time can be predicted with average accuracy of 94% for dhool 1 and 92% and 91% for dhools 2 and 3 respectively. Th