Monitoring Fermentation of Black Tea with Image Processing Techniques

Show simple item record

dc.contributor.author Saranka, S.
dc.contributor.author Kartheeswaran, T.
dc.contributor.author Wanniarachchi, D.D.C.
dc.contributor.author Wanniarachchi, W.K.I.L.
dc.date.accessioned 2019-11-25T05:52:32Z
dc.date.accessioned 2022-03-11T10:28:50Z
dc.date.available 2019-11-25T05:52:32Z
dc.date.available 2022-03-11T10:28:50Z
dc.date.issued 22-05-16
dc.identifier.uri http://drr.vau.ac.lk/handle/123456789/1288
dc.description.abstract The possibility to use digital images of tea particles as a tool to monitor fermentation ofblack tea processing is studied in this project. Copper green color is the predicted colorused to measure the degree of fermentation; therefore, determining the fermentation levelby observing the copper green using naked eye is error prone and affects the completeproduct outcome. Tea particles of a certain batch after rolling step are categorized in to three difrent groups as dhool 1-3 based upon particle size.Therefore, the duration offermentation is varied by dhool number of a given batch due to varied sizes of teaparticles. 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 VectorMachine (SVM) is used as the classifier to train the system and obtain accuracy in eachstage. 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 and92% and 91% for dhools 2 and 3 respectively. Therefore, results indicate that imageprocessing techniques can en_US
dc.language.iso en_US en_US
dc.publisher Institute o f Physics - Sri Lanka, 32nd Technical Sessions, March 2016, Colombo, Sri Lanka en_US
dc.subject Fermentation en_US
dc.subject Image processing en_US
dc.title Monitoring Fermentation of Black Tea with Image Processing Techniques en_US
dc.type Article en_US


Files in this item

This item appears in the following Collection(s)

Show simple item record

Search


Browse

My Account