Cutting Edge App for Tea Leaves Classification

Ayoub Berdeddouch 1 year, 6 months 2 min read -    -   0 Stars   



Using AI for Improving Quality of Green Tea Leaves in Sri Lanka (Phase-2)


Sri Lanka is one of the top Tea manufacturers in the world and it holds the rank No 1 in the black tea exporter category throughout the past 2 decades. The tea industry contributes more than 5% to the national GDP. The tea manufacturing process is an interlinked process and the final output of the tea production depends entirely on the quality of green leaves received from Green Tea dealers  to the tea factory. 

Unfortunately, a significant amount (10% – 40%) of total leaves get damaged during the plucking, collection, packing and transportation process. To mitigate the issue of receiving poor leaves to the factory, we have decided to identify tea leaves using AI with an image processing method during the initiation phase of this challenge. Under the Machine Learning  life cycle following phases have been completed successfully and we will do further improvements during the 2nd phase of the project. 

FInalized Tasks under Machine life cycle

Expected UI design under the final Solution

Remaining steps will be started from the model which we have already built during the 1st phase and embed the model to a mobile application , so that users could operate the ML based classification model without any inconvenience.

The Problem

Though we develop the ML based model with higher accuracy, it’s pointless if we are unable to deploy the application on a portable and versatile device, so that real-world users can classify tea leaves on their own, without any inconvenience. Therefore, it’s mandatory to identify existing barriers and difficulties prior to deploying a mobile application with the MLOps Cycle. Image capturing, uploading, preprocessing and training model has to be a recursive process. This might help to improve the accuracy of the model incrementally and give better results to end-users.  So, deploying a fully fledged mobile application will be focused on this phase.  

The Project Goals:

1. Develop mobile applications for the classification Tea qualities, based on main tea regions.

2. Using edge computing and cloud development for mobile applications