Tea harvesting is an operation in which the tender tea shoots (buds) are pickled, which is generally termed as "plucking". In order the make a plucking decision, counting correctly the maturity of tea shoots is extremely important because it determines the quality of tea production. However, it is a tedious task and takes large amount of time of tea producers. In this work, we show how computer vision can be used to improve the manual method. Our automatic system requires only the images acquired from a tea field in order the count tea shoots.


Motivation & Objective

  • Counting tender tea-shoot to make a decision for plucking (tea harvesting decision)
     Manual issues





  • Tedious task
  • Time consuming
  • Proposed a system to detect and count the tea-shoots automatically 

Proposed method

First, we build a parametric model of a tea-shoot's color distribution in order to roughly separate Regions-of-Interest (ROIs) of tea shoots from a complicated background.

For each ROI, we then extract supportive (local) features with expectations that these features will only appear around an apical bud of tea shoots thanks to two measurements: the density of edge pixels and a statistic of gradient directions. Consequently, the extracted features are put into a mean shift cluster to locate the position of tea shoots. The proposed method is evaluated on a set of testing images with different species of tea plants and ages. 


A training set of tea shoot



Clustering detected features

Defected features Cluster results


Proposed system


The results show 86% correct tea shoots detected, whereas 25% of a false alarm rate exists. It offers an elegant way to build an assisting tool for tea harvesting.