Automatic classification of turmeric rhizomes using the external morphological characteristics

Arshpreet Kaur, Navreet Saini, Ranjit Kaur, Amitava Das

Abstract: Machine vision is a computer based decision making process useful for reducing manual inspections. Accurate classification of agricultural products can be obtained by using external morphological details. This study presents a machine vision system that classifies turmeric rhizomes into three defined classes based on its origin. The objective of this paper was to classify the varieties of turmeric rhizomes using neural network based classifier. The visible images of the turmeric rhizomes were acquired and imaging techniques such as histogram thresholding and morphological operations were performed on them. The external morphological features such as shape and size showed promising results in automatically classifying the turmeric rhizomes.