Evaluating the Effectiveness of Machine Learning Techniques for Flower Recognition

Abstract

Identifying different kinds of flowers and leaves according to their traits is very beneficial in several agricultural and
medicinal domains. This article applies machine learning methods to the problem of flower identification using their
unique traits. The accuracy of a collection of floral data is determined by using the machine learning techniques
Knearest neighbor, Random Forest, and Decision Tree. The Python programming language is used to apply
algorithms to a dataset. The KNN machine learning algorithm has the greatest performance when it comes to flower
recognition.