Leaf Recognition Using K-Nearest Neighbors Algorithm with Zernike Moments

Leaf recognition is a vital component of plant classification, which is crucial in agricultural automation. Previous studies have employed various machine learning algorithms, ranging from deep learning methods such as Convolutional Neural Network (CNN) to traditional methods like Support Vector Machine (SVM), and demonstrated success in leaf recognition. This study introduces a method for leaf recognition that employs the k-Nearest Neighbors (k-NN) algorithm as the classifier and utilizes Zernike moments as the image features. The proposed method is evaluated on the Flavia leaf dataset, and the results affirm the effectiveness of the approach. Furthermore, while Zernike moments have been extensively studied by researchers in the image recognition domain, they have predominantly been limited to a maximum order of 10. This study explores the use of Zernike moments with different maximum orders, including higher orders, to evaluate their classification abilities for leaf recognition.