Weed identification using machine learning models

Abstract

Image classification is a complex process and an important direction in the field of image processing. Image classification methods require learning and training stages. Using machine learning classification models in image classification gives better results. Decision Tree, Random Forest, Gradient Boosting, Bagging Classifier, Multi-Layer Perceptron (MLP) Classifier, and Support Vector Machine (SVM) are different machine-learning classification models. The goal of this paper is to analyze the machine learning classification models. These models classify 12 kinds of plant seedlings, of which 3 are crop seedlings and 9 are weed seedlings. This paper suggests that, when using a V2 Plant Seedlings dataset, the accuracy of SVM is 0.71 and the accuracy of other models is less compared to SVM. The experimental results in this paper show that the machine learning model SVM has a better solution effect and higher recognition accuracy. This paper focuses on model building, training, and assessing the quality of the model by generating a confusion matrix and a classification report.

Related Papers

• → Performance Comparison of Multi-layer Perceptron (Back Propagation, Delta Rule and Perceptron) algorithms in Neural Networks(2009)113 cited
• → Prediction of significant wave height using geno-multilayer perceptron(2012)48 cited
• → Kajian Literatur Multi Layer Perceptron Seberapa Baik Performa Algoritma Ini(2022)10 cited
• → <title>Comparison of sinusoidal perceptron with multilayer classical perceptron</title>(1991)
• → Single-Layer Perceptron Capable Of Classifying 2N+1 Distinct Input Patterns(1990)