ROC Curve Analysis for Classification of Road Defects

Huong Thu Nguyen, Long The Nguyen


ROC analysis is a visual and numerical method used to evaluate the performance of classification algorithms, such as those used to predict the structure and functions from string data. The main objective of the paper is to use the ROC analysis to evaluate the accuracy of the Random Forest algorithm to classify road surface defects on three different sets of data collected from Portugal, Irkutsk city - Russia Federation and Thai Nguyen city - Vietnam. This article summarizes the basics of ROC analysis and interprets the results analysis with other thresholds to build ROC curve. In addition, we present the steps to build a system to automatically classify road surface defects based on visual techniques and machine learning methods.



Road Defect; Graph Cuts; Image Segmentation; Object Classification; Random Forest Algorithm; Machine Learning; ROC Curve Analysis

Full Text:


(C) 2010-2022 EduSoft