Comparison Of Supervised Classifcation Techniques For Vision-Based Pavement Crack Detection
Abstract
In this study, the application of four classifcation techniques for computer vision-based pavement crack detection systems was investigated. The classifcation methods-artifcial neural network (ANN), decision tree, k-nearest neighbor, and adaptive neuro-fuzzy inference system (ANFIS)-were selected on the basis of the complexity and clarity of their procedures. These methods were evaluated for (a) prediction performance, (b) computation time, (c) stability of results for highly imbalanced data sets, (d) stability of the classifers' performance for pavements in different deterioration stages, and (e) interpretability of results and clarity of the procedure. According to the results, the ANN and ANFIS methods not only provide superior performance but also are more flexible and compatible for the crack detection application. The ANFIS method is called a "white-box classifer," and the inferred knowledge from its membership functions can be used to characterize the imagery properties of detected image components.
Publication Date
1-1-2016
Publication Title
Transportation Research Record
Volume
2595
Number of Pages
119-127
Document Type
Article
Personal Identifier
scopus
DOI Link
https://doi.org/10.3141/2595-13
Copyright Status
Unknown
Socpus ID
84991263716 (Scopus)
Source API URL
https://api.elsevier.com/content/abstract/scopus_id/84991263716
STARS Citation
Mokhtari, Soroush; Wu, Liuliu; and Yun, Hae Bum, "Comparison Of Supervised Classifcation Techniques For Vision-Based Pavement Crack Detection" (2016). Scopus Export 2015-2019. 2601.
https://stars.library.ucf.edu/scopus2015/2601