Evaluation of two automated thresholding techniques for pavement images : Kaseko, M.S.; Ritchie, S.G.; Lo, Z.P. Infrastructure Planning and Management Conference Proceedings, Denver, Colorado (United States), 21–23 Jun. 1993. pp. 277–281. Edited by J.L. Gifford, D.R. Vzarski and S. McNeil. American Society of Civil Engineers (1993). ISBN 0-87262-917-1

Abstract

Thresholding of pavement images is an important step towards the design of an automated pavement crack detection system. However, traditional automated thresholding techniques generally do not perform well on pavement images. Recently, a number of studies have been conducted proposing different approaches for this thresholding problem. This paper presents a comparative analysis and evaluation of the performance of one of the most promising of these approaches, the regression analysis approach based on artificial neural networks.