Title :
Application of Contrast Enhancement Bilateral Closing Top-hat Otsu Thresholding (CEBICTOT) technique on crack images
Author :
Sim, K.S. ; Kho, Y.Y. ; Tso, C.P.
Author_Institution :
Fac. of Eng. & Technol., Multimedia Univ., Ayer Keroh
Abstract :
This paper introduces the contrast enhancement bilateral closing top-hat Otsu thresholding (CEBITOT) technique to perform crack detection. This technique is based on the mathematical morphology and image filtering technique to extract the crack like patterns. Mathematical morphology highlights the cracks clearly while bilateral filtering filters out the noise from the image efficiently and preserving the edges. The performance of the proposed estimator is compared with two existing methods: Otsu method, Iyer* and Sinha method over several images. The performance of the CEBITOT is significantly greater than that of the two methods.
Keywords :
image enhancement; image segmentation; mathematical morphology; object detection; CEBICTOT technique; bilateral filtering; contrast enhancement bilateral closing; crack image detection; image filtering; mathematical morphology; top-hat Otsu thresholding technique; Background noise; Clustering algorithms; Concrete; Filtering; Image edge detection; Image segmentation; Principal component analysis; Safety; Surface cracks; Surface morphology;
Conference_Titel :
Cybernetic Intelligent Systems, 2008. CIS 2008. 7th IEEE International Conference on
Conference_Location :
London
Print_ISBN :
978-1-4244-2914-1
Electronic_ISBN :
978-1-4244-2915-8
DOI :
10.1109/UKRICIS.2008.4798963