Multiple Resolution Texture Analysis and Classification
IEEE Transactions on Pattern Analysis and Machine Intelligence
An improved box-counting method for image fractal dimension estimation
Pattern Recognition
Detection of Cracks and Corrosion for Automated Vessels Visual Inspection
Proceedings of the 2010 conference on Artificial Intelligence Research and Development: Proceedings of the 13th International Conference of the Catalan Association for Artificial Intelligence
Hi-index | 0.10 |
A new approach is proposed based on box-counting method to estimate the fractal dimensions, D"2"d and D"3"d of corrosion images. They denote two-dimensional (2D) and three-dimensional (3D) characteristics of corroded surface morphology. The results have been tested through dealing with classical fractal figures, pit morphology of moon surface and practical corroded samples etc. to show that this new method is computationally simple, convenient and accurate. More specially, D"2"d and D"3"d have definite corrosion expressions, which respectively denote the fractal dimensions for pit diameter distribution and pit depth distribution on real corroded surface.