A novel method for 3D crack edge extraction in CT volume data.

Abstract

To reduce time cost and improve the performance of edge extraction in CT volume data which is often in large size, we propose a novel method of 3D crack edge extraction using two fusion steps, one is fusion on Finite Line Integral Transform (FLIT) values in spatial directions called SD-FLIT and another is fusion on Local Binary Pattern (LBP) values on spatial planes called SP-LBP. By analyzing the S function of LBP operator, we find that value "0" of this function can describe the change between two equivalence planes. However, this property is sensitive to point difference, thus SD-FLIT is introduced to smooth noises and artifacts before the application of SP-LBP to extract 3D edge on binary volume data. Besides, fusions on directions and planes are aimed at extracting enough spatial information. Experimental results show that, owing to the sufficiency of information extraction and the simplicity of computation, our method can get continuous, thin and occlusive 3D edge, including the crack tip. Furthermore, it can be used to complicate volume data. Compared with 3D wavelet and Facet model, our method cost less time, saving at least 89% of that.