脊波在工业CT图像裂纹边缘检测中的应用

在分析工业CT图像本身特点及小波变换检测点状奇异性的基础上，研究改进了一种基于脊波变换的边缘检钡0方法，并将其应用于实际工业CT图像裂纹检测中。首先利用脊波变换获得裂纹方向和大致范围，然后通过区域灰度均值比较定位裂纹区域，最后采用梯度算子检测出裂纹边缘并对其进行多项式拟合，得到定位准确、连续、独立的裂纹边缘图像。CT图像的旋转实验验证了该算法的鲁棒性，而与Earlace算子、Canny算子和Mallat小波方法的对比实验则证实该算法具有较强的抗噪声能力。

Application of ridgelet in crack edge detection of ICT image

After analyzing the characteristic of ICT(industrial computerized tomography)image and wavelet transformation singularity,an edge detection method based on ridgelet transform was studied and improved,and applied in crack edge detection of ICT image.First we get the direction and approximate bound of the crack using ridgelet transform,and then compare the average area grayscale to locate the crack area.At last,we adopt gradient operator to detect the crack edge,which is processed using polynomial fit to get an accurate,continuous and independent crack edge image.The experiment of CT image rotation validates the robustness of this algorithm,and the comparative experiments with Laplace,Canny operators and Mallat method prove that the algorithm has strong robustness against noise.