一种基于反几何扩散分类的图像二值化方法及应用

An Anti-Geometric Diffusion Classification Based Image Binarization Method

从背景中将目标识别提取出来往往受到复杂背景中的不均匀信息干扰.本文研究基于反几何扩散的图像二值化方法,通过各向异性扩散的一种特殊形式——反几何扩散,对图像边缘进行最大限度的模糊和扩散,形成一个个分割阈值面,通过扩展的分类法则,在扩散过程中对每个目标像素进行分类.提出一种分类后处理方法使目标最终从不均匀背景中分割出来.通过对 X 光图像中铸造缺陷的识别实验,证明该方法对抑制噪声有较好的鲁棒性,给出处理背景变化不均匀的铸造产品 X 光图像的结果.

It is difficult to extract objects from background due to the uneven and complex background information. In this paper, a binarization method is developed, which is based on the anti-geometric diffusion, a special form of the anisotropic diffusion. The anti-geometric diffusion method is used to blur and diffuse the edge of images as much as possible, and thus many threshold surfaces are formed. Each pixel is classified during the diffusion process according to the developed classification criterions. Finally, a post-processing approach is proposed to extract the object from background. The numerical experimental results show that the presented method is robust to the noise restriction. Furthermore, the results for handling X-ray images of casting products with uneven background by the presented method are given.