参数自适应的KPCA先验形状约束目标分割

为克服固定先验形状在分割可变形目标时的困难,提出一种基于核主元分析(KPCA)的参数自适应先验形状约束水平集分割方法.首先使用KPCA变换获取目标先验形状特征空间的基底向量；其次用Parzen窗估计待分割图像的灰度分布以构造图像数据能量项；然后使用仿射变换对齐图像感兴趣区域与先验形状,从而将目标形状先验知识集成到分割模型中；最后在基于水平集方法求解演化方程时自适应地估计参数,实现形变目标的分割.实验结果表明,相比于CV (Chan-Vese)模型和单先验形状约束的水平集方法,该模型能够有效地分割不同姿态的目标形状.

Shape prior constrained KPCA object segmentation with parameter adaption

In order to solve the problem of deformable objects segmentation with a fixed shape prior, a shape prior constrained and parameter adaption level set segmentation method based on kernel principal component analysis(KPCA) is proposed. Firstly KPCA method is used to get the base vectors in shape prior feature space. Then, Parzen window method is used to estimate the results of original image for image data term and affine transformation is performed to align the image region of interest and prior shape training set to add shape priors to segmentation model. At last, a parameter adaptive method is introduced when solving evolution equation based on level set method. Experimental results show that our method can effectively segment the objects with different attitudes under background in comparison with CV model and single prior shape constrained level set methods.