The introduction of shape priori in the segmentation model ameliorates effectively the poor segmentation result due to the using of the image information alone to segment the image including noise, occlusion, or missing parts. But the presentation of shape via Principal Component Analysis (PCA) brings on the limitation of the similarity between the objet and the prior shape. In this paper, we proposed using Kernel PCA (KPCA) to capture the shape information - the variability. KPCA can present better shape prior knowledge. The model based on KPCA allows segmenting the object with nonlinear transformation or a quite difference with the priori shape. Moreover, since the shape model is incorporated into the deformable model, our segmentation model includes the image term and the shape term to balance the influence of the global image information and the shape prior knowledge in proceed of segmentation. Our model and the model based on PCA both are applied to synthetic images and CT medical images. The comparative results show that KPCA can more accurately identify the object with large deformation or from the noised seriously background.

Date Published: 8 July 2011
PDF: 8 pages
Proc. SPIE 8009, Third International Conference on Digital Image Processing (ICDIP 2011), 800937 (8 July 2011); doi: 10.1117/12.896324

Published in SPIE Proceedings Vol. 8009:
Third International Conference on Digital Image Processing (ICDIP 2011)
Ting Zhang, Editor(s)