Translator Disclaimer
20 April 2005 Image registration using a weighted region adjacency graph
Author Affiliations +
Image registration is an important problem for image processing and computer vision with many proposed applications in medical image analysis.1, 2 Image registration techniques attempt to map corresponding features between two images. The problem is particularly difficult as anatomy is subject to elastic deformations. This paper considers this problem in the context of graph matching. Firstly, weighted Region Adjacency Graphs (RAGs) are constructed from each image using an approach based on watershed saliency. 3 The vertices of the RAG represent salient regions in the image and the (weighted) edges represent the relationship (bonding) between each region. Correspondences between images are then determined using a weighted graph matching method. Graph matching is considered to be one of the most complex problems in computer vision, due to its combinatorial nature. Our approach uses a multi-spectral technique to graph matching first proposed by Umeyama4 to find an approximate solution to the weighted graph matching problem (WGMP) based on the singular value decomposition of the adjacency matrix. Results show the technique is successful in co-registering 2-D MRI images and the method could be useful in co-registering 3-D volumetric data (e.g. CT, MRI, SPECT, PET etc.).
© (2005) COPYRIGHT Society of Photo-Optical Instrumentation Engineers (SPIE). Downloading of the abstract is permitted for personal use only.
Muhannad Al-Hasan and Mark Fisher "Image registration using a weighted region adjacency graph", Proc. SPIE 5745, Medical Imaging 2005: Physics of Medical Imaging, (20 April 2005);

Back to Top