Medical Image Registration Based on BSP and Quad-Tree Partitioning
نویسندگان
چکیده
This paper presents a study of image simplification techniques as a first stage to define a multiresolution registration framework. We propose here a new approach for image registration based on the partitioning of the source images in binary-space (BSP) and quad-tree structures. These partitioned images have been obtained with a maximum mutual information gain algorithm. Multimodal registration experiments with downsampled, BSP and quadtree partitioned images show an outstanding accuracy and robustness by using BSP images, since the grid effects are drastically reduced. The obtained results indicate that BSP partitioning can provide a suitable framework for multiresolution registration.
منابع مشابه
Color image coding, indexing and retrieval using binary space partitioning tree
This paper presents a unified approach to colour image coding, content-based indexing, and retrieval for database applications. The binary space partitioning (BSP) tree, traditionally used in gray scale image coding [1, 2] is extended to represent colour images. The BSP tree, hence the structure, of the image is explicitly coded. A method is developed to compute the similarities of images based...
متن کاملColor Image Representation Using Bsp Tree
This paper presents a novel approach to colour image representation using Binary Space Partitioning (BSP) Tree. In the past, BSP tree has been used to represent grey scale images. Extending the method to colour images is however not straightforward. We propose to apply the moment-preserving thresholding technique to binarize the colour image, and determine the partitioning lines from the binary...
متن کاملApplication of Binary Spatial Partitioning to Computer Aided Design
Computer Aided Design (CAD) applications usually need to store and process dynamically and efficiently various drawing elements. Typically the quad-tree data structure is used in 2 dimensions and the octant-tree data structure in 3 dimensions. Here the Binary Spatial Partitioning (BSP) tree data structure is proposed for CAD applications. BSP scales better in irregular geometries such as long n...
متن کاملFPGA Implementation of Quadtree Partitioning Iterated Function Systems Applied to Medical Images
Owing to the growth of technology there is a need for high performance and high capacity systems to efficiently utilize the bandwidth during transmission of images. Hence Compression of medical Images is required for data storage and transmission. One such compression algorithms which is found effective for medical images is fractal image compression. Fractal image compression (FIC) is a lossy ...
متن کاملSOAR: Stochastic Optimization for Affine global point set Registration
We introduce a stochastic algorithm for pairwise affine registration of partially overlapping 3D point clouds with unknown point correspondences. The algorithm recovers the globally optimal scale, rotation, and translation alignment parameters and is applicable in a variety of difficult settings, including very sparse, noisy, and outlierridden datasets that do not permit the computation of loca...
متن کامل