Parallel set operations with visual data

This paper treats data structures for image representation suitable for parallel algorithms for operations associated with databases of images. In our approach, images are converted from input pixel form to linear quadtrees that allow efficient storage of image data and that are suitable for a large number of operations, e.g. set operations such as union, intersection and difference. Set operations are essential for data retrieval in spatial database queries. All the algorithms mentioned above were developed on a MasPar SIMD parallel computer.