Hierarchical algorithms for morphological image processing

摘要

One drawback of the morphological image processing technique is its long computation time when run on a general purpose sequential computer. While prior research on improving the computation time for morphological processing has focused on using specialized hardware architecture, we propose to reduce the computation time by using a hierarchical data structure. In this paper, techniques and algorithms for performing morphological image processing based on the proposed approach are presented. Experimental results demonstrate that a substantial speed up in computation time can be obtained using the proposed method.