EFFICIENT MORPHOLOGICAL SET TRANSFORMATIONS ON LINE DRAWINGS

摘要

Image compression techniques have been recently used not only for reducing storage requirements, but also computational costs when processing images on low cost computers. This approach might be also of interest for processing large engineering drawings, where feature extraction techniques must be intensively applied for their segmentation into regions of interest for subsequent analysis. This paper explores this alternative using a simple run-length compression, leading to excellent results. Although this approach is not new and can be classified within the decomposition paradigm used since the early stages of line drawing image processing, the developed formalism allows directional morphological set transformations to be performed, on a low cost personal computer, faster than on costly parallel computers for the same, but uncompressed, images. This good performance is proved in two different applications: the generation of homotopic skeletons through thinning processes, and the extraction of linear features through serializing multiangle parallelism operations.