Semantic image segmentation using morphological tools

Alberto Pardo · Proceedings - International Conference on Image Processing · 2003

In this work, we study the extraction of semantic objects using morphological tools. We decompose the image into its level sets and level lines (the borders of the level sets). Specifically, from all the level lines we extract the ones that contain T-junctions, have compact form, and are well-contrasted to obtain the semantic objects in the scene. For all these factors, we establish an estimation procedure.

Read the paper · More papers on PaperTik