Semantically Homogeneous Segmentation with Nonparametric Region Competition

Thispaper presents a nonparametricregion competition algorithm which combines scale-space clustering and region competition to segment the image. It also proposes a formal and general procedure to automaticallyfind the initial regions. Our algorithm can also segment an image into regions which are not homogeneous in the sense of statistics, but is homogeneous in the sense of semantics with respect to the segmentationcontext. Keywords Segmentation,region growing, region competition

• Type: Conference
• Year: 2000
• Where: ICPR
• Authors: Ming Tang, Jing Xiao, Songde Ma
• Keywords: ICPR 2000, Nonparametricregion Competition Algorithm, Region Competition, Scale-space Clustering