A New Fuzzy Connectivity Class Application to Structural Recognition in Images

Fuzzy sets theory constitutes a poweful tool, that can lead to more robustness in problems such as image segmentation and recognition. This robustness results to some extent from the partial recovery of the continuity that is lost during digitization. Here we deal with fuzzy connectivity notions. We show that usual fuzzy connectivity definitions have some drawbacks, and we propose a new definition, based on the notion of hyperconnection, that exhibits better properties, in particular in terms of continuity. We illustrate the potential use of this definition in a recognition procedure based on connected filters. A max-tree representation is also used, in order to deal efficiently with the proposed connectivity.

• Type: Conference
• Year: 2008
• Where: DGCI
• Authors: Olivier Nempont, Jamal Atif, Enrico Angelini, Isabelle Bloch
• Keywords: DGCI 2008, Discrete Geometry, Fuzzy Connectivity, Fuzzy Connectivity Notions, Fuzzy Sets Theory