
Speaker  Stina Svensson 
Comment  
Title  Distance weighted propagation of gradient magnitudes OR how to avoid edge binarisation in Hierarchical Chamfer Matching 
Abstract  I will talk about a modification of the Hierarchical Chamfer Matching
Algorithm (HCMA) with the effect that the edge binarisation step can
be skipped. HCMA is a template matching algorithm used in many
applications. A distance transform (DT) from binarised edges in the
search image is used to guide the template to good positions. Local
minima of a function using the distance values hit by the template
correspond to potential matches. The proposed modification is to use distance weighted propagation of gradient magnitude information as a cost image instead of a DT from the edges. By this as much information as possible is kept until later in the matching process and, hence, we decrease the risk of discarding good matches in the edge detection and binarisation process. Distance weighted propagation of gradient magnitude information can be useful also in other algorithm. This work is done in cooperation with IdaMaria Sintorn (earlier CBA, currently at CSIRO, Sydney, Australia). 