Title :
Skeleton branch distances for shape recognition
Author :
Boluk, S. Arda ; Demirci, M. Fatih
Author_Institution :
Bilgisayar Muhendisligi Bolumu, TOBB Ekonomi ve Teknoloji Univ., Ankara, Turkey
Abstract :
In this paper, we presented a novel shape recognition framework based on medial axis graph. After extracting medial axis graph of a shape, we constructed a multi-dimensional distribution by calculating distances between each node and all of the branch nodes in the graph. Then similarity rates between these distributions is found by using a transportation-based distance function. At last, we compared our results with results of similar works conducted in the past.
Keywords :
shape recognition; branch nodes; medial axis graph; shape recognition framework; skeleton branch distances; transportation-based distance function; Computer vision; Earth; Histograms; IEEE Computer Society; Pattern recognition; Shape; Skeleton; Earth Mover´s Distance; Shape retrieval; medial axis graph; shape matching;
Conference_Titel :
Signal Processing and Communications Applications Conference (SIU), 2015 23th
Conference_Location :
Malatya
DOI :
10.1109/SIU.2015.7129883
