Title :
The medial feature detector: Stable regions from image boundaries
Author :
Avrithis, Yannis ; Rapantzikos, Konstantinos
Author_Institution :
Nat. Tech. Univ. of Athens, Athens, Germany
Abstract :
We present a local feature detector that is able to detect regions of arbitrary scale and shape, without scale space construction. We compute a weighted distance map on image gradient, using our exact linear-time algorithm, a variant of group marching for Euclidean space. We find the weighted medial axis by extending residues, typically used in Voronoi skeletons. We decompose the medial axis into a graph representing image structure in terms of peaks and saddle points. A duality property enables reconstruction of regions using the same marching method. We greedily group regions taking both contrast and shape into account. On the way, we select regions according to our shape fragmentation factor, favoring those well enclosed by boundaries-even incomplete. We achieve state of the art performance in matching and retrieval experiments with reduced memory and computational requirements.
Keywords :
computational geometry; feature extraction; graph theory; image matching; image reconstruction; image representation; image retrieval; object detection; Euclidean space; Voronoi skeletons; duality property; graph image structure representation; group marching; image boundaries; image gradient; linear-time algorithm; local feature detector; matching experiments; medial feature detector; peak points; retrieval experiments; saddle points; shape fragmentation factor; weighted distance map; weighted medial axis; Detectors; Euclidean distance; Feature extraction; Image edge detection; Image segmentation; Shape; Transforms;
Conference_Titel :
Computer Vision (ICCV), 2011 IEEE International Conference on
Conference_Location :
Barcelona
Print_ISBN :
978-1-4577-1101-5
DOI :
10.1109/ICCV.2011.6126436