DocumentCode :
2678710
Title :
Color object detection using pyramidal adjacency graphs
Author :
Lozano, Vincent ; Colantoni, Philappe ; Laget, B.
Author_Institution :
Inst. d´´Ingenierie de la Vision, Univ. Jean Monnet, Saint-Etienne, France
Volume :
3
fYear :
1996
fDate :
16-19 Sep 1996
Firstpage :
1007
Abstract :
We describe here a new method for object detection that uses a special structure called a pyramidal adjacency graph. Using that structure, which is built upon a Gaussian pyramid structure, and several predicates of color homogeneity, we are able to detect a spot region in a color pyramid. One interesting aspect of this structure is that it helps to describe connections between events at different levels of a pyramid, and so provides a more global analysis
Keywords :
Gaussian processes; graph theory; image colour analysis; image segmentation; object detection; Gaussian pyramid structure; color homogeneity; color object detection; color pyramid; global analysis; pyramidal adjacency graphs; spot region; Frequency; Image analysis; Image color analysis; Image processing; Image segmentation; Kernel; Object detection; Performance analysis; Personnel; Visual system;
fLanguage :
English
Publisher :
ieee
Conference_Titel :
Image Processing, 1996. Proceedings., International Conference on
Conference_Location :
Lausanne
Print_ISBN :
0-7803-3259-8
Type :
conf
DOI :
10.1109/ICIP.1996.560996
Filename :
560996
Link To Document :
بازگشت