Consistent line clusters for building recognition in CBIR

Yi Li, L.G. Shapiro
Object recognition supported by user interaction for service robots  
This paper introduces a new mid-level feature, the consistent line cluster, for use in content-based image retrieval. The color, orientation, and spatial features of line segments are exploited to group them into line clusters. The interrelationships among different clusters and the intrarelationships within single clusters are used to recognize and roughly locate buildings in photographic images. Experiments are performed on a database of color images of outdoor scenes.
doi:10.1109/icpr.2002.1048195 dblp:conf/icpr/LiS02 fatcat:wrjprhbfdzfkrexzkwwdihjo7a