%0 Journal Article %T Real-time object retrieval with dominant orientation template matching improved by pyramid scoring
金字塔评分改进主方向模板匹配的实时目标检索 %A Hong Chaoqun %A Zhu Jianke %A Li N %A Bu Jiajun %A Chen Chun %A
洪朝群 %A 朱建科 %A 李娜 %A 卜佳俊 %A 陈纯 %J 中国图象图形学报 %D 2012 %I %X Traditional methods for Content-based Object Retrieval usually employ extracting and comparing local features, which are too computational demanding and require offline training process. Therefore, a novel real-time CBOR method based on dominant orientation templates (DOT) is proposed. Besides, the proposed method makes use of the spatial distributions of grid scores to construct likelihood maps and utilizes a pyramid-scoring strategy to dispose the false windows in which the grid scores are dispersed. With the above improvement, the implementation for CBOR is able to retrieve the query target directly from the videos without offline training. The results show the proposed method improves the retrieval performance while retaining real-time processing ability of DOT matching. %K content-based object retrieval %K dominant orientation templates %K likehood map %K pyramid-based scoring strategy
基于内容的目标检索 %K 主方向模板 %K 相似度映射图 %K 金字塔评分策略 %U http://www.alljournals.cn/get_abstract_url.aspx?pcid=5B3AB970F71A803DEACDC0559115BFCF0A068CD97DD29835&cid=8240383F08CE46C8B05036380D75B607&jid=D06194629680C940ACE75262F54B9D85&aid=3B18C081A6B0F9F4B253AFC9A07718FA&yid=99E9153A83D4CB11&vid=BCA2697F357F2001&iid=94C357A881DFC066&sid=27A3D4EE1F52A91C&eid=C19D5524C51D7FE4&journal_id=1006-8961&journal_name=中国图象图形学报&referenced_num=0&reference_num=15