%0 Journal Article
%T Study on Reference Image Selection Roles for Scene Matching Guidance<br>景象匹配制导基准图选定准则研究*
%A CAO Fei
%A YANG Xiao-gang
%A MIAO Dong
%A ZHANG Yun-peng
%A <br>曹菲
%A 杨小冈
%A 缪栋
%A 张云鹏
%J 计算机应用研究
%D 2005
%I 
%X Several image matching ability verification parameters are systematically studied. Image self-matching performance parameters are defined, and the calculation approach for the parameters is designed, more over, a new RISR is proposed. Based on theoretical analysis and simulation experiments, the limitations of the conventional RISR are pointed out and the advantages of the proposed RISR are indicated. According to massive reference image selection experiments, some thresholds of the conventional in specific condition are given, the practicability and efficiency of the proposed RISR is demonstrated.
%K Scene Matching
%K Reference Image Selection Role (RISR)
%K Self-Matching
%K Performance Parameter<br>景象匹配
%K 基准图选定准则
%K 自匹配
%K 性能参数
%U http://www.alljournals.cn/get_abstract_url.aspx?pcid=5B3AB970F71A803DEACDC0559115BFCF0A068CD97DD29835&cid=8240383F08CE46C8B05036380D75B607&jid=A9D9BE08CDC44144BE8B5685705D3AED&aid=A0FA3CB77E408117&yid=2DD7160C83D0ACED&vid=BC12EA701C895178&iid=94C357A881DFC066&sid=205BE674D84A456D&eid=12DC19455C3A2FA8&journal_id=1001-3695&journal_name=计算机应用研究&referenced_num=5&reference_num=10