In　order　to　locate　all　the　objects　of　a　model　in　a　large　image,　we　proposed　an　effective　Hausdorff　distance　(HD)　matching　algorithm　that　is　based　on　coarse-to-fine　hierarchical　matching.　In　constructing　the　hierarchical　pyramidal　structure,　the　decimation　mode　of　decomposition　and　the　number　of　hierarchical　levels　are　determined　adaptively　by　the　edge　model.　Thus　the　proposed　algorithm　can　decrease　the　number　of　losing　objects,　at　the　same　time　sharply　speed　up　the　search　when　locating　objects　in　an　image.　For　integrate　circuit＇s　(IC)　micro　images,　which　are　mainly　composed　of　vertical　and　horizontal　linear　edges,　the　algorithm　shows　better　performance.　The　experiments　also　illustrate　good　matching　results　with　other　images.　©　2006　IEEE.