3D Object Recognition Based on Description of Geometric Relations among Features Extracted from Surface Models

Geom 巴 trichashing method is well-known 出 oneof techniques that realize 3D model matching procedure as quickly as possible. The matching proc 巴 ssof the method uses hash-tables prepar 巴 doff-line for th 巴 sur face moclels of all 3D objects to be registered in a database. 1n order to index th 巴 modelinformation into the hash-table ， a hash function is required. It has to provide an index value that uniquely describes geometric relations among features extracted from the surface models. 1n this paper ， two hash functions are proposed ， in which they are defined by using several geometric features such as normal vectors and curvatUI 四 Further-mor 巴， in order to improve the efficiency of the matching process ， a rehashing procedure is introduced so that the calculated indexes may be scatterecl within the hash table as llniformly as possible. Through experiments using several surface models ， it has been verified the g 巴 ometrichashing method introducing the novel hash functions ancl th 巴 rehashingprocedure is effective in 3D object recognition