Japanese / English


論文の言語 英語
著者 Katsufumi Inoue, Koichi Kise
論文名 Memory Reduction Method for Specific Object Recognition Based on Lossy Encoding of Feature Vectors with a Bloomier Filter
論文誌名 Proceedings of the 2nd China-Japan-Korea Joint Workshop on Pattern Recognition (CJKPR2010)
ページ pp.166-171
年月 2010年11月
要約 Specific object recognition method with the nearest neighbor search of local features needs an immense of memory storage to store them for distance calculation since the number of local features is very large. A way to solve this problem is to skip the distance calculation. In this paper, we propose a memory reduction method with a Bloomier filter which is far memory efficient than hash tables. From the experiments with 55 3D objects and 5,000 planar objects, the proposed method was successful to reduce the required memory for specific object recognition compared with the method with a hash table.