Download | - View accepted manuscript: Acceleration of Binning Nearest Neighbour Methods (PDF, 603 KB)
|
---|
Author | Search for: Greenspan, Michael; Search for: Godin, Guy; Search for: Talbot, J. |
---|
Format | Text, Article |
---|
Conference | Proceedings of Vision Interface 2000, May 14-17, 2000., Montréal, Québec, Canada |
---|
Abstract | A new solution method to the Nearest Neighbour Problem is presented. The method is based upon the triangle inequality and works well for small point sets, where traditional solutions are particularly ineffective. Its performance is characterized experimentally and compared with k-d tree and Elias approaches. A hybrid approach is proposed wherein the triangle inequality method is applied to the k-d tree and Elias bin sets. The hybridization is shown to accelerate the k-d tree for large point sets, resulting in 20% improvement in time performance. The space efficiencies for both the k-d tree and Elias methods also improve under the hybrid scheme. |
---|
Publication date | 2000 |
---|
Language | English |
---|
NRC number | NRCC 44167 |
---|
NPARC number | 5763679 |
---|
Export citation | Export as RIS |
---|
Report a correction | Report a correction (opens in a new tab) |
---|
Record identifier | a4dfbe41-b704-487a-8f19-884197124ff5 |
---|
Record created | 2009-03-29 |
---|
Record modified | 2020-03-26 |
---|