| Summary: | What is the database table KDTree | ||
|---|---|---|---|
| Product: | [Applications] digikam | Reporter: | Thomas Bach <Thomas.bach> |
| Component: | Faces-Workflow | Assignee: | Digikam Developers <digikam-bugs-null> |
| Status: | RESOLVED FIXED | ||
| Severity: | normal | CC: | caulier.gilles, metzpinguin |
| Priority: | NOR | ||
| Version First Reported In: | 7.3.0 | ||
| Target Milestone: | --- | ||
| Platform: | Microsoft Windows | ||
| OS: | Microsoft Windows | ||
| Latest Commit: | Version Fixed/Implemented In: | 7.3.0 | |
| Sentry Crash Report: | |||
|
Description
Thomas Bach
2021-04-04 17:27:50 UTC
KD-Tree is a vector space partionning: https://en.wikipedia.org/wiki/K-d_tree It used with face recognition to support clustering for speed up auto tagging with group of faces: https://ui.adsabs.harvard.edu/abs/2015SPIE.9631E..1IW/abstract Gilles Caulier This paper explain in details clustering technique for face recognition : https://arxiv.org/pdf/1604.00989.pdf Gilles Caulier The KDTree table is currently unused because we are creating one in RAM for speed reasons. The possibility of creating them in the database is optionally available in the source code. This means that there is a possibility that we will use the table in the DB in the future. Maik I think it's all explained. Maik Tx |