Robust Extraction, rewrited
Project description
Robust Extraction2
Robust Extraction, rewrited
Changes w.r.t. Version 1
Cluster Intersections
- Original: mean intersection of the cartesian product of lines in both clusters
- New: intersection of a fitted line by cluster (regressed on all endpoints)
ST-Invariant Matching Penalization
Given the number of matched points $N$ and number of minimum points $n_{min}$, the penalization is defined as $1/(N-n_{min}+1)^e$, where $e$ is the "penalization exponent" parameter:
Original | New |
---|---|
$e=0.5$ | $e=5$ |
Put simply, we basically force matching as many points as possible that don't incur a huge cost.
Project details
Release history Release notifications | RSS feed
Download files
Download the file for your platform. If you're not sure which to choose, learn more about installing packages.
Source Distribution
robust_extraction2-0.1.7.tar.gz
(19.8 kB
view hashes)
Built Distribution
Close
Hashes for robust_extraction2-0.1.7-py3-none-any.whl
Algorithm | Hash digest | |
---|---|---|
SHA256 | 08a1a65587baad5f2fe3b05c93cad04a9a17b3e2408922da03605c5f75c5e824 |
|
MD5 | 2f747c7f3c4cb7553cb4ff906d931233 |
|
BLAKE2b-256 | cb47df5fc3ec23aa1834cd751e0e1b5ff48e41e0a62689e4f836aeb389482490 |