Skip to content
Snippets Groups Projects
Commit 91189df8 authored by André Anjos's avatar André Anjos :speech_balloon:
Browse files

Merge branch 'baseline_experiments' into 'master' 

Update baseline results for rlt, mc, and wld

See merge request !38
parents 4843fd6c 03b2e053
No related branches found
No related tags found
1 merge request!38Update baseline results for rlt, mc, and wld
Pipeline #
Hide whitespace changes
Inline Side-by-side
Showing
with 15 additions and 16 deletions
doc/baselines.rst
+ 15
− 16
View file @ 91189df8
...@@ -147,10 +147,10 @@ performance: ...@@ -147,10 +147,10 @@ performance:
.. code-block:: sh .. code-block:: sh
$ bob_eval_threshold.py <path-to>/verafinger/rlt/Nom/nonorm/scores-dev $ bob_eval_threshold.py <path-to>/verafinger/rlt/Nom/nonorm/scores-dev
('Threshold:', 0.32045327) ('Threshold:', 0.31835292)
FAR : 26.362% (12701/48180) FAR : 23.636% (11388/48180)
FRR : 26.364% (58/220) FRR : 23.636% (52/220)
HTER: 26.363% HTER: 23.636%
Maximum Curvature with Miura Matching Maximum Curvature with Miura Matching
...@@ -180,11 +180,10 @@ we obtained: ...@@ -180,11 +180,10 @@ we obtained:
.. code-block:: sh .. code-block:: sh
$ bob_eval_threshold.py <path-to>/verafinger/mc/Nom/nonorm/scores-dev $ bob_eval_threshold.py <path-to>/verafinger/mc/Nom/nonorm/scores-dev
('Threshold:', 0.078274325) ('Threshold:', 0.0737283)
FAR : 3.182% (1533/48180) FAR : 4.388% (2114/48180)
FRR : 3.182% (7/220) FRR : 4.545% (10/220)
HTER: 3.182% HTER: 4.467%
Wide Line Detector with Miura Matching Wide Line Detector with Miura Matching
====================================== ======================================
...@@ -214,10 +213,10 @@ we obtained: ...@@ -214,10 +213,10 @@ we obtained:
.. code-block:: sh .. code-block:: sh
$ bob_eval_threshold.py <path-to>/verafinger/wld/NOM/nonorm/scores-dev $ bob_eval_threshold.py <path-to>/verafinger/wld/NOM/nonorm/scores-dev
('Threshold:', 0.239141175) ('Threshold:', 0.240269475)
FAR : 10.455% (5037/48180) FAR : 9.770% (4707/48180)
FRR : 10.455% (23/220) FRR : 9.545% (21/220)
HTER: 10.455% HTER: 9.658%
Results for other Baselines Results for other Baselines
...@@ -232,9 +231,9 @@ correspond to the the equal-error rate on the development set, in percentage): ...@@ -232,9 +231,9 @@ correspond to the the equal-error rate on the development set, in percentage):
------------------------ -------------------- ------------- ------------------------ -------------------- -------------
Feature Extractor Full B Nom 1vsall nom Feature Extractor Full B Nom 1vsall nom
======================== ====== ====== ====== ====== ====== ======================== ====== ====== ====== ====== ======
Repeated Line Tracking 23.9 24.1 24.9 1.7 1.4 Repeated Line Tracking 14.6 13.4 23.6 3.4 1.4
Wide Line Detector 10.2 10.2 10.5 2.3 1.7 Wide Line Detector 5.8 5.6 9.7 2.8 1.9
Maximum Curvature 3.2 3.2 3.1 0.4 0. Maximum Curvature 2.5 1.4 4.5 0.9 0.4
======================== ====== ====== ====== ====== ====== ======================== ====== ====== ====== ====== ======
In a machine with 48 cores, running these baselines took the following time In a machine with 48 cores, running these baselines took the following time
......
0% or .
You are about to add 0 people to the discussion. Proceed with caution.
Please register or to comment