diff --git a/bob/bio/face/config/database/morph.py b/bob/bio/face/config/database/morph.py
new file mode 100644
index 0000000000000000000000000000000000000000..c42d79cc4d1d11b19876840cac24c00f1f6a2300
--- /dev/null
+++ b/bob/bio/face/config/database/morph.py
@@ -0,0 +1,9 @@
+from bob.bio.face.database import MorphDatabase
+
+# In case protocol is comming from chain loading
+# https://www.idiap.ch/software/bob/docs/bob/bob.extension/stable/py_api.html#bob.extension.config.load
+if "protocol" not in locals():
+ protocol = "verification_fold1"
+
+
+database = MorphDatabase(protocol=protocol)
diff --git a/bob/bio/face/database/__init__.py b/bob/bio/face/database/__init__.py
index a7ef08a73f923b185fbe9b13e02fff77a9a9b236..3c0429f2e189eaacd4280f9ee99cdf78e3da237f 100644
--- a/bob/bio/face/database/__init__.py
+++ b/bob/bio/face/database/__init__.py
@@ -13,6 +13,7 @@ from .ijbc import IJBCBioDatabase
from .replaymobile import ReplayMobileBioDatabase
from .fargo import FargoBioDatabase
from .meds import MEDSDatabase
+from .morph import MorphDatabase
# gets sphinx autodoc done right - don't remove it
@@ -45,5 +46,6 @@ __appropriate__(
ReplayMobileBioDatabase,
FargoBioDatabase,
MEDSDatabase,
+ MorphDatabase,
)
__all__ = [_ for _ in dir() if not _.startswith("_")]
diff --git a/bob/bio/face/database/meds.py b/bob/bio/face/database/meds.py
index db2424e1dd9f83ee21f6b1e9a0e0ee3d08fad2ce..81576a93f1ea78c04225de1858fa7dea0c12434f 100644
--- a/bob/bio/face/database/meds.py
+++ b/bob/bio/face/database/meds.py
@@ -30,7 +30,62 @@ dataset_protocol_path = os.path.join(
class MEDSDatabase(CSVDatasetZTNorm):
"""
- The MEDS-II (Multiple Encounter Data Set II) database interface
+ The MEDS II database was developed by NIST to support and assists their biometrics evaluation program.
+ It is composed by 518 identities from both men/women (labeled as M and F) and five different race annotations (Asian, Black, American Indian, Unknown and White)
+ (labeled as A, B, I, U and W.
+
+ Unfortunately, the distribution of gender and race is extremely unbalanced as it can be
+ observed in their statistics. Furthermore, only 256 subjects has
+ more than one image sample (obviously it is not possible to do a biometric evaluation with one sample per subject).
+ For this reason, this interface contains a subset of the data, which is composed only by 383 subjects (White and Black men only).
+
+ This dataset contains three verification protocols and they are:
+ `verification_fold1`, `verification_fold2` and `verification_fold1`.
+ Follow below the identities distribution in each set for the for each protocol:
+
+
+ +--------------------+---------------+-----------+-----------+-----------+
+ | | Training set | Dev. Set | Eval. Set |
+ +--------------------+---------------+-----------+ + +
+ | | T-References | Z-Probes | | |
+ +====================+===============+===========+===========+===========+
+ | verification_fold1 | 80 | 80 | 111 | 112 |
+ +--------------------+---------------+-----------+-----------+-----------+
+ | verification_fold2 | 80 | 80 | 111 | 112 |
+ +--------------------+---------------+-----------+-----------+-----------+
+ | verification_fold3 | 80 | 80 | 111 | 112 |
+ +--------------------+---------------+-----------+-----------+-----------+
+
+ Example
+ -------
+
+ Fetching biometric references::
+
+ >>> from bob.bio.face.database import MEDSDatabase
+ >>> database = MEDSDatabase(protocol="verification_fold1")
+ >>> database.references()
+
+
+ Fetching probes::
+
+ >>> from bob.bio.face.database import MEDSDatabase
+ >>> database = MEDSDatabase(protocol="verification_fold1")
+ >>> database.probes()
+
+
+ Fetching refererences for T-Norm normalization::
+
+ >>> from bob.bio.face.database import MEDSDatabase
+ >>> database = MEDSDatabase(protocol="verification_fold1")
+ >>> database.trerefences()
+
+
+ Fetching probes for Z-Norm normalization::
+
+ >>> from bob.bio.face.database import MEDSDatabase
+ >>> database = MEDSDatabase(protocol="verification_fold1")
+ >>> database.zprobes()
+
.. warning::
Use the command below to set the path of the real data::
@@ -54,7 +109,7 @@ class MEDSDatabase(CSVDatasetZTNorm):
]
get_file(filename, urls)
- self.annotation_type = ("eyes-center",)
+ self.annotation_type = "eyes-center"
self.fixed_positions = None
database = CSVDataset(
diff --git a/bob/bio/face/database/morph.py b/bob/bio/face/database/morph.py
new file mode 100644
index 0000000000000000000000000000000000000000..4790fe71acc2c55cea0a986325c699d5115accba
--- /dev/null
+++ b/bob/bio/face/database/morph.py
@@ -0,0 +1,87 @@
+#!/usr/bin/env python
+# vim: set fileencoding=utf-8 :
+# Tiago de Freitas Pereira <tiago.pereira@idiap.ch>
+
+"""
+ MEDS database implementation
+"""
+
+from bob.bio.base.database import (
+ CSVDataset,
+ CSVDatasetZTNorm,
+)
+from bob.pipelines.datasets import CSVToSampleLoader
+from bob.bio.face.database.sample_loaders import EyesAnnotations
+from bob.extension import rc
+from bob.extension.download import get_file
+import bob.io.base
+from sklearn.pipeline import make_pipeline
+
+
+class MorphDatabase(CSVDatasetZTNorm):
+ """
+ The MORPH dataset is relatively old, but is getting some traction recently mostly because its richness
+ with respect to sensitive attributes.
+ It is composed by 55,000 samples from 13,000 subjects from men and women and five
+ race clusters (called ancestry) and they are the following: African, European, Asian, Hispanic and Others. Figure 8
+ present some samples from this database.
+
+ This dataset contains faces from five ethnicities (African, European, Asian, Hispanic, "Other")
+ and two genders (Male and Female).
+ Furthermore, this interface contains three verification protocols and they are:
+ `verification_fold1`, `verification_fold2` and `verification_fold1`.
+ Follow below the identities distribution in each set for the for each protocol:
+
+ +--------------------+---------------+-----------+-----------+-----------+
+ | | Training set | Dev. Set | Eval. Set |
+ +--------------------+---------------+-----------+ + +
+ | | T-References | Z-Probes | | |
+ +====================+===============+===========+===========+===========+
+ | verification_fold1 | 69 | 66 | 6738 | 6742 |
+ +--------------------+---------------+-----------+-----------+-----------+
+ | verification_fold2 | 69 | 67 | 6734 | 6737 |
+ +--------------------+---------------+-----------+-----------+-----------+
+ | verification_fold3 | 70 | 66 | 6736 | 6740 |
+ +--------------------+---------------+-----------+-----------+-----------+
+
+ .. warning::
+ Use the command below to set the path of the real data::
+
+ $ bob config set bob.db.morph.directory [PATH-TO-MORPH-DATA]
+
+ Parameters
+ ----------
+
+ protocol: str
+ One of the database protocols. Options are `verification_fold1`, `verification_fold2` and `verification_fold3`
+
+ """
+
+ def __init__(self, protocol):
+
+ # Downloading model if not exists
+ urls = [
+ "https://www.idiap.ch/software/bob/databases/latest/morph.tar.gz",
+ "http://www.idiap.ch/software/bob/databases/latest/morph.tar.gz",
+ ]
+ filename = get_file("morph.tar.gz", urls)
+
+ self.annotation_type = "eyes-center"
+ self.fixed_positions = None
+
+ database = CSVDataset(
+ filename,
+ protocol,
+ csv_to_sample_loader=make_pipeline(
+ CSVToSampleLoader(
+ data_loader=bob.io.base.load,
+ dataset_original_directory=rc["bob.db.morph.directory"]
+ if rc["bob.db.morph.directory"]
+ else "",
+ extension=".JPG",
+ ),
+ EyesAnnotations(),
+ ),
+ )
+
+ super().__init__(database)
diff --git a/bob/bio/face/database/sample_loaders.py b/bob/bio/face/database/sample_loaders.py
index ef5871c21dfc4424547d2dcf4995bc65ed53798b..607145ea69ed22831199765542cf924b5acdee86 100644
--- a/bob/bio/face/database/sample_loaders.py
+++ b/bob/bio/face/database/sample_loaders.py
@@ -32,8 +32,14 @@ class EyesAnnotations(TransformerMixin, BaseEstimator):
annotated_samples = []
for x in X:
eyes = {
- "leye": (find_attribute, (x, "leye_x"), find_attribute(x, "leye_y")),
- "reye": (find_attribute(x, "reye_x"), find_attribute(x, "reye_y")),
+ "leye": (
+ float(find_attribute(x, "leye_x")),
+ float(find_attribute(x, "leye_y")),
+ ),
+ "reye": (
+ float(find_attribute(x, "reye_x")),
+ float(find_attribute(x, "reye_y")),
+ ),
}
sample = DelayedSample(x._load, parent=x, annotations=eyes)
diff --git a/doc/implemented.rst b/doc/implemented.rst
index e1f29a24a187427b61f265d738ab8fb0f304034c..0deac2602496a6ed7390588ea7b7666459ef43d3 100644
--- a/doc/implemented.rst
+++ b/doc/implemented.rst
@@ -20,7 +20,8 @@ Databases
bob.bio.face.database.LFWBioDatabase
bob.bio.face.database.MultipieBioDatabase
bob.bio.face.database.FargoBioDatabase
- bob.bio.face.database.meds.MEDSDatabase
+ bob.bio.face.database.MEDSDatabase
+ bob.bio.face.database.MorphDatabase
Face Image Annotators
diff --git a/setup.py b/setup.py
index 4b978b1e1a46dab35c3a9572ed005a4b1c9dbe87..daf7cdb02e6053673d10f8343262a3103b686a8e 100644
--- a/setup.py
+++ b/setup.py
@@ -111,6 +111,7 @@ setup(
"replaymobile-img-spoof = bob.bio.face.config.database.replaymobile:replaymobile_spoof",
"fargo = bob.bio.face.config.database.fargo:database",
"meds = bob.bio.face.config.database.meds:database",
+ "morph = bob.bio.face.config.database.morph:database",
],
"bob.bio.annotator": [
"facedetect = bob.bio.face.config.annotator.facedetect:annotator",
@@ -172,6 +173,7 @@ setup(
"replaymobile-img-spoof = bob.bio.face.config.database.replaymobile_spoof",
"fargo = bob.bio.face.config.database.fargo",
"meds = bob.bio.face.config.database.meds",
+ "morph = bob.bio.face.config.database.morph",
],
"bob.bio.cli": [
"display-face-annotations = bob.bio.face.script.display_face_annotations:display_face_annotations",