From a81d163847baa4166c012337102aa8b84c421b52 Mon Sep 17 00:00:00 2001
From: Philip ABBET <philip.abbet@idiap.ch>
Date: Fri, 3 Nov 2017 10:49:39 +0100
Subject: [PATCH] Fix kboc16: There was already two versions of it on the
platform, different from ours
---
advanced/databases/kboc16/1.json | 109 +++----
advanced/databases/kboc16/1.py | 26 +-
advanced/databases/kboc16/1.rst | 23 +-
advanced/databases/kboc16/2.py | 476 ++++++++-----------------------
advanced/databases/kboc16/2.rst | 44 ++-
advanced/databases/kboc16/3.json | 76 +++++
advanced/databases/kboc16/3.py | 430 ++++++++++++++++++++++++++++
advanced/databases/kboc16/3.rst | 80 ++++++
8 files changed, 768 insertions(+), 496 deletions(-)
create mode 100644 advanced/databases/kboc16/3.json
create mode 100644 advanced/databases/kboc16/3.py
create mode 100644 advanced/databases/kboc16/3.rst
diff --git a/advanced/databases/kboc16/1.json b/advanced/databases/kboc16/1.json
index cf37377..3aee554 100644
--- a/advanced/databases/kboc16/1.json
+++ b/advanced/databases/kboc16/1.json
@@ -1,76 +1,41 @@
{
- "description": "The KBOC16 database",
- "root_folder": "/idiap/group/biometric/databases/kboc16",
- "protocols": [
- {
- "name": "A",
- "template": "simple_keystroke_recognition_kboc16",
- "sets": [
+ "root_folder": "/idiap/group/biometric/databases/kboc16",
+ "description": "The KBOC16 database",
+ "protocols": [
{
- "name": "templates",
- "template": "templates",
- "view": "Templates",
- "parameters": {
- "protocol": "A"
- },
- "outputs": {
- "file_id": "{{ system_user.username }}/uint64/1",
- "client_id": "{{ system_user.username }}/text/1",
- "template_id": "{{ system_user.username }}/text/1",
- "keystroke": "{{ user.username }}/kboc16_keystroke/1"
- }
- },
- {
- "name": "probes",
- "template": "probes",
- "view": "Probes",
- "parameters": {
- "protocol": "A"
- },
- "outputs": {
- "file_id": "{{ system_user.username }}/uint64/1",
- "probe_id": "{{ system_user.username }}/uint64/1",
- "client_id": "{{ system_user.username }}/text/1",
- "template_ids": "{{ system_user.username }}/array_1d_text/1",
- "keystroke": "{{ user.username }}/kboc16_keystroke/1"
- }
- }
- ]
- },
- {
- "name": "D",
- "template": "simple_keystroke_recognition_kboc16",
- "sets": [
- {
- "name": "templates",
- "template": "templates",
- "view": "Templates",
- "parameters": {
- "protocol": "D"
- },
- "outputs": {
- "file_id": "{{ system_user.username }}/uint64/1",
- "client_id": "{{ system_user.username }}/text/1",
- "template_id": "{{ system_user.username }}/text/1",
- "keystroke": "{{ user.username }}/kboc16_keystroke/1"
- }
- },
- {
- "name": "probes",
- "template": "probes",
- "view": "Probes",
- "parameters": {
- "protocol": "D"
- },
- "outputs": {
- "file_id": "{{ system_user.username }}/uint64/1",
- "probe_id": "{{ system_user.username }}/uint64/1",
- "client_id": "{{ system_user.username }}/text/1",
- "template_ids": "{{ system_user.username }}/array_1d_text/1",
- "keystroke": "{{ user.username }}/kboc16_keystroke/1"
- }
+ "name": "D",
+ "template": "simple_keystroke_recognition_kboc16",
+ "sets": [
+ {
+ "outputs": {
+ "keystroke": "{{ system_user.username }}/kboc16_keystroke/1",
+ "file_id": "{{ system_user.username }}/uint64/1",
+ "client_id": "{{ system_user.username }}/text/1",
+ "template_id": "{{ system_user.username }}/text/1"
+ },
+ "view": "Templates",
+ "name": "templates",
+ "parameters": {
+ "protocol": "D"
+ },
+ "template": "templates"
+ },
+ {
+ "outputs": {
+ "probe_id": "{{ system_user.username }}/uint64/1",
+ "keystroke": "{{ system_user.username }}/kboc16_keystroke/1",
+ "file_id": "{{ system_user.username }}/uint64/1",
+ "client_id": "{{ system_user.username }}/text/1",
+ "template_ids": "{{ system_user.username }}/array_1d_text/1"
+ },
+ "view": "Probes",
+ "name": "probes",
+ "parameters": {
+ "protocol": "D"
+ },
+ "template": "probes"
+ }
+ ]
}
- ]
- }
- ]
+ ]
}
diff --git a/advanced/databases/kboc16/1.py b/advanced/databases/kboc16/1.py
index 03ad415..60437f2 100644
--- a/advanced/databases/kboc16/1.py
+++ b/advanced/databases/kboc16/1.py
@@ -1,33 +1,9 @@
-###############################################################################
-# #
-# Copyright (c) 2016 Idiap Research Institute, http://www.idiap.ch/ #
-# Contact: beat.support@idiap.ch #
-# #
-# This file is part of the beat.examples module of the BEAT platform. #
-# #
-# Commercial License Usage #
-# Licensees holding valid commercial BEAT licenses may use this file in #
-# accordance with the terms contained in a written agreement between you #
-# and Idiap. For further information contact tto@idiap.ch #
-# #
-# Alternatively, this file may be used under the terms of the GNU Affero #
-# Public License version 3 as published by the Free Software and appearing #
-# in the file LICENSE.AGPL included in the packaging of this file. #
-# The BEAT platform is distributed in the hope that it will be useful, but #
-# WITHOUT ANY WARRANTY; without even the implied warranty of MERCHANTABILITY #
-# or FITNESS FOR A PARTICULAR PURPOSE. #
-# #
-# You should have received a copy of the GNU Affero Public License along #
-# with the BEAT platform. If not, see http://www.gnu.org/licenses/. #
-# #
-###############################################################################
-
import string
import numpy
import bob.db.kboc16
-keystroke_feature = ['', 'holdtime', 'key_events']
+keystroke_feature = ['', 'timestamps', 'key_events']
#keystroke_type = ['', 'given_name', 'family_name', 'email', 'nationality', 'id_number']
def keystroke_reader(filename):
diff --git a/advanced/databases/kboc16/1.rst b/advanced/databases/kboc16/1.rst
index e058314..201e96a 100644
--- a/advanced/databases/kboc16/1.rst
+++ b/advanced/databases/kboc16/1.rst
@@ -1,24 +1,3 @@
-.. Copyright (c) 2016 Idiap Research Institute, http://www.idiap.ch/ ..
-.. Contact: beat.support@idiap.ch ..
-.. ..
-.. This file is part of the beat.examples module of the BEAT platform. ..
-.. ..
-.. Commercial License Usage ..
-.. Licensees holding valid commercial BEAT licenses may use this file in ..
-.. accordance with the terms contained in a written agreement between you ..
-.. and Idiap. For further information contact tto@idiap.ch ..
-.. ..
-.. Alternatively, this file may be used under the terms of the GNU Affero ..
-.. Public License version 3 as published by the Free Software and appearing ..
-.. in the file LICENSE.AGPL included in the packaging of this file. ..
-.. The BEAT platform is distributed in the hope that it will be useful, but ..
-.. WITHOUT ANY WARRANTY; without even the implied warranty of MERCHANTABILITY ..
-.. or FITNESS FOR A PARTICULAR PURPOSE. ..
-.. ..
-.. You should have received a copy of the GNU Affero Public License along ..
-.. with the BEAT platform. If not, see http://www.gnu.org/licenses/. ..
-
-
The KBOC16 Database
-------------------
@@ -61,4 +40,4 @@ available in the publications section of the `ATVS group webpage
.. [BTAS16] To appear.
Please remember to reference [BTAS15]_ and [BTAS16]_ on any work made public,
-whatever the form, based directly or indirectly on any part of the KBOC16 DB.
+whatever the form, based directly or indirectly on any part of the KBOC16 DB.
\ No newline at end of file
diff --git a/advanced/databases/kboc16/2.py b/advanced/databases/kboc16/2.py
index 34c0dd0..03ad415 100644
--- a/advanced/databases/kboc16/2.py
+++ b/advanced/databases/kboc16/2.py
@@ -1,6 +1,6 @@
###############################################################################
# #
-# Copyright (c) 2017 Idiap Research Institute, http://www.idiap.ch/ #
+# Copyright (c) 2016 Idiap Research Institute, http://www.idiap.ch/ #
# Contact: beat.support@idiap.ch #
# #
# This file is part of the beat.examples module of the BEAT platform. #
@@ -23,408 +23,180 @@
###############################################################################
import string
-import numpy as np
+import numpy
import bob.db.kboc16
-#----------------------------------------------------------
-
+keystroke_feature = ['', 'holdtime', 'key_events']
+#keystroke_type = ['', 'given_name', 'family_name', 'email', 'nationality', 'id_number']
def keystroke_reader(filename):
- times = []
- keys = []
-
- for line in open(filename, 'r').readlines():
- parts = string.split(line)
- times.append(numpy.int32(parts[1]))
- keys.append(parts[0])
-
- return dict(
- holdtime = times,
- key_events = keys,
- )
-
-
-#----------------------------------------------------------
-
-
-def get_client_end_index(objs, client_id, client_start_index,
- start_index, end_index):
- client_end_index = client_start_index
-
- while client_end_index + 1 <= end_index:
- obj = objs[client_end_index + 1 - start_index]
-
- if isinstance(obj, tuple):
- obj = obj[1]
-
- if obj.client_id != client_id:
- return client_end_index
-
- client_end_index += 1
-
- return end_index
-
-
-#----------------------------------------------------------
-
-
-def get_value_end_index(objs, value, index_in_tuple, value_start_index,
- start_index, end_index):
- value_end_index = value_start_index
-
- while value_end_index + 1 <= end_index:
- id = objs[value_end_index + 1 - start_index][index_in_tuple]
+ data = {}
+ valuesTime = []
+ valuesKey = []
+ for line in open(filename, 'r').readlines():
+ parts = string.split(line)
+ valuesTime.append(numpy.int32(parts[1]))
+ valuesKey.append(parts[0])
- if id != value:
- return value_end_index
+ data[keystroke_feature[1]] = valuesTime
+ data[keystroke_feature[2]] = valuesKey
- value_end_index += 1
-
- return end_index
-
-
-#----------------------------------------------------------
+ return data
class Templates:
- """Outputs:
- - keystroke: "{{ user.username }}/kboc16_keystroke/1
- - file_id: "{{ system_user.username }}/uint64/1"
- - template_id: "{{ system_user.username }}/text/1"
- - client_id: "{{ system_user.username }}/text/1"
-
- One "file_id" is associated with a given "keystroke".
- Several "keystroke" are associated with a given "template_id".
- Several "template_id" are associated with a given "client_id".
-
- --------------- --------------- --------------- --------------- --------------- ---------------
- | keystroke | | keystroke | | keystroke | | keystroke | | keystroke | | keystroke |
- --------------- --------------- --------------- --------------- --------------- ---------------
- --------------- --------------- --------------- --------------- --------------- ---------------
- | file_id | | file_id | | file_id | | file_id | | file_id | | file_id |
- --------------- --------------- --------------- --------------- --------------- ---------------
- ----------------------------------------------- -----------------------------------------------
- | template_id | | template_id |
- ----------------------------------------------- -----------------------------------------------
- -----------------------------------------------------------------------------------------------
- | client_id |
- -----------------------------------------------------------------------------------------------
-
- Note: for this particular database, there is only one "template_id"
- per "client_id".
- """
-
- def setup(self, root_folder, outputs, parameters, force_start_index=None,
- force_end_index=None):
-
- # Initialisations
- self.root_folder = root_folder
- self.outputs = outputs
- self.parameters = parameters
-
- # Open the database and load the objects to provide via the outputs
- self.db = bob.db.kboc16.Database()
-
- template_ids = self.db.model_ids(groups='eval',
- protocol=parameters['protocol'])
-
- self.objs = []
-
- for template_id in template_ids:
- objs = self.db.objects(groups='eval',
- protocol=self.parameters['protocol'],
- purposes='enrol',
- model_ids=[template_id])
-
- self.objs.extend([ (template_id, obj) for obj in objs ])
-
- self.objs = sorted(self.objs, key=lambda x: (x[1].client_id, x[0], x[1].id))
-
- # Determine the range of indices that must be provided
- self.start_index = force_start_index if force_start_index is not None else 0
- self.end_index = force_end_index if force_end_index is not None else len(self.objs) - 1
-
- self.objs = self.objs[self.start_index : self.end_index + 1]
-
- self.next_index = self.start_index
+ # Reasoning: Each client may have a number of models in certain databases.
+ # So, each model receives an unique identifier. Those identifiers are linked
+ # to the client identifier and contain a number of keystrokes to generated
+ # the model from.
+
+ def setup(self, root_folder, outputs, parameters, force_start_index=None, force_end_index=None):
+ self.root_folder = root_folder
+ self.outputs = outputs
+ self.parameters = parameters
+
+ self.db = bob.db.kboc16.Database()
+
+ self.template_ids = sorted([str(v) for v in self.db.model_ids(groups='eval',
+ protocol=parameters['protocol'])])
+ self.objs = None
+
+ self.current_template_index = 0
+ self.current_obj_index = 0
+ self.next_index = 0
+
+ self.force_start_index = force_start_index
+ self.force_end_index = force_end_index
+
+ # Retrieve only 'useful' data
+ ### End index
+ #if self.force_end_index is not None:
+ # self.objs = self.objs[:self.force_end_index+1]
+ ### Start index
+ if self.force_start_index is None:
+ self.force_start_index = 0
+ while self.next_index < self.force_start_index:
+ self.next()
return True
- def done(self, last_data_index):
- return last_data_index >= self.end_index
+ def done(self):
+ return (self.current_template_index >= len(self.template_ids)) or (self.force_end_index is not None and self.force_end_index < self.next_index)
def next(self):
- (template_id, obj) = self.objs[self.next_index - self.start_index]
-
-
- # Output: template_id (only provide data when the template_id change)
- if self.outputs['template_id'].isConnected() and \
- self.outputs['template_id'].last_written_data_index < self.next_index:
-
- template_end_index = get_value_end_index(self.objs, template_id, 0,
- self.next_index,
- self.start_index,
- self.end_index)
-
- self.outputs['template_id'].write(
- {
- 'text': str(template_id)
- },
- template_end_index
- )
+ if self.objs is None:
+ # probe for the specific objects concerning a given client
+ self.objs = sorted(self.db.objects(model_ids=[self.template_ids[self.current_template_index]],
+ groups='eval',
+ protocol=self.parameters['protocol'],
+ purposes='enrol'), key=lambda x: x.id)
+ if self.force_start_index <= self.next_index and (self.force_end_index is None or self.force_end_index >= self.next_index):
+ # For this database, 'self.template_ids[self.current_template_index]' corresponds to 'obj.client_id'
+ if self.outputs['template_id'].isConnected():
+ self.outputs['template_id'].write({'text': str(self.template_ids[self.current_template_index])}, self.next_index+len(self.objs)-1)
- # Output: client_id (only provide data when the client_id change)
- if self.outputs['client_id'].isConnected() and \
- self.outputs['client_id'].last_written_data_index < self.next_index:
+ if self.outputs['client_id'].isConnected():
+ self.outputs['client_id'].write({'text': str(self.objs[0].client_id)}, self.next_index+len(self.objs)-1)
- client_end_index = get_client_end_index(self.objs, obj.client_id,
- self.next_index,
- self.start_index,
- self.end_index)
+ obj = self.objs[self.current_obj_index]
- self.outputs['client_id'].write(
- {
- 'text': str(obj.client_id)
- },
- client_end_index
- )
+ if self.outputs['file_id'].isConnected() or self.outputs['keystroke'].isConnected():
+ if self.force_start_index <= self.next_index and (self.force_end_index is None or self.force_end_index >= self.next_index):
+ if self.outputs['file_id'].isConnected():
+ self.outputs['file_id'].write({'value': numpy.uint64(obj.id)}, self.next_index)
+ if self.outputs['keystroke'].isConnected():
+ data = keystroke_reader(obj.make_path(self.root_folder, '.txt'))
+ self.outputs['keystroke'].write(data, self.next_index)
- # Output: file_id (provide data at each iteration)
- if self.outputs['file_id'].isConnected():
- self.outputs['file_id'].write(
- {
- 'value': np.uint64(obj.id)
- },
- self.next_index
- )
-
+ self.next_index += 1
+ self.current_obj_index += 1
- # Output: image (provide data at each iteration)
- if self.outputs['keystroke'].isConnected():
- self.outputs['keystroke'].write(
- keystroke_reader(obj.make_path(self.root_folder, '.txt')),
- self.next_index
- )
+ else:
+ self.next_index += len(self.objs)
+ self.current_obj_index = len(self.objs)
-
- # Determine the next data index that must be provided
- self.next_index = 1 + min([ x.last_written_data_index for x in self.outputs
- if x.isConnected() ]
- )
+ if self.current_obj_index == len(self.objs):
+ self.objs = None
+ self.current_obj_index = 0
+ self.current_template_index += 1
return True
-#----------------------------------------------------------
-
-
class Probes:
- """Outputs:
- - keystroke: "{{ user.username }}/kboc16_keystroke/1
- - file_id: "{{ system_user.username }}/uint64/1"
- - client_id: "{{ system_user.username }}/text/1"
- - probe_id: "{{ system_user.username }}/uint64/1",
- - template_ids: "{{ system_user.username }}/array_1d_text/1",
-
- One "file_id" is associated with a given "keystroke".
- One "probe_id" is associated with a given "keystroke".
- Several "keystroke" are associated with a given "client_id".
- Several "client_id" are associated with a given "template_ids".
-
- --------------- --------------- --------------- --------------- --------------- ---------------
- | keystroke | | keystroke | | keystroke | | keystroke | | keystroke | | keystroke |
- --------------- --------------- --------------- --------------- --------------- ---------------
- --------------- --------------- --------------- --------------- --------------- ---------------
- | file_id | | file_id | | file_id | | file_id | | file_id | | file_id |
- --------------- --------------- --------------- --------------- --------------- ---------------
- --------------- --------------- --------------- --------------- --------------- ---------------
- | probe_id | | probe_id | | probe_id | | probe_id | | probe_id | | probe_id |
- --------------- --------------- --------------- --------------- --------------- ---------------
- ----------------------------------------------- -----------------------------------------------
- | client_id | | client_id |
- ----------------------------------------------- -----------------------------------------------
- -----------------------------------------------------------------------------------------------
- | template_ids |
- -----------------------------------------------------------------------------------------------
- """
-
- def setup(self, root_folder, outputs, parameters, force_start_index=None,
- force_end_index=None):
-
- # Initialisations
+ # Reasoning: Each client may have a number of probes. Each probe may be
+ # composed of any number of keystrokes. So, each probe receives an unique
+ # identifier. Those identifiers are linked to the client identifier and
+ # contain a number of keystrokes to generated the match/comparison score.
+ # Each probe must be matched against a number of models defined by a list
+ # of client identifiers.
+
+ def setup(self, root_folder, outputs, parameters, force_start_index=None, force_end_index=None):
self.root_folder = root_folder
- self.outputs = outputs
- self.parameters = parameters
-
- # Open the database and load the objects to provide via the outputs
- self.db = bob.db.kboc16.Database()
-
- template_ids = sorted(self.db.model_ids(protocol=parameters['protocol'],
- groups='eval'),
- key=lambda x: int(x))
-
- template_probes = {}
- for template_id in template_ids:
- objs = sorted(self.db.objects(protocol=parameters['protocol'],
- groups='eval',
- purposes='probe',
- model_ids=[template_id]),
- key=lambda x: (x.client_id, x.id))
+ self.outputs = outputs
+ self.parameters = parameters
- template_probes[template_id] = [ p.id for p in objs ]
+ self.db = bob.db.kboc16.Database()
- objs = sorted(self.db.objects(protocol=parameters['protocol'],
- groups='eval',
- purposes='probe'),
- key=lambda x: (x.client_id, x.id))
+ self.template_ids = sorted([str(v) for v in self.db.model_ids(groups='eval',
+ protocol=parameters['protocol'])])
+ self.objs = sorted(self.db.objects(groups='eval', protocol=self.parameters['protocol'], purposes='probe'), key=lambda x: x.id)
- self.objs = []
- for obj in objs:
- templates = [ template_id for template_id in template_ids
- if obj.id in template_probes[template_id] ]
- self.objs.append( (templates, obj) )
+ self.template_probes = {}
+ for t_id in self.template_ids:
+ self.template_probes[t_id] = [p.id for p in sorted(self.db.objects(model_ids=[t_id], groups='eval', protocol=self.parameters['protocol'], purposes='probe'), key=lambda x: x.id)]
- self.objs = sorted(self.objs, key=lambda x: (len(x[0]), x[0], x[1].client_id, x[1].id))
+ self.next_index = 0
- # Determine the range of indices that must be provided
- self.start_index = force_start_index if force_start_index is not None else 0
- self.end_index = force_end_index if force_end_index is not None else len(self.objs) - 1
+ self.force_start_index = force_start_index
+ self.force_end_index = force_end_index
- self.objs = self.objs[self.start_index : self.end_index + 1]
-
- self.next_index = self.start_index
+ # Retrieve only 'useful' data
+ ### End index
+ if self.force_end_index is not None:
+ self.objs = self.objs[:self.force_end_index+1]
+ ### Start index
+ if self.force_start_index is not None:
+ self.objs = self.objs[self.force_start_index:]
+ self.next_index = self.force_start_index
+ else:
+ self.force_start_index = 0
return True
- def done(self, last_data_index):
- return last_data_index >= self.end_index
+ def done(self):
+ return (self.next_index-self.force_start_index >= len(self.objs))
def next(self):
- (template_ids, obj) = self.objs[self.next_index - self.start_index]
-
-
- # Output: template_ids (only provide data when the template_ids change)
- if self.outputs['template_ids'].isConnected() and \
- self.outputs['template_ids'].last_written_data_index < self.next_index:
-
- template_ids_end_index = get_value_end_index(self.objs, template_ids, 0,
- self.next_index,
- self.start_index,
- self.end_index)
-
- self.outputs['template_ids'].write(
- {
- 'text': [ str(x) for x in template_ids ]
- },
- template_ids_end_index
- )
-
-
- # Output: client_id (only provide data when the client_id change)
- if self.outputs['client_id'].isConnected() and \
- self.outputs['client_id'].last_written_data_index < self.next_index:
-
- client_end_index = get_client_end_index(self.objs, obj.client_id,
- self.next_index,
- self.start_index,
- self.end_index)
- self.outputs['client_id'].write(
- {
- 'text': str(obj.client_id)
- },
- client_end_index
- )
+ obj = self.objs[self.next_index-self.force_start_index]
+ if self.outputs['file_id'].isConnected():
+ self.outputs['file_id'].write({'value': numpy.uint64(obj.id)}, self.next_index)
- # Output: probe_id (provide data at each iteration)
if self.outputs['probe_id'].isConnected():
- self.outputs['probe_id'].write(
- {
- 'value': np.uint64(obj.id)
- },
- self.next_index
- )
-
- # Output: file_id (provide data at each iteration)
- if self.outputs['file_id'].isConnected():
- self.outputs['file_id'].write(
- {
- 'value': np.uint64(obj.id)
- },
- self.next_index
- )
+ self.outputs['probe_id'].write({'value': numpy.uint64(obj.id)}, self.next_index)
+ if self.outputs['client_id'].isConnected():
+ self.outputs['client_id'].write({'text': str(obj.client_id)}, self.next_index)
- # Output: image (provide data at each iteration)
- if self.outputs['keystroke'].isConnected():
- self.outputs['keystroke'].write(
- keystroke_reader(obj.make_path(self.root_folder, '.txt')),
- self.next_index
- )
+ if self.outputs['template_ids'].isConnected():
+ data = {
+ 'text': [t_id for t_id in self.template_ids if obj.id in self.template_probes[t_id]]
+ }
+ self.outputs['template_ids'].write(data, self.next_index)
+ if self.outputs['keystroke'].isConnected():
+ data = keystroke_reader(obj.make_path(self.root_folder, '.txt'))
+ self.outputs['keystroke'].write(data, self.next_index)
- # Determine the next data index that must be provided
- self.next_index = 1 + min([ x.last_written_data_index for x in self.outputs
- if x.isConnected() ]
- )
+ self.next_index += 1
return True
-
-
-#----------------------------------------------------------
-
-
-def setup_tests():
- # Install a mock load function for the keystrokes
- def mock_keystroke_reader(filename):
- return {}
-
- global keystroke_reader
- keystroke_reader = mock_keystroke_reader
-
-
-#----------------------------------------------------------
-
-
-# Test the behavior of the views (on fake data)
-if __name__ == '__main__':
-
- setup_tests()
-
- from beat.backend.python.database import DatabaseTester
-
- DatabaseTester('Templates', Templates,
- [
- 'client_id',
- 'template_id',
- 'file_id',
- 'keystroke',
- ],
- dict(
- protocol = 'A',
- )
- )
-
- DatabaseTester('Probes', Probes,
- [
- 'template_ids',
- 'client_id',
- 'probe_id',
- 'file_id',
- 'keystroke',
- ],
- dict(
- protocol = 'A',
- ),
- irregular_outputs = [
- 'client_id',
- ]
- )
diff --git a/advanced/databases/kboc16/2.rst b/advanced/databases/kboc16/2.rst
index dfc6911..ccb5f0c 100644
--- a/advanced/databases/kboc16/2.rst
+++ b/advanced/databases/kboc16/2.rst
@@ -1,35 +1,15 @@
-.. Copyright (c) 2017 Idiap Research Institute, http://www.idiap.ch/ ..
-.. Contact: beat.support@idiap.ch ..
-.. ..
-.. This file is part of the beat.examples module of the BEAT platform. ..
-.. ..
-.. Commercial License Usage ..
-.. Licensees holding valid commercial BEAT licenses may use this file in ..
-.. accordance with the terms contained in a written agreement between you ..
-.. and Idiap. For further information contact tto@idiap.ch ..
-.. ..
-.. Alternatively, this file may be used under the terms of the GNU Affero ..
-.. Public License version 3 as published by the Free Software and appearing ..
-.. in the file LICENSE.AGPL included in the packaging of this file. ..
-.. The BEAT platform is distributed in the hope that it will be useful, but ..
-.. WITHOUT ANY WARRANTY; without even the implied warranty of MERCHANTABILITY ..
-.. or FITNESS FOR A PARTICULAR PURPOSE. ..
-.. ..
-.. You should have received a copy of the GNU Affero Public License along ..
-.. with the BEAT platform. If not, see http://www.gnu.org/licenses/. ..
-
-
The KBOC16 Database
-------------------
+
Changelog
=========
-* **Version 2**, 30/Oct/2017:
+* **Version 2**, 4/Apr/2016:
- - Port to beat.backend.python v1.4.2
+ - Added protocol ``A``
-* **Version 1**:
+* **Version 1**, 09/Feb/2016:
- Initial release
@@ -68,9 +48,23 @@ competition results we refer the reader to (the following articles are publicly
available in the publications section of the `ATVS group webpage
<http://atvs.ii.uam.es/listpublications.do>`_)
+Implemented protocols are:
+
+* **Protocol A**: Complete dataset (300 users). This is the dataset used during
+ the final kboc16 evaluation (same dataset in the offline evaluation).
+* **Protocol D**: Subset with first 100 users of the complete dataset. This
+ dataset was used to better generalize the models of the participants and
+ avoid overfitting.
+
+
+
+References
+==========
+
+
.. [BTAS15] A. Morales, M. Falanga, J. Fierrez, C. Sansone and J. Ortega-Garcia, ''Keystroke Dynamics Recognition based on Personal Data: A Comparative Experimental Evaluation Implementing Reproducible Research'', in Proc. of the IEEE Seventh International Conference on Biometrics: Theory, Applications and Systems, Arlington, Virginia, USA, September 2015.
.. [BTAS16] To appear.
Please remember to reference [BTAS15]_ and [BTAS16]_ on any work made public,
-whatever the form, based directly or indirectly on any part of the KBOC16 DB.
+whatever the form, based directly or indirectly on any part of the KBOC16 DB.
\ No newline at end of file
diff --git a/advanced/databases/kboc16/3.json b/advanced/databases/kboc16/3.json
new file mode 100644
index 0000000..cf37377
--- /dev/null
+++ b/advanced/databases/kboc16/3.json
@@ -0,0 +1,76 @@
+{
+ "description": "The KBOC16 database",
+ "root_folder": "/idiap/group/biometric/databases/kboc16",
+ "protocols": [
+ {
+ "name": "A",
+ "template": "simple_keystroke_recognition_kboc16",
+ "sets": [
+ {
+ "name": "templates",
+ "template": "templates",
+ "view": "Templates",
+ "parameters": {
+ "protocol": "A"
+ },
+ "outputs": {
+ "file_id": "{{ system_user.username }}/uint64/1",
+ "client_id": "{{ system_user.username }}/text/1",
+ "template_id": "{{ system_user.username }}/text/1",
+ "keystroke": "{{ user.username }}/kboc16_keystroke/1"
+ }
+ },
+ {
+ "name": "probes",
+ "template": "probes",
+ "view": "Probes",
+ "parameters": {
+ "protocol": "A"
+ },
+ "outputs": {
+ "file_id": "{{ system_user.username }}/uint64/1",
+ "probe_id": "{{ system_user.username }}/uint64/1",
+ "client_id": "{{ system_user.username }}/text/1",
+ "template_ids": "{{ system_user.username }}/array_1d_text/1",
+ "keystroke": "{{ user.username }}/kboc16_keystroke/1"
+ }
+ }
+ ]
+ },
+ {
+ "name": "D",
+ "template": "simple_keystroke_recognition_kboc16",
+ "sets": [
+ {
+ "name": "templates",
+ "template": "templates",
+ "view": "Templates",
+ "parameters": {
+ "protocol": "D"
+ },
+ "outputs": {
+ "file_id": "{{ system_user.username }}/uint64/1",
+ "client_id": "{{ system_user.username }}/text/1",
+ "template_id": "{{ system_user.username }}/text/1",
+ "keystroke": "{{ user.username }}/kboc16_keystroke/1"
+ }
+ },
+ {
+ "name": "probes",
+ "template": "probes",
+ "view": "Probes",
+ "parameters": {
+ "protocol": "D"
+ },
+ "outputs": {
+ "file_id": "{{ system_user.username }}/uint64/1",
+ "probe_id": "{{ system_user.username }}/uint64/1",
+ "client_id": "{{ system_user.username }}/text/1",
+ "template_ids": "{{ system_user.username }}/array_1d_text/1",
+ "keystroke": "{{ user.username }}/kboc16_keystroke/1"
+ }
+ }
+ ]
+ }
+ ]
+}
diff --git a/advanced/databases/kboc16/3.py b/advanced/databases/kboc16/3.py
new file mode 100644
index 0000000..34c0dd0
--- /dev/null
+++ b/advanced/databases/kboc16/3.py
@@ -0,0 +1,430 @@
+###############################################################################
+# #
+# Copyright (c) 2017 Idiap Research Institute, http://www.idiap.ch/ #
+# Contact: beat.support@idiap.ch #
+# #
+# This file is part of the beat.examples module of the BEAT platform. #
+# #
+# Commercial License Usage #
+# Licensees holding valid commercial BEAT licenses may use this file in #
+# accordance with the terms contained in a written agreement between you #
+# and Idiap. For further information contact tto@idiap.ch #
+# #
+# Alternatively, this file may be used under the terms of the GNU Affero #
+# Public License version 3 as published by the Free Software and appearing #
+# in the file LICENSE.AGPL included in the packaging of this file. #
+# The BEAT platform is distributed in the hope that it will be useful, but #
+# WITHOUT ANY WARRANTY; without even the implied warranty of MERCHANTABILITY #
+# or FITNESS FOR A PARTICULAR PURPOSE. #
+# #
+# You should have received a copy of the GNU Affero Public License along #
+# with the BEAT platform. If not, see http://www.gnu.org/licenses/. #
+# #
+###############################################################################
+
+import string
+import numpy as np
+import bob.db.kboc16
+
+
+#----------------------------------------------------------
+
+
+def keystroke_reader(filename):
+ times = []
+ keys = []
+
+ for line in open(filename, 'r').readlines():
+ parts = string.split(line)
+ times.append(numpy.int32(parts[1]))
+ keys.append(parts[0])
+
+ return dict(
+ holdtime = times,
+ key_events = keys,
+ )
+
+
+#----------------------------------------------------------
+
+
+def get_client_end_index(objs, client_id, client_start_index,
+ start_index, end_index):
+ client_end_index = client_start_index
+
+ while client_end_index + 1 <= end_index:
+ obj = objs[client_end_index + 1 - start_index]
+
+ if isinstance(obj, tuple):
+ obj = obj[1]
+
+ if obj.client_id != client_id:
+ return client_end_index
+
+ client_end_index += 1
+
+ return end_index
+
+
+#----------------------------------------------------------
+
+
+def get_value_end_index(objs, value, index_in_tuple, value_start_index,
+ start_index, end_index):
+ value_end_index = value_start_index
+
+ while value_end_index + 1 <= end_index:
+ id = objs[value_end_index + 1 - start_index][index_in_tuple]
+
+ if id != value:
+ return value_end_index
+
+ value_end_index += 1
+
+ return end_index
+
+
+#----------------------------------------------------------
+
+
+class Templates:
+ """Outputs:
+ - keystroke: "{{ user.username }}/kboc16_keystroke/1
+ - file_id: "{{ system_user.username }}/uint64/1"
+ - template_id: "{{ system_user.username }}/text/1"
+ - client_id: "{{ system_user.username }}/text/1"
+
+ One "file_id" is associated with a given "keystroke".
+ Several "keystroke" are associated with a given "template_id".
+ Several "template_id" are associated with a given "client_id".
+
+ --------------- --------------- --------------- --------------- --------------- ---------------
+ | keystroke | | keystroke | | keystroke | | keystroke | | keystroke | | keystroke |
+ --------------- --------------- --------------- --------------- --------------- ---------------
+ --------------- --------------- --------------- --------------- --------------- ---------------
+ | file_id | | file_id | | file_id | | file_id | | file_id | | file_id |
+ --------------- --------------- --------------- --------------- --------------- ---------------
+ ----------------------------------------------- -----------------------------------------------
+ | template_id | | template_id |
+ ----------------------------------------------- -----------------------------------------------
+ -----------------------------------------------------------------------------------------------
+ | client_id |
+ -----------------------------------------------------------------------------------------------
+
+ Note: for this particular database, there is only one "template_id"
+ per "client_id".
+ """
+
+ def setup(self, root_folder, outputs, parameters, force_start_index=None,
+ force_end_index=None):
+
+ # Initialisations
+ self.root_folder = root_folder
+ self.outputs = outputs
+ self.parameters = parameters
+
+ # Open the database and load the objects to provide via the outputs
+ self.db = bob.db.kboc16.Database()
+
+ template_ids = self.db.model_ids(groups='eval',
+ protocol=parameters['protocol'])
+
+ self.objs = []
+
+ for template_id in template_ids:
+ objs = self.db.objects(groups='eval',
+ protocol=self.parameters['protocol'],
+ purposes='enrol',
+ model_ids=[template_id])
+
+ self.objs.extend([ (template_id, obj) for obj in objs ])
+
+ self.objs = sorted(self.objs, key=lambda x: (x[1].client_id, x[0], x[1].id))
+
+ # Determine the range of indices that must be provided
+ self.start_index = force_start_index if force_start_index is not None else 0
+ self.end_index = force_end_index if force_end_index is not None else len(self.objs) - 1
+
+ self.objs = self.objs[self.start_index : self.end_index + 1]
+
+ self.next_index = self.start_index
+
+ return True
+
+
+ def done(self, last_data_index):
+ return last_data_index >= self.end_index
+
+
+ def next(self):
+ (template_id, obj) = self.objs[self.next_index - self.start_index]
+
+
+ # Output: template_id (only provide data when the template_id change)
+ if self.outputs['template_id'].isConnected() and \
+ self.outputs['template_id'].last_written_data_index < self.next_index:
+
+ template_end_index = get_value_end_index(self.objs, template_id, 0,
+ self.next_index,
+ self.start_index,
+ self.end_index)
+
+ self.outputs['template_id'].write(
+ {
+ 'text': str(template_id)
+ },
+ template_end_index
+ )
+
+
+ # Output: client_id (only provide data when the client_id change)
+ if self.outputs['client_id'].isConnected() and \
+ self.outputs['client_id'].last_written_data_index < self.next_index:
+
+ client_end_index = get_client_end_index(self.objs, obj.client_id,
+ self.next_index,
+ self.start_index,
+ self.end_index)
+
+ self.outputs['client_id'].write(
+ {
+ 'text': str(obj.client_id)
+ },
+ client_end_index
+ )
+
+
+ # Output: file_id (provide data at each iteration)
+ if self.outputs['file_id'].isConnected():
+ self.outputs['file_id'].write(
+ {
+ 'value': np.uint64(obj.id)
+ },
+ self.next_index
+ )
+
+
+ # Output: image (provide data at each iteration)
+ if self.outputs['keystroke'].isConnected():
+ self.outputs['keystroke'].write(
+ keystroke_reader(obj.make_path(self.root_folder, '.txt')),
+ self.next_index
+ )
+
+
+ # Determine the next data index that must be provided
+ self.next_index = 1 + min([ x.last_written_data_index for x in self.outputs
+ if x.isConnected() ]
+ )
+
+ return True
+
+
+#----------------------------------------------------------
+
+
+class Probes:
+ """Outputs:
+ - keystroke: "{{ user.username }}/kboc16_keystroke/1
+ - file_id: "{{ system_user.username }}/uint64/1"
+ - client_id: "{{ system_user.username }}/text/1"
+ - probe_id: "{{ system_user.username }}/uint64/1",
+ - template_ids: "{{ system_user.username }}/array_1d_text/1",
+
+ One "file_id" is associated with a given "keystroke".
+ One "probe_id" is associated with a given "keystroke".
+ Several "keystroke" are associated with a given "client_id".
+ Several "client_id" are associated with a given "template_ids".
+
+ --------------- --------------- --------------- --------------- --------------- ---------------
+ | keystroke | | keystroke | | keystroke | | keystroke | | keystroke | | keystroke |
+ --------------- --------------- --------------- --------------- --------------- ---------------
+ --------------- --------------- --------------- --------------- --------------- ---------------
+ | file_id | | file_id | | file_id | | file_id | | file_id | | file_id |
+ --------------- --------------- --------------- --------------- --------------- ---------------
+ --------------- --------------- --------------- --------------- --------------- ---------------
+ | probe_id | | probe_id | | probe_id | | probe_id | | probe_id | | probe_id |
+ --------------- --------------- --------------- --------------- --------------- ---------------
+ ----------------------------------------------- -----------------------------------------------
+ | client_id | | client_id |
+ ----------------------------------------------- -----------------------------------------------
+ -----------------------------------------------------------------------------------------------
+ | template_ids |
+ -----------------------------------------------------------------------------------------------
+ """
+
+ def setup(self, root_folder, outputs, parameters, force_start_index=None,
+ force_end_index=None):
+
+ # Initialisations
+ self.root_folder = root_folder
+ self.outputs = outputs
+ self.parameters = parameters
+
+ # Open the database and load the objects to provide via the outputs
+ self.db = bob.db.kboc16.Database()
+
+ template_ids = sorted(self.db.model_ids(protocol=parameters['protocol'],
+ groups='eval'),
+ key=lambda x: int(x))
+
+ template_probes = {}
+ for template_id in template_ids:
+ objs = sorted(self.db.objects(protocol=parameters['protocol'],
+ groups='eval',
+ purposes='probe',
+ model_ids=[template_id]),
+ key=lambda x: (x.client_id, x.id))
+
+ template_probes[template_id] = [ p.id for p in objs ]
+
+ objs = sorted(self.db.objects(protocol=parameters['protocol'],
+ groups='eval',
+ purposes='probe'),
+ key=lambda x: (x.client_id, x.id))
+
+ self.objs = []
+ for obj in objs:
+ templates = [ template_id for template_id in template_ids
+ if obj.id in template_probes[template_id] ]
+ self.objs.append( (templates, obj) )
+
+ self.objs = sorted(self.objs, key=lambda x: (len(x[0]), x[0], x[1].client_id, x[1].id))
+
+ # Determine the range of indices that must be provided
+ self.start_index = force_start_index if force_start_index is not None else 0
+ self.end_index = force_end_index if force_end_index is not None else len(self.objs) - 1
+
+ self.objs = self.objs[self.start_index : self.end_index + 1]
+
+ self.next_index = self.start_index
+
+ return True
+
+
+ def done(self, last_data_index):
+ return last_data_index >= self.end_index
+
+
+ def next(self):
+ (template_ids, obj) = self.objs[self.next_index - self.start_index]
+
+
+ # Output: template_ids (only provide data when the template_ids change)
+ if self.outputs['template_ids'].isConnected() and \
+ self.outputs['template_ids'].last_written_data_index < self.next_index:
+
+ template_ids_end_index = get_value_end_index(self.objs, template_ids, 0,
+ self.next_index,
+ self.start_index,
+ self.end_index)
+
+ self.outputs['template_ids'].write(
+ {
+ 'text': [ str(x) for x in template_ids ]
+ },
+ template_ids_end_index
+ )
+
+
+ # Output: client_id (only provide data when the client_id change)
+ if self.outputs['client_id'].isConnected() and \
+ self.outputs['client_id'].last_written_data_index < self.next_index:
+
+ client_end_index = get_client_end_index(self.objs, obj.client_id,
+ self.next_index,
+ self.start_index,
+ self.end_index)
+
+ self.outputs['client_id'].write(
+ {
+ 'text': str(obj.client_id)
+ },
+ client_end_index
+ )
+
+
+ # Output: probe_id (provide data at each iteration)
+ if self.outputs['probe_id'].isConnected():
+ self.outputs['probe_id'].write(
+ {
+ 'value': np.uint64(obj.id)
+ },
+ self.next_index
+ )
+
+ # Output: file_id (provide data at each iteration)
+ if self.outputs['file_id'].isConnected():
+ self.outputs['file_id'].write(
+ {
+ 'value': np.uint64(obj.id)
+ },
+ self.next_index
+ )
+
+
+ # Output: image (provide data at each iteration)
+ if self.outputs['keystroke'].isConnected():
+ self.outputs['keystroke'].write(
+ keystroke_reader(obj.make_path(self.root_folder, '.txt')),
+ self.next_index
+ )
+
+
+ # Determine the next data index that must be provided
+ self.next_index = 1 + min([ x.last_written_data_index for x in self.outputs
+ if x.isConnected() ]
+ )
+
+ return True
+
+
+#----------------------------------------------------------
+
+
+def setup_tests():
+ # Install a mock load function for the keystrokes
+ def mock_keystroke_reader(filename):
+ return {}
+
+ global keystroke_reader
+ keystroke_reader = mock_keystroke_reader
+
+
+#----------------------------------------------------------
+
+
+# Test the behavior of the views (on fake data)
+if __name__ == '__main__':
+
+ setup_tests()
+
+ from beat.backend.python.database import DatabaseTester
+
+ DatabaseTester('Templates', Templates,
+ [
+ 'client_id',
+ 'template_id',
+ 'file_id',
+ 'keystroke',
+ ],
+ dict(
+ protocol = 'A',
+ )
+ )
+
+ DatabaseTester('Probes', Probes,
+ [
+ 'template_ids',
+ 'client_id',
+ 'probe_id',
+ 'file_id',
+ 'keystroke',
+ ],
+ dict(
+ protocol = 'A',
+ ),
+ irregular_outputs = [
+ 'client_id',
+ ]
+ )
diff --git a/advanced/databases/kboc16/3.rst b/advanced/databases/kboc16/3.rst
new file mode 100644
index 0000000..f7260d3
--- /dev/null
+++ b/advanced/databases/kboc16/3.rst
@@ -0,0 +1,80 @@
+.. Copyright (c) 2017 Idiap Research Institute, http://www.idiap.ch/ ..
+.. Contact: beat.support@idiap.ch ..
+.. ..
+.. This file is part of the beat.examples module of the BEAT platform. ..
+.. ..
+.. Commercial License Usage ..
+.. Licensees holding valid commercial BEAT licenses may use this file in ..
+.. accordance with the terms contained in a written agreement between you ..
+.. and Idiap. For further information contact tto@idiap.ch ..
+.. ..
+.. Alternatively, this file may be used under the terms of the GNU Affero ..
+.. Public License version 3 as published by the Free Software and appearing ..
+.. in the file LICENSE.AGPL included in the packaging of this file. ..
+.. The BEAT platform is distributed in the hope that it will be useful, but ..
+.. WITHOUT ANY WARRANTY; without even the implied warranty of MERCHANTABILITY ..
+.. or FITNESS FOR A PARTICULAR PURPOSE. ..
+.. ..
+.. You should have received a copy of the GNU Affero Public License along ..
+.. with the BEAT platform. If not, see http://www.gnu.org/licenses/. ..
+
+
+The KBOC16 Database
+-------------------
+
+Changelog
+=========
+
+* **Version 3**, 30/Oct/2017:
+
+ - Port to beat.backend.python v1.4.2
+
+* **Version 2**, 4/Apr/2016:
+
+ - Added protocol ``A``
+
+* **Version 1**:
+
+ - Initial release
+
+
+Description
+===========
+
+The KBOC16 database is part of the `KBOC competition
+<https://sites.google.com/site/btas16kboc/database>`_, an official competition
+of The IEEE Eighth International Conference on Biometrics: Theory,
+Applications, and Systems (BTAS 2016) organized by `ATVS Biometric Research
+Group <http://atvs.ii.uam.es>`_.
+
+
+The database consists of keystroke sequences from 300 subjects acquired in four
+different sessions (5 samples per session including genuine and impostors)
+distributed in a four month time span. Thus, three different levels of
+temporal variability are taken into account: (1) within the same session (the
+samples are not acquired consecutively), (2) within weeks (between two
+consecutive sessions), and (3) within months (between non-consecutive
+sessions).
+
+Each session comprises 5 case-insensitive repetitions of the subject’s name and
+surname typed in a natural and continuous manner (case insensitive). Mistakes
+(and backspace) are not permitted. The time (in milliseconds) elapsed between
+consecutive key events (press and release) is provided as keystroke dynamics
+sequence.
+
+There are two types of sequences: 1) Genuine sequences: typed by the owner of
+the password and 2) Impostor sequences: typed by other users (different to the
+owner) who try to spoof the system. The number of genuine and impostor samples
+per user varies (this information remains sequestered).
+
+For further information on the reproducible keystroke experiments and
+competition results we refer the reader to (the following articles are publicly
+available in the publications section of the `ATVS group webpage
+<http://atvs.ii.uam.es/listpublications.do>`_)
+
+.. [BTAS15] A. Morales, M. Falanga, J. Fierrez, C. Sansone and J. Ortega-Garcia, ''Keystroke Dynamics Recognition based on Personal Data: A Comparative Experimental Evaluation Implementing Reproducible Research'', in Proc. of the IEEE Seventh International Conference on Biometrics: Theory, Applications and Systems, Arlington, Virginia, USA, September 2015.
+
+.. [BTAS16] To appear.
+
+Please remember to reference [BTAS15]_ and [BTAS16]_ on any work made public,
+whatever the form, based directly or indirectly on any part of the KBOC16 DB.
--
GitLab