BEAT - tutorial/isv

This algorithm is a legacy one. The API has changed since its implementation. New versions and forks will need to be updated.

This algorithm is splittable

Endpoint Groups 2

Algorithms have at least one input and one output. All algorithm endpoints are organized in groups. Groups are used by the platform to indicate which inputs and outputs are synchronized together. The first group is automatically synchronized with the channel defined by the block in which the algorithm is deployed.

Group: main

Endpoint Name	Data Format	Nature
statistics	tutorial/gmm_statistics/1	Input
template_id	system/uint64/1	Input
model	tutorial/isvmachine/1	Output

Unnamed group

Endpoint Name	Data Format	Nature
ubm	tutorial/gmm/1	Input
isvbase	tutorial/isvbase/1	Input

Parameters 1

Parameters allow users to change the configuration of an algorithm when scheduling an experiment

Name	Description	Type	Default	Range/Choices
isv-enroll-iterations		uint32	1

import bob
import numpy

def gmm_from_data(data):
    """Unmangles a bob.machine.GMMMachine from a BEAT Data object"""

dim_c, dim_d = data.means.shape
    gmm = bob.machine.GMMMachine(dim_c, dim_d)
    gmm.weights = data.weights
    gmm.means = data.means
    gmm.variances = data.variances
    gmm.variance_thresholds = data.variance_thresholds
    return gmm

def isvbase_from_data(data, ubm):
    """Unmangles a bob.machine.ISVBase from a BEAT Data object"""

dim_cd, dim_u = data.subspace_u.shape
    isvbase = bob.machine.ISVBase(ubm, dim_u)
    isvbase.u = data.subspace_u
    isvbase.d = data.subspace_d
    return isvbase

def stats_from_data(data):
    """Unmangles a bob.machine.GMMStats from a BEAT Data object"""

dim_c, dim_d = data.sum_px.shape
    stat = bob.machine.GMMStats(dim_c, dim_d)
    stat.t = long(data.t)
    stat.n = data.n
    stat.sum_px = data.sum_px
    stat.sum_pxx = data.sum_pxx
    return stat

class Algorithm:

def __init__(self):
        self.ubm      = None
        self.isvbase  = None
        self.statistics = []
        self.isv_enroll_iterations = 1

def setup(self, parameters):
        self.isv_enroll_iterations = parameters.get('isv-enroll-iterations', self.isv_enroll_iterations) 
        return True

def process(self, inputs, outputs):
        # retrieve the UBM once
        if self.ubm is None:
            inputs['ubm'].next()
            self.ubm = gmm_from_data(inputs['ubm'].data)

# retrieve the ISVBase once
        if self.isvbase is None:
            inputs['isvbase'].next()
            self.isvbase = isvbase_from_data(inputs['isvbase'].data, self.ubm)

# collect all the features for the current template
        self.statistics.append(stats_from_data(inputs["statistics"].data))

# adapts the UBM GMM for the template (when all the features have been collected)
        if inputs["template_id"].isDataUnitDone():
            model = bob.machine.ISVMachine(self.isvbase)

trainer = bob.trainer.ISVTrainer()
            trainer.enrol(model, self.statistics, int(self.isv_enroll_iterations))

# outputs data
            outputs["model"].write({
                'latent_z':             model.z,
            })

self.statistics = []

return True

xxxxxxxxxx
 
import bob
import numpy
​
​
​
def gmm_from_data(data):
    """Unmangles a bob.machine.GMMMachine from a BEAT Data object"""
​
    dim_c, dim_d = data.means.shape
    gmm = bob.machine.GMMMachine(dim_c, dim_d)
    gmm.weights = data.weights
    gmm.means = data.means
    gmm.variances = data.variances
    gmm.variance_thresholds = data.variance_thresholds
    return gmm
​
​
def isvbase_from_data(data, ubm):
    """Unmangles a bob.machine.ISVBase from a BEAT Data object"""
​
    dim_cd, dim_u = data.subspace_u.shape
    isvbase = bob.machine.ISVBase(ubm, dim_u)
    isvbase.u = data.subspace_u
    isvbase.d = data.subspace_d
    return isvbase
​
​
def stats_from_data(data):
    """Unmangles a bob.machine.GMMStats from a BEAT Data object"""
​
    dim_c, dim_d = data.sum_px.shape
    stat = bob.machine.GMMStats(dim_c, dim_d)
    stat.t = long(data.t)
    stat.n = data.n
    stat.sum_px = data.sum_px
    stat.sum_pxx = data.sum_pxx
    return stat
​
​
​
​
class Algorithm:
​
    def __init__(self):
        self.ubm      = None
        self.isvbase  = None
        self.statistics = []
        self.isv_enroll_iterations = 1
​
    def setup(self, parameters):
        self.isv_enroll_iterations = parameters.get('isv-enroll-iterations', self.isv_enroll_iterations) 
        return True
​
    def process(self, inputs, outputs):
        # retrieve the UBM once
        if self.ubm is None:
            inputs['ubm'].next()
            self.ubm = gmm_from_data(inputs['ubm'].data)
​
        # retrieve the ISVBase once
        if self.isvbase is None:
            inputs['isvbase'].next()
            self.isvbase = isvbase_from_data(inputs['isvbase'].data, self.ubm)
​
        # collect all the features for the current template
        self.statistics.append(stats_from_data(inputs["statistics"].data))
​
​
        # adapts the UBM GMM for the template (when all the features have been collected)
        if inputs["template_id"].isDataUnitDone():
            model = bob.machine.ISVMachine(self.isvbase)
​
            trainer = bob.trainer.ISVTrainer()
            trainer.enrol(model, self.statistics, int(self.isv_enroll_iterations))
​
            # outputs data
            outputs["model"].write({
                'latent_z':             model.z,
            })
​
            self.statistics = []
​
        return True
​

The code for this algorithm in Python
The ruler at 80 columns indicate suggested POSIX line breaks (for readability).
The editor will automatically enlarge to accomodate the entirety of your input
Use keyboard shortcuts for search/replace and faster editing. For example, use Ctrl-F (PC) or Cmd-F (Mac) to search through this box

Given a feature vector, a GMM and a U subspace, computes the Intersession Variability Modeling (ISV) client model. Basically, this algorithm computes the latent variable z_i excluding possible session factors (described by the latent variable x_i, j).

Specific details can be found in [McCool2013]:

This algorithm relies on the Bob library.

The inputs are:

statistics: A set of GMM Statistics of a client for enrollment.
ubm: A GMM corresponding to the Universal Background Model.
isvbase: The subspace_u and subspace_d for the session and the client offset respectivelly.
template_id: Client (class/subject) identifier as an unsigned 64 bits integer.

The output, model, is the latent variable z_i ( Eq. (31) in [McCool2013]) that corresponds to the client offset (with the session variations suppressed)

[McCool2013]

(1, 2) McCool, Christopher, et al. "Session variability modelling for face authentication." IET biometrics 2.3 (2013): 117-129.

Experiments

Attestation:

Privacy:

Status:

Name	Databases/Protocols	Analyzers
smarcel/tutorial/full_isv/2/mobio_male-gmm_100Gx10I-isv_50Ux10Ix4R-dct_12Bx8Ox45C-seed101	mobio/1@male	tutorial/eerhter_postperf_iso/1
tutorial/tutorial/full_isv/2/bancaMc_isv_DCT12x8_100G_U50	banca/1@Mc	tutorial/eerhter_postperf_iso/1
tutorial/tutorial/full_isv/2/xm2vtsLp1_isv_DCT12x8_100G_U50	xm2vts/1@lp1	tutorial/eerhter_postperf_iso/1
tutorial/tutorial/full_isv/2/mobioMale_isv_DCT12x8_100G_U50	mobio/1@male	tutorial/eerhter_postperf_iso/1
tutorial/tutorial/full_isv/2/bancaP_isv_DCT12x8_100G_U50	banca/1@P	tutorial/eerhter_postperf_iso/1
tutorial/tutorial/full_isv/2/atnt_isv_DCT12x8_100G_U50	atnt/1@idiap_test_eyepos	tutorial/eerhter_postperf_iso/1

This table shows the number of times this algorithm has been successfully run using the given environment. Note this does not provide sufficient information to evaluate if the algorithm will run when submitted to different conditions.

algorithms tutorial isv_enroll 3

Endpoint Groups 2

Group: main

Unnamed group

Parameters 1

Experiments

algorithms

tutorial

isv_enroll

3