BEAT - pkorshunov/lr-score-fusion-project/1

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 4

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: asv_real

Endpoint Name	Data Format	Nature
asv_real_scores	elie_khoury/string_probe_scores/1	Input
asv_probe_id	system/text/1	Input
fused_scores	pkorshunov/fusion_scores/1	Output

Group: pad

Endpoint Name	Data Format	Nature
pad_scores_class	system/text/1	Input
pad_file_id	system/text/1	Input
pad_scores	system/float/1	Input

Group: asv_attack

Endpoint Name	Data Format	Nature
asv_attack_scores	elie_khoury/string_probe_scores/1	Input
asv_attack_id	system/text/1	Input

Unnamed group

Endpoint Name	Data Format	Nature
classifier	tutorial/linear_machine/1	Input

import bob.learn.linear
import numpy

def linear_machine_from_data(data):
    """Extracts a bob.learn.linear.Machine from a BEAT Data object"""

machine = bob.learn.linear.Machine(data.weights)
    machine.biases = data.biases
    machine.input_subtract = data.input_subtract
    machine.input_divide = data.input_divide
    return machine

class Algorithm:

def __init__(self):
        self.machine            = None
        self.toevaluate_real= []
        self.toevaluate_zimp = []
        self.toevaluate_attack = None
        self.pad_real_id_matched = None
        self.pad_attack_id_matched = None

def process(self, inputs, outputs):

# retrieve the linear machine once
        if self.machine is None:
            inputs['classifier'].next()
            self.machine = linear_machine_from_data(inputs['classifier'].data)

# accumulates the scores from PAD
        if self.pad_real_id_matched is None and self.pad_attack_id_matched is None:
            self.pad_real_id_matched = {}
            self.pad_attack_id_matched = {}
            while inputs['pad_scores'].hasMoreData():
                inputs['pad_scores'].next()
                inputs['pad_scores_class'].next()
                inputs['pad_file_id'].next()
                score_pad = inputs['pad_scores'].data.value
                label_pad = inputs['pad_scores_class'].data.text
                file_id = inputs['pad_file_id'].data.text
                if label_pad == 'real':
                    self.pad_real_id_matched[file_id] = score_pad  # add real score matching file id
                else:
                    self.pad_attack_id_matched[file_id] = score_pad  # add attack score matching file id
                
        if self.toevaluate_attack is None:
            self.toevaluate_attack = []
            while inputs['asv_attack_id'].hasMoreData():
                inputs['asv_attack_id'].next()
                inputs['asv_attack_scores'].next()
                asv_attack_id = inputs['asv_attack_id'].data.text
                asv_attack_scores = inputs['asv_attack_scores'].data
                corresponding_pad_attack_score = self.pad_attack_id_matched[asv_attack_id]
                for score in asv_attack_scores.scores:
                    if score.template_identity == asv_attack_scores.client_identity:
                        self.toevaluate_attack.append((score.score, corresponding_pad_attack_score))
                    
        # get correct scores from ASV real
        asv_probe_id = inputs['asv_probe_id'].data.text
        corresponding_pad_real_score = self.pad_real_id_matched[asv_probe_id]
#        corresponding_pad_real_score = 0.1
        asv_real_scores = inputs['asv_real_scores'].data
        for score in asv_real_scores.scores:
            # if this is real score
            if score.template_identity == asv_real_scores.client_identity:
                self.toevaluate_real.append((score.score, corresponding_pad_real_score))
            # if this is zero-impostor score
            else: 
                self.toevaluate_zimp.append((score.score, corresponding_pad_real_score))

if not(inputs.hasMoreData()):
            
            real_scores = []
            for score_pair in self.toevaluate_real:
                real_scores.extend(self.machine(score_pair))
            zimp_scores = []
            for score_pair in self.toevaluate_zimp:
                zimp_scores.extend(self.machine(score_pair))
            attack_scores = []
            for score_pair in self.toevaluate_attack:
                attack_scores.extend(self.machine(score_pair))
                
            # output the projected scores
            outputs['fused_scores'].write({
                    'real_scores': real_scores,
                    'zimp_scores': zimp_scores,
                    'attack_scores': attack_scores
                })

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

Project input features on a given linear machine (e.g., logistic regression)

Experiments

Attestation:

Privacy:

Status:

			Updated	Name	Databases/Protocols	Analyzers
				pkorshunov/pkorshunov/isv-asv-pad-fusion-complete/1/asv_isv-pad_lbp_hist_ratios_lr-fusion_lr-pa_aligned	avspoof/2@physicalaccess_verify_train,avspoof/2@physicalaccess_verification,avspoof/2@physicalaccess_verification_spoof,avspoof/2@physicalaccess_verify_train_spoof,avspoof/2@physicalaccess_antispoofing	pkorshunov/spoof-score-fusion-roc_hist/1
				pkorshunov/pkorshunov/isv-asv-pad-fusion-complete/1/asv_isv-pad_gmm-fusion_lr-pa	avspoof/2@physicalaccess_verify_train,avspoof/2@physicalaccess_verification,avspoof/2@physicalaccess_verification_spoof,avspoof/2@physicalaccess_verify_train_spoof,avspoof/2@physicalaccess_antispoofing	pkorshunov/spoof-score-fusion-roc_hist/1

Scientific Python 2.7 (0.1.0) 24

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 pkorshunov lr-score-fusion-project 1