BEAT - anjos/livdet

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 an analyzer. It can only be used on analysis blocks.

Endpoint Groups 1

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
score	system/float/1	Input
class	system/boolean/1	Input

Results 6

Analyzers may produce any number of results. Once experiments using this analyzer are done, you may display the results or filter experiments using criteria based on them.

Name	Type
scores_distribution	plot/bar/1
roc	plot/isoroc/1
eer	float32
number_of_positives	int32
threshold	float32
number_of_negatives	int32

import bob
import numpy

class Algorithm:

def __init__(self):
        self.positives = []
        self.negatives = []
        self.n_bins = 20

def process(self, inputs, output):

# accumulate the scores
        if inputs['class'].data.value: #spoofing
            self.negatives.append(inputs['score'].data.value)
        else:
            self.positives.append(inputs['score'].data.value)
                
        # once all values are received, evaluate the scores
        if not(inputs.hasMoreData()):
            eer_threshold = bob.measure.eer_threshold(self.negatives, self.positives)
            far, frr      = bob.measure.farfrr(self.negatives, self.positives, eer_threshold)
            roc_points    = bob.measure.roc(self.negatives, self.positives, 100)
            
            histo_pos, bin_pos = numpy.histogram(self.positives, self.n_bins)
            histo_neg, bin_neg = numpy.histogram(self.negatives, self.n_bins)

# writes the output back to the platform
            output.write({
                'eer': numpy.float32((far+frr) / 2.),
                'number_of_positives': numpy.int32(len(self.positives)),
                'number_of_negatives': numpy.int32(len(self.negatives)),
                'threshold': numpy.float32(eer_threshold),
                'scores_distribution': {
                    'data':
                        [
                            {
                                "label": "negative scores",
                                "x": bin_neg[:-1],
                                "y": histo_neg,
                            },
                            {
                                "label": "positive scores",
                                "x": bin_pos[:-1],
                                "y": histo_pos,
                            }
                        ]
                    },
                'roc': {
                    'data':
                        [
                            {
                                "label": "roc",
                                "false_positives": roc_points[0],
                                "false_negatives": roc_points[1],
                                "number_of_positives": numpy.uint64(len(self.positives)),
                                "number_of_negatives": numpy.uint64(len(self.negatives)),
                            }
                        ]
                    }
            })

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

An algorithm that implements simple metrics for the LivDet2013 Competition

Specifically, it returns:

eer: the equal error rate (EER) on the test set.
number_of_positives: the number of positive (genuine) trials on the test set
number_of_negatives: the number of negative (spoof) trials on the test set
threshold: the threshold at the equal error rate on the test set
roc: the receiver operating characteristic (ROC) curve on the test set according to the biometrics standard ISO/IEC 19795-1:2006(E)

This implementation relies on the 'measure' package from the Bob library.

Experiments

Attestation:

Privacy:

Status:

			Updated	Name	Databases/Protocols	Analyzers
				anjos/anjos/livdet-lda/1/livdet-2013-biometrika-test	livdet2013/1@Biometrika	anjos/livdet_analysis/1

Scientific Python 2.7 (0.0.4) 2

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 anjos livdet_analysis 1

Endpoint Groups 1

Group: main

Results 6

Experiments

algorithms

anjos

livdet_analysis

1