BEAT - siebenkopf/SortScores/6

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

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: probes

Endpoint Name	Data Format	Nature
comparison_ids	system/array_1d_uint64/1	Input
probe_client_id	system/uint64/1	Input
probe_id	system/uint64/1	Input
scores	system/array_1d_floats/1	Input
positives	system/array_1d_floats/1	Output
negatives	system/array_1d_floats/1	Output

Group: models

Endpoint Name	Data Format	Nature
model_id	system/uint64/1	Input
model_client_id	system/uint64/1	Input

import bob
import numpy

class Algorithm:

def __init__(self):
    self.positives = []
    self.negatives = []
    # dictionary from model ids to client ids
    self.id_dict = None
    
  def process(self, inputs, outputs):
    # retrieve all the models once
    if self.id_dict is None:
      self.id_dict = {}
      group = inputs.groupOf('model_id')
      while group.hasMoreData(): 
        group.next()
        self.id_dict[group['model_id'].data.value] = group['model_client_id'].data.value
        
    # process scores for one probe
    comparison_ids = inputs['comparison_ids'].data.value
    scores = inputs['scores'].data.value
    assert len(scores) == len(comparison_ids)
    
    probe_client_id = inputs['probe_client_id'].data.value
    for i, comparison_id in enumerate(comparison_ids):
      # check if clients of model and probe are identical
      if self.id_dict[comparison_id] == probe_client_id:
        self.positives.append(scores[i])
      else:
        self.negatives.append(scores[i])
        
    if not inputs.groupOf('probe_id').hasMoreData():
      # finally, write all scores when finished
      outputs['positives'].write(
        {
          'value': self.positives
        }
      )
      outputs['negatives'].write(
        {
          'value': 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

This algorithm sorts the scores coming from the comparison of templates and probes according to the ground truth information from the database. If a score comes from a comparsion of a template and a probe from the same identity, it is added to the positives. When the identities of template and probe differ, it is a negative score.

Note

In most of the cases, there are many more negative than positive scores.

Experiments

Attestation:

Privacy:

Status:

Name	Databases/Protocols	Analyzers
siebenkopf/siebenkopf/FaceRec-WithOut-Training/2/XM2VTS-PhaseDiff	xm2vts/1@darkened-lp1	siebenkopf/ROC/15,siebenkopf/EER_HTER/8
siebenkopf/siebenkopf/FaceRec-WithOut-Training/2/XM2VTS-ScalarProduct	xm2vts/1@darkened-lp1	siebenkopf/ROC/15,siebenkopf/EER_HTER/8
siebenkopf/siebenkopf/FaceRec-WithOut-Training/2/XM2VTS-Canberra	xm2vts/1@darkened-lp1	siebenkopf/ROC/15,siebenkopf/EER_HTER/8
siebenkopf/siebenkopf/FaceRec-WithOut-Training/2/Banca_P-ScalarProduct	banca/1@P	siebenkopf/ROC/15,siebenkopf/EER_HTER/8
siebenkopf/siebenkopf/FaceRec-WithOut-Training/2/Banca_P-Canberra	banca/1@P	siebenkopf/ROC/14,siebenkopf/EER_HTER/8
siebenkopf/siebenkopf/FaceRec-WithOut-Training/2/Banca_P-PhaseDiff	banca/1@P	siebenkopf/ROC/14,siebenkopf/EER_HTER/8

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 siebenkopf SortScores 6

Endpoint Groups 2

Group: probes

Group: models

Experiments

algorithms

siebenkopf

SortScores

6