BEAT - robertodaza/proof0/1

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 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
template_id	system/array_1d_text/1	Input
client_id	system/text/1	Input
scores	elie_khoury/string_probe_scores/1	Input

Results 3

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
client_id1	string
mean_eer	float32
std	float32

import bob
import numpy

class Algorithm:
    def __init__(self):       
        self.mean_eer = []  
        self.mi_user= []    
        self.positives = [None] * 63
        self.negatives = [None] * 63        
        self.flag=0
        
    def process(self, inputs, output):
        # initialize the score vector
      	if self.flag==0:
            self.flag=1
            for i in range(63):
                self.positives[i] = []
                self.negatives[i] = [] 
        # read the input data   
        data = inputs['scores'].data 
        client_id = inputs['client_id'].data.text
             
         
        user=inputs["client_id"].data.text        
        if user[0]=="G":            
            self.mi_user=numpy.int32(user[8:len(user)])           
        if user[0]=="I":            
            self.mi_user=numpy.int32(user[9:len(user)])    
        
        self.positives[self.mi_user-1].extend([k.score for k in data.scores if k.template_identity == data.client_identity])        
        self.negatives[self.mi_user-1].extend([k.score for k in data.scores if k.template_identity != data.client_identity])  
        
        if not(inputs.hasMoreData()):
            for iuser in range(63):
                positive_scores=self.positives[iuser]
                negative_scores=self.negatives[iuser]
                eer_threshold = bob.measure.eer_threshold(negative_scores, positive_scores)
                far, frr      = bob.measure.farfrr(negative_scores, positive_scores, eer_threshold)                
                self.mean_eer.append(numpy.float32((far+frr) / 2.))
            
        	# writes the output back to the platform
            
            output.write({
                'mean_eer': numpy.float32(numpy.average(self.mean_eer)), #average of all 63 EER
                'std': numpy.float32(numpy.std(self.mean_eer)), 
                'client_id1': user,    
            })
            
        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

Could not find any documentation for this object.

Experiments

Attestation:

Privacy:

Status:

			Updated	Name	Databases/Protocols	Analyzers
				robertodaza/aythamimm/atvs_keystroke_btas_benchmark/1/proof0	atvskeystroke/1@A	robertodaza/proof0/1

Scientific Python 2.7 (0.0.4) 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 robertodaza proof0 1

Endpoint Groups 1

Group: main

Results 3

Experiments

algorithms

robertodaza

proof0

1