Fusion in Multibiometric Identification Systems: What about the Missing Data? View Full Text


Ontology type: schema:Chapter      Open Access: True


Chapter Info

DATE

2009

AUTHORS

Karthik Nandakumar , Anil K. Jain , Arun Ross

ABSTRACT

Many large-scale biometric systems operate in the identification mode and include multimodal information. While biometric fusion is a well-studied problem, most of the fusion schemes have been implicitly designed for the verification scenario and cannot account for missing data (missing modalities or incomplete score lists) that is commonly encountered in multibiometric identification systems. In this paper, we show that likelihood ratio-based score fusion, which was originally designed for verification systems, can be extended for fusion in the identification scenario under certain assumptions. We further propose a Bayesian approach for consolidating ranks and a hybrid scheme that utilizes both ranks and scores to perform fusion in identification systems. We also demonstrate that the proposed fusion rules can handle missing information without any ad-hoc modifications. We observe that the recognition performance of the simplest rank level fusion scheme, namely, the highest rank method, is comparable to the performance of complex fusion strategies, especially when the goal is not to obtain the best rank-1 accuracy but to just retrieve the top few matches. More... »

PAGES

743-752

Identifiers

URI

http://scigraph.springernature.com/pub.10.1007/978-3-642-01793-3_76

DOI

http://dx.doi.org/10.1007/978-3-642-01793-3_76

DIMENSIONS

https://app.dimensions.ai/details/publication/pub.1014371936


Indexing Status Check whether this publication has been indexed by Scopus and Web Of Science using the SN Indexing Status Tool
Incoming Citations Browse incoming citations for this publication using opencitations.net

JSON-LD is the canonical representation for SciGraph data.

TIP: You can open this SciGraph record using an external JSON-LD service: JSON-LD Playground Google SDTT

[
  {
    "@context": "https://springernature.github.io/scigraph/jsonld/sgcontext.json", 
    "about": [
      {
        "id": "http://purl.org/au-research/vocabulary/anzsrc-for/2008/08", 
        "inDefinedTermSet": "http://purl.org/au-research/vocabulary/anzsrc-for/2008/", 
        "name": "Information and Computing Sciences", 
        "type": "DefinedTerm"
      }, 
      {
        "id": "http://purl.org/au-research/vocabulary/anzsrc-for/2008/0801", 
        "inDefinedTermSet": "http://purl.org/au-research/vocabulary/anzsrc-for/2008/", 
        "name": "Artificial Intelligence and Image Processing", 
        "type": "DefinedTerm"
      }
    ], 
    "author": [
      {
        "affiliation": {
          "alternateName": "Institute for Infocomm Research, A*STAR, Fusionopolis, Singapore", 
          "id": "http://www.grid.ac/institutes/grid.418705.f", 
          "name": [
            "Institute for Infocomm Research, A*STAR, Fusionopolis, Singapore"
          ], 
          "type": "Organization"
        }, 
        "familyName": "Nandakumar", 
        "givenName": "Karthik", 
        "id": "sg:person.013262445601.05", 
        "sameAs": [
          "https://app.dimensions.ai/discover/publication?and_facet_researcher=ur.013262445601.05"
        ], 
        "type": "Person"
      }, 
      {
        "affiliation": {
          "alternateName": "Michigan State University, East Lansing, MI, USA", 
          "id": "http://www.grid.ac/institutes/grid.17088.36", 
          "name": [
            "Michigan State University, East Lansing, MI, USA"
          ], 
          "type": "Organization"
        }, 
        "familyName": "Jain", 
        "givenName": "Anil K.", 
        "id": "sg:person.01031110710.30", 
        "sameAs": [
          "https://app.dimensions.ai/discover/publication?and_facet_researcher=ur.01031110710.30"
        ], 
        "type": "Person"
      }, 
      {
        "affiliation": {
          "alternateName": "West Virginia University, Morgantown, WV, USA", 
          "id": "http://www.grid.ac/institutes/grid.268154.c", 
          "name": [
            "West Virginia University, Morgantown, WV, USA"
          ], 
          "type": "Organization"
        }, 
        "familyName": "Ross", 
        "givenName": "Arun", 
        "id": "sg:person.07467067501.92", 
        "sameAs": [
          "https://app.dimensions.ai/discover/publication?and_facet_researcher=ur.07467067501.92"
        ], 
        "type": "Person"
      }
    ], 
    "datePublished": "2009", 
    "datePublishedReg": "2009-01-01", 
    "description": "Many large-scale biometric systems operate in the identification mode and include multimodal information. While biometric fusion is a well-studied problem, most of the fusion schemes have been implicitly designed for the verification scenario and cannot account for missing data (missing modalities or incomplete score lists) that is commonly encountered in multibiometric identification systems. In this paper, we show that likelihood ratio-based score fusion, which was originally designed for verification systems, can be extended for fusion in the identification scenario under certain assumptions. We further propose a Bayesian approach for consolidating ranks and a hybrid scheme that utilizes both ranks and scores to perform fusion in identification systems. We also demonstrate that the proposed fusion rules can handle missing information without any ad-hoc modifications. We observe that the recognition performance of the simplest rank level fusion scheme, namely, the highest rank method, is comparable to the performance of complex fusion strategies, especially when the goal is not to obtain the best rank-1 accuracy but to just retrieve the top few matches.", 
    "editor": [
      {
        "familyName": "Tistarelli", 
        "givenName": "Massimo", 
        "type": "Person"
      }, 
      {
        "familyName": "Nixon", 
        "givenName": "Mark S.", 
        "type": "Person"
      }
    ], 
    "genre": "chapter", 
    "id": "sg:pub.10.1007/978-3-642-01793-3_76", 
    "isAccessibleForFree": true, 
    "isPartOf": {
      "isbn": [
        "978-3-642-01792-6", 
        "978-3-642-01793-3"
      ], 
      "name": "Advances in Biometrics", 
      "type": "Book"
    }, 
    "keywords": [
      "identification system", 
      "fusion scheme", 
      "large-scale biometric systems", 
      "level fusion scheme", 
      "rank-1 accuracy", 
      "ad-hoc modifications", 
      "highest rank method", 
      "biometric systems", 
      "biometric fusion", 
      "score fusion", 
      "verification scenarios", 
      "verification system", 
      "fusion strategy", 
      "identification mode", 
      "multimodal information", 
      "recognition performance", 
      "fusion rule", 
      "Bayesian approach", 
      "identification scenario", 
      "certain assumptions", 
      "rank method", 
      "Missing Data", 
      "hybrid scheme", 
      "scheme", 
      "scenarios", 
      "fusion", 
      "information", 
      "system", 
      "performance", 
      "rank", 
      "accuracy", 
      "problem", 
      "rules", 
      "assumption", 
      "data", 
      "match", 
      "goal", 
      "approach", 
      "method", 
      "mode", 
      "strategies", 
      "modification", 
      "scores", 
      "paper"
    ], 
    "name": "Fusion in Multibiometric Identification Systems: What about the Missing Data?", 
    "pagination": "743-752", 
    "productId": [
      {
        "name": "dimensions_id", 
        "type": "PropertyValue", 
        "value": [
          "pub.1014371936"
        ]
      }, 
      {
        "name": "doi", 
        "type": "PropertyValue", 
        "value": [
          "10.1007/978-3-642-01793-3_76"
        ]
      }
    ], 
    "publisher": {
      "name": "Springer Nature", 
      "type": "Organisation"
    }, 
    "sameAs": [
      "https://doi.org/10.1007/978-3-642-01793-3_76", 
      "https://app.dimensions.ai/details/publication/pub.1014371936"
    ], 
    "sdDataset": "chapters", 
    "sdDatePublished": "2022-11-24T21:19", 
    "sdLicense": "https://scigraph.springernature.com/explorer/license/", 
    "sdPublisher": {
      "name": "Springer Nature - SN SciGraph project", 
      "type": "Organization"
    }, 
    "sdSource": "s3://com-springernature-scigraph/baseset/20221124/entities/gbq_results/chapter/chapter_63.jsonl", 
    "type": "Chapter", 
    "url": "https://doi.org/10.1007/978-3-642-01793-3_76"
  }
]
 

Download the RDF metadata as:  json-ld nt turtle xml License info

HOW TO GET THIS DATA PROGRAMMATICALLY:

JSON-LD is a popular format for linked data which is fully compatible with JSON.

curl -H 'Accept: application/ld+json' 'https://scigraph.springernature.com/pub.10.1007/978-3-642-01793-3_76'

N-Triples is a line-based linked data format ideal for batch operations.

curl -H 'Accept: application/n-triples' 'https://scigraph.springernature.com/pub.10.1007/978-3-642-01793-3_76'

Turtle is a human-readable linked data format.

curl -H 'Accept: text/turtle' 'https://scigraph.springernature.com/pub.10.1007/978-3-642-01793-3_76'

RDF/XML is a standard XML format for linked data.

curl -H 'Accept: application/rdf+xml' 'https://scigraph.springernature.com/pub.10.1007/978-3-642-01793-3_76'


 

This table displays all metadata directly associated to this object as RDF triples.

128 TRIPLES      22 PREDICATES      69 URIs      62 LITERALS      7 BLANK NODES

Subject Predicate Object
1 sg:pub.10.1007/978-3-642-01793-3_76 schema:about anzsrc-for:08
2 anzsrc-for:0801
3 schema:author N89f10007c3504d578b11c0ed87a470b8
4 schema:datePublished 2009
5 schema:datePublishedReg 2009-01-01
6 schema:description Many large-scale biometric systems operate in the identification mode and include multimodal information. While biometric fusion is a well-studied problem, most of the fusion schemes have been implicitly designed for the verification scenario and cannot account for missing data (missing modalities or incomplete score lists) that is commonly encountered in multibiometric identification systems. In this paper, we show that likelihood ratio-based score fusion, which was originally designed for verification systems, can be extended for fusion in the identification scenario under certain assumptions. We further propose a Bayesian approach for consolidating ranks and a hybrid scheme that utilizes both ranks and scores to perform fusion in identification systems. We also demonstrate that the proposed fusion rules can handle missing information without any ad-hoc modifications. We observe that the recognition performance of the simplest rank level fusion scheme, namely, the highest rank method, is comparable to the performance of complex fusion strategies, especially when the goal is not to obtain the best rank-1 accuracy but to just retrieve the top few matches.
7 schema:editor N366bd06f64d04d75808dc764dccbd55a
8 schema:genre chapter
9 schema:isAccessibleForFree true
10 schema:isPartOf N95eb278a0bb84241958832649bae9e71
11 schema:keywords Bayesian approach
12 Missing Data
13 accuracy
14 ad-hoc modifications
15 approach
16 assumption
17 biometric fusion
18 biometric systems
19 certain assumptions
20 data
21 fusion
22 fusion rule
23 fusion scheme
24 fusion strategy
25 goal
26 highest rank method
27 hybrid scheme
28 identification mode
29 identification scenario
30 identification system
31 information
32 large-scale biometric systems
33 level fusion scheme
34 match
35 method
36 mode
37 modification
38 multimodal information
39 paper
40 performance
41 problem
42 rank
43 rank method
44 rank-1 accuracy
45 recognition performance
46 rules
47 scenarios
48 scheme
49 score fusion
50 scores
51 strategies
52 system
53 verification scenarios
54 verification system
55 schema:name Fusion in Multibiometric Identification Systems: What about the Missing Data?
56 schema:pagination 743-752
57 schema:productId Nb0468c6109a647be92feaf726b8b6f61
58 Nd876e7d843464475bae138004a8ee5d2
59 schema:publisher N5d5bd019544b4fe1a14245410ecdc772
60 schema:sameAs https://app.dimensions.ai/details/publication/pub.1014371936
61 https://doi.org/10.1007/978-3-642-01793-3_76
62 schema:sdDatePublished 2022-11-24T21:19
63 schema:sdLicense https://scigraph.springernature.com/explorer/license/
64 schema:sdPublisher Nd106b281c4044c95a843641fe340b707
65 schema:url https://doi.org/10.1007/978-3-642-01793-3_76
66 sgo:license sg:explorer/license/
67 sgo:sdDataset chapters
68 rdf:type schema:Chapter
69 N1b39af5f8ba44838b6c285ec4eb447dd rdf:first sg:person.01031110710.30
70 rdf:rest Nc8785c7e1e5d47eb8926da839c5d7d2a
71 N366bd06f64d04d75808dc764dccbd55a rdf:first Na5482855f15f45abb1c167f708b07441
72 rdf:rest N714a537562614f44b995c2a4f2117ad7
73 N5d5bd019544b4fe1a14245410ecdc772 schema:name Springer Nature
74 rdf:type schema:Organisation
75 N714a537562614f44b995c2a4f2117ad7 rdf:first Nab05e084c8a743339a9a85aea55836fc
76 rdf:rest rdf:nil
77 N89f10007c3504d578b11c0ed87a470b8 rdf:first sg:person.013262445601.05
78 rdf:rest N1b39af5f8ba44838b6c285ec4eb447dd
79 N95eb278a0bb84241958832649bae9e71 schema:isbn 978-3-642-01792-6
80 978-3-642-01793-3
81 schema:name Advances in Biometrics
82 rdf:type schema:Book
83 Na5482855f15f45abb1c167f708b07441 schema:familyName Tistarelli
84 schema:givenName Massimo
85 rdf:type schema:Person
86 Nab05e084c8a743339a9a85aea55836fc schema:familyName Nixon
87 schema:givenName Mark S.
88 rdf:type schema:Person
89 Nb0468c6109a647be92feaf726b8b6f61 schema:name dimensions_id
90 schema:value pub.1014371936
91 rdf:type schema:PropertyValue
92 Nc8785c7e1e5d47eb8926da839c5d7d2a rdf:first sg:person.07467067501.92
93 rdf:rest rdf:nil
94 Nd106b281c4044c95a843641fe340b707 schema:name Springer Nature - SN SciGraph project
95 rdf:type schema:Organization
96 Nd876e7d843464475bae138004a8ee5d2 schema:name doi
97 schema:value 10.1007/978-3-642-01793-3_76
98 rdf:type schema:PropertyValue
99 anzsrc-for:08 schema:inDefinedTermSet anzsrc-for:
100 schema:name Information and Computing Sciences
101 rdf:type schema:DefinedTerm
102 anzsrc-for:0801 schema:inDefinedTermSet anzsrc-for:
103 schema:name Artificial Intelligence and Image Processing
104 rdf:type schema:DefinedTerm
105 sg:person.01031110710.30 schema:affiliation grid-institutes:grid.17088.36
106 schema:familyName Jain
107 schema:givenName Anil K.
108 schema:sameAs https://app.dimensions.ai/discover/publication?and_facet_researcher=ur.01031110710.30
109 rdf:type schema:Person
110 sg:person.013262445601.05 schema:affiliation grid-institutes:grid.418705.f
111 schema:familyName Nandakumar
112 schema:givenName Karthik
113 schema:sameAs https://app.dimensions.ai/discover/publication?and_facet_researcher=ur.013262445601.05
114 rdf:type schema:Person
115 sg:person.07467067501.92 schema:affiliation grid-institutes:grid.268154.c
116 schema:familyName Ross
117 schema:givenName Arun
118 schema:sameAs https://app.dimensions.ai/discover/publication?and_facet_researcher=ur.07467067501.92
119 rdf:type schema:Person
120 grid-institutes:grid.17088.36 schema:alternateName Michigan State University, East Lansing, MI, USA
121 schema:name Michigan State University, East Lansing, MI, USA
122 rdf:type schema:Organization
123 grid-institutes:grid.268154.c schema:alternateName West Virginia University, Morgantown, WV, USA
124 schema:name West Virginia University, Morgantown, WV, USA
125 rdf:type schema:Organization
126 grid-institutes:grid.418705.f schema:alternateName Institute for Infocomm Research, A*STAR, Fusionopolis, Singapore
127 schema:name Institute for Infocomm Research, A*STAR, Fusionopolis, Singapore
128 rdf:type schema:Organization
 




Preview window. Press ESC to close (or click here)


...