3D Model-Based Face Recognition in Video View Full Text


Ontology type: schema:Chapter      Open Access: True


Chapter Info

DATE

2007-01-01

AUTHORS

Unsang Park , Anil K. Jain

ABSTRACT

Face recognition in video has gained wide attention due to its role in designing surveillance systems. One of the main advantages of video over still frames is that evidence accumulation over multiple frames can provide better face recognition performance. However, surveillance videos are generally of low resolution containing faces mostly in non-frontal poses. Consequently, face recognition in video poses serious challenges to state-of-the-art face recognition systems. Use of 3D face models has been suggested as a way to compensate for low resolution, poor contrast and non-frontal pose. We propose to overcome the pose problem by automatically (i) reconstructing a 3D face model from multiple non-frontal frames in a video, (ii) generating a frontal view from the derived 3D model, and (iii) using a commercial 2D face recognition engine to recognize the synthesized frontal view. A factorization-based structure from motion algorithm is used for 3D face reconstruction. The proposed scheme has been tested on CMU’s Face In Action (FIA) video database with 221 subjects. Experimental results show a 40% improvement in matching performance as a result of using the 3D models. More... »

PAGES

1085-1094

Identifiers

URI

http://scigraph.springernature.com/pub.10.1007/978-3-540-74549-5_113

DOI

http://dx.doi.org/10.1007/978-3-540-74549-5_113

DIMENSIONS

https://app.dimensions.ai/details/publication/pub.1029149984


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": "Department of Computer Science and Engineering, Michigan State University, 3115 Engineering Building, East Lasing, MI 48824, USA", 
          "id": "http://www.grid.ac/institutes/grid.17088.36", 
          "name": [
            "Department of Computer Science and Engineering, Michigan State University, 3115 Engineering Building, East Lasing, MI 48824, USA"
          ], 
          "type": "Organization"
        }, 
        "familyName": "Park", 
        "givenName": "Unsang", 
        "id": "sg:person.014647177263.64", 
        "sameAs": [
          "https://app.dimensions.ai/discover/publication?and_facet_researcher=ur.014647177263.64"
        ], 
        "type": "Person"
      }, 
      {
        "affiliation": {
          "alternateName": "Department of Computer Science and Engineering, Michigan State University, 3115 Engineering Building, East Lasing, MI 48824, USA", 
          "id": "http://www.grid.ac/institutes/grid.17088.36", 
          "name": [
            "Department of Computer Science and Engineering, Michigan State University, 3115 Engineering Building, East Lasing, MI 48824, 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"
      }
    ], 
    "datePublished": "2007-01-01", 
    "datePublishedReg": "2007-01-01", 
    "description": "Face recognition in video has gained wide attention due to its role in designing surveillance systems. One of the main advantages of video over still frames is that evidence accumulation over multiple frames can provide better face recognition performance. However, surveillance videos are generally of low resolution containing faces mostly in non-frontal poses. Consequently, face recognition in video poses serious challenges to state-of-the-art face recognition systems. Use of 3D face models has been suggested as a way to compensate for low resolution, poor contrast and non-frontal pose. We propose to overcome the pose problem by automatically (i) reconstructing a 3D face model from multiple non-frontal frames in a video, (ii) generating a frontal view from the derived 3D model, and (iii) using a commercial 2D face recognition engine to recognize the synthesized frontal view. A factorization-based structure from motion algorithm is used for 3D face reconstruction. The proposed scheme has been tested on CMU\u2019s Face In Action (FIA) video database with 221 subjects. Experimental results show a 40% improvement in matching performance as a result of using the 3D models.", 
    "editor": [
      {
        "familyName": "Lee", 
        "givenName": "Seong-Whan", 
        "type": "Person"
      }, 
      {
        "familyName": "Li", 
        "givenName": "Stan Z.", 
        "type": "Person"
      }
    ], 
    "genre": "chapter", 
    "id": "sg:pub.10.1007/978-3-540-74549-5_113", 
    "isAccessibleForFree": true, 
    "isPartOf": {
      "isbn": [
        "978-3-540-74548-8", 
        "978-3-540-74549-5"
      ], 
      "name": "Advances in Biometrics", 
      "type": "Book"
    }, 
    "keywords": [
      "non-frontal poses", 
      "face recognition", 
      "face model", 
      "art face recognition systems", 
      "face recognition engine", 
      "factorization-based structure", 
      "face recognition system", 
      "better face recognition performance", 
      "face recognition performance", 
      "frontal view", 
      "low resolution", 
      "surveillance videos", 
      "video database", 
      "recognition engine", 
      "recognition system", 
      "face reconstruction", 
      "motion algorithm", 
      "multiple frames", 
      "recognition performance", 
      "video", 
      "poor contrast", 
      "pose problems", 
      "pose", 
      "surveillance system", 
      "experimental results", 
      "recognition", 
      "main advantage", 
      "wide attention", 
      "serious challenge", 
      "frame", 
      "algorithm", 
      "performance", 
      "system", 
      "engine", 
      "model", 
      "scheme", 
      "evidence accumulation", 
      "database", 
      "view", 
      "face", 
      "challenges", 
      "advantages", 
      "reconstruction", 
      "way", 
      "results", 
      "resolution", 
      "improvement", 
      "attention", 
      "use", 
      "state", 
      "structure", 
      "role", 
      "subjects", 
      "contrast", 
      "accumulation", 
      "problem"
    ], 
    "name": "3D Model-Based Face Recognition in Video", 
    "pagination": "1085-1094", 
    "productId": [
      {
        "name": "dimensions_id", 
        "type": "PropertyValue", 
        "value": [
          "pub.1029149984"
        ]
      }, 
      {
        "name": "doi", 
        "type": "PropertyValue", 
        "value": [
          "10.1007/978-3-540-74549-5_113"
        ]
      }
    ], 
    "publisher": {
      "name": "Springer Nature", 
      "type": "Organisation"
    }, 
    "sameAs": [
      "https://doi.org/10.1007/978-3-540-74549-5_113", 
      "https://app.dimensions.ai/details/publication/pub.1029149984"
    ], 
    "sdDataset": "chapters", 
    "sdDatePublished": "2022-12-01T06:50", 
    "sdLicense": "https://scigraph.springernature.com/explorer/license/", 
    "sdPublisher": {
      "name": "Springer Nature - SN SciGraph project", 
      "type": "Organization"
    }, 
    "sdSource": "s3://com-springernature-scigraph/baseset/20221201/entities/gbq_results/chapter/chapter_285.jsonl", 
    "type": "Chapter", 
    "url": "https://doi.org/10.1007/978-3-540-74549-5_113"
  }
]
 

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.10.1007/978-3-540-74549-5_113'

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

curl -H 'Accept: application/n-triples' 'https://scigraph.springernature.com/pub.10.1007/978-3-540-74549-5_113'

Turtle is a human-readable linked data format.

curl -H 'Accept: text/turtle' 'https://scigraph.springernature.com/pub.10.1007/978-3-540-74549-5_113'

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

curl -H 'Accept: application/rdf+xml' 'https://scigraph.springernature.com/pub.10.1007/978-3-540-74549-5_113'


 

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

127 TRIPLES      22 PREDICATES      80 URIs      73 LITERALS      7 BLANK NODES

Subject Predicate Object
1 sg:pub.10.1007/978-3-540-74549-5_113 schema:about anzsrc-for:08
2 anzsrc-for:0801
3 schema:author N5b3cc61964c6494480d2242768ce5ff1
4 schema:datePublished 2007-01-01
5 schema:datePublishedReg 2007-01-01
6 schema:description Face recognition in video has gained wide attention due to its role in designing surveillance systems. One of the main advantages of video over still frames is that evidence accumulation over multiple frames can provide better face recognition performance. However, surveillance videos are generally of low resolution containing faces mostly in non-frontal poses. Consequently, face recognition in video poses serious challenges to state-of-the-art face recognition systems. Use of 3D face models has been suggested as a way to compensate for low resolution, poor contrast and non-frontal pose. We propose to overcome the pose problem by automatically (i) reconstructing a 3D face model from multiple non-frontal frames in a video, (ii) generating a frontal view from the derived 3D model, and (iii) using a commercial 2D face recognition engine to recognize the synthesized frontal view. A factorization-based structure from motion algorithm is used for 3D face reconstruction. The proposed scheme has been tested on CMU’s Face In Action (FIA) video database with 221 subjects. Experimental results show a 40% improvement in matching performance as a result of using the 3D models.
7 schema:editor N20b2b9c100b7411390de070c5290543a
8 schema:genre chapter
9 schema:isAccessibleForFree true
10 schema:isPartOf N59c65e3171cc4d5a87607cabac9411b4
11 schema:keywords accumulation
12 advantages
13 algorithm
14 art face recognition systems
15 attention
16 better face recognition performance
17 challenges
18 contrast
19 database
20 engine
21 evidence accumulation
22 experimental results
23 face
24 face model
25 face recognition
26 face recognition engine
27 face recognition performance
28 face recognition system
29 face reconstruction
30 factorization-based structure
31 frame
32 frontal view
33 improvement
34 low resolution
35 main advantage
36 model
37 motion algorithm
38 multiple frames
39 non-frontal poses
40 performance
41 poor contrast
42 pose
43 pose problems
44 problem
45 recognition
46 recognition engine
47 recognition performance
48 recognition system
49 reconstruction
50 resolution
51 results
52 role
53 scheme
54 serious challenge
55 state
56 structure
57 subjects
58 surveillance system
59 surveillance videos
60 system
61 use
62 video
63 video database
64 view
65 way
66 wide attention
67 schema:name 3D Model-Based Face Recognition in Video
68 schema:pagination 1085-1094
69 schema:productId N2d006da84eba4d208aecd32f42a79e60
70 Necb861b34b064b069bbb2e45878cef07
71 schema:publisher N5771e8b6aaaa415f9e2f3df7e272815c
72 schema:sameAs https://app.dimensions.ai/details/publication/pub.1029149984
73 https://doi.org/10.1007/978-3-540-74549-5_113
74 schema:sdDatePublished 2022-12-01T06:50
75 schema:sdLicense https://scigraph.springernature.com/explorer/license/
76 schema:sdPublisher Ne95b9e05c5c842b3890f7e9838fbcc34
77 schema:url https://doi.org/10.1007/978-3-540-74549-5_113
78 sgo:license sg:explorer/license/
79 sgo:sdDataset chapters
80 rdf:type schema:Chapter
81 N0054e904dffb4c00a5ddf024f9b8be1f schema:familyName Li
82 schema:givenName Stan Z.
83 rdf:type schema:Person
84 N20b2b9c100b7411390de070c5290543a rdf:first N721e684d579849208baffbeaf42f4d9a
85 rdf:rest Ne51c4e06c62d4e8291c98afb688fc3a1
86 N2d006da84eba4d208aecd32f42a79e60 schema:name doi
87 schema:value 10.1007/978-3-540-74549-5_113
88 rdf:type schema:PropertyValue
89 N5771e8b6aaaa415f9e2f3df7e272815c schema:name Springer Nature
90 rdf:type schema:Organisation
91 N59c65e3171cc4d5a87607cabac9411b4 schema:isbn 978-3-540-74548-8
92 978-3-540-74549-5
93 schema:name Advances in Biometrics
94 rdf:type schema:Book
95 N5b3cc61964c6494480d2242768ce5ff1 rdf:first sg:person.014647177263.64
96 rdf:rest Naf73b5419cfb46139dba6f5bbc9a9206
97 N721e684d579849208baffbeaf42f4d9a schema:familyName Lee
98 schema:givenName Seong-Whan
99 rdf:type schema:Person
100 Naf73b5419cfb46139dba6f5bbc9a9206 rdf:first sg:person.01031110710.30
101 rdf:rest rdf:nil
102 Ne51c4e06c62d4e8291c98afb688fc3a1 rdf:first N0054e904dffb4c00a5ddf024f9b8be1f
103 rdf:rest rdf:nil
104 Ne95b9e05c5c842b3890f7e9838fbcc34 schema:name Springer Nature - SN SciGraph project
105 rdf:type schema:Organization
106 Necb861b34b064b069bbb2e45878cef07 schema:name dimensions_id
107 schema:value pub.1029149984
108 rdf:type schema:PropertyValue
109 anzsrc-for:08 schema:inDefinedTermSet anzsrc-for:
110 schema:name Information and Computing Sciences
111 rdf:type schema:DefinedTerm
112 anzsrc-for:0801 schema:inDefinedTermSet anzsrc-for:
113 schema:name Artificial Intelligence and Image Processing
114 rdf:type schema:DefinedTerm
115 sg:person.01031110710.30 schema:affiliation grid-institutes:grid.17088.36
116 schema:familyName Jain
117 schema:givenName Anil K.
118 schema:sameAs https://app.dimensions.ai/discover/publication?and_facet_researcher=ur.01031110710.30
119 rdf:type schema:Person
120 sg:person.014647177263.64 schema:affiliation grid-institutes:grid.17088.36
121 schema:familyName Park
122 schema:givenName Unsang
123 schema:sameAs https://app.dimensions.ai/discover/publication?and_facet_researcher=ur.014647177263.64
124 rdf:type schema:Person
125 grid-institutes:grid.17088.36 schema:alternateName Department of Computer Science and Engineering, Michigan State University, 3115 Engineering Building, East Lasing, MI 48824, USA
126 schema:name Department of Computer Science and Engineering, Michigan State University, 3115 Engineering Building, East Lasing, MI 48824, USA
127 rdf:type schema:Organization
 




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


...