Nighttime Face Recognition at Long Distance: Cross-Distance and Cross-Spectral Matching View Full Text


Ontology type: schema:Chapter     


Chapter Info

DATE

2013

AUTHORS

Hyunju Maeng , Shengcai Liao , Dongoh Kang , Seong-Whan Lee , Anil K. Jain

ABSTRACT

Automatic face recognition capability in surveillance systems is important for security applications. However, few studies have addressed the problem of outdoor face recognition at a long distance (over 100 meters) in both daytime and nighttime environments. In this paper, we first report on a system that we have designed to collect face image database at a long distance, called the Long Distance Heterogeneous Face Database (LDHF-DB) to advance research on this topic. The LDHF-DB contains face images collected in an outdoor environment at distances of 60 meters, 100 meters, and 150 meters, with both visible light (VIS) face images captured in daytime and near infrared (NIR) face images captured in nighttime. Given this database, we have conducted two types of cross-distance face matching (matching long-distance probe to 1-meter gallery) experiments: (i) intra-spectral (VIS to VIS) face matching, and (ii) cross-spectral (NIR to VIS) face matching. The proposed face recognition algorithm consists of following three major steps: (i) Gaussian filtering to remove high frequency noise, (ii) Scale Invariant Feature Transform (SIFT) in local image regions for feature representation, and (iii) a random subspace method to build discriminant subspaces for face recognition. Experimental results show that the proposed face recognition algorithm outperforms two commercial state-of-the-art face recognition SDKs (FaceVACS and PittPatt) for long distance face recognition in both daytime and nighttime operations. These results highlight the need for better data capture setup and robust face matching algorithms for cross spectral matching at distances greater than 100 meters. More... »

PAGES

708-721

Identifiers

URI

http://scigraph.springernature.com/pub.10.1007/978-3-642-37444-9_55

DOI

http://dx.doi.org/10.1007/978-3-642-37444-9_55

DIMENSIONS

https://app.dimensions.ai/details/publication/pub.1019593791


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": "Dept. of Brain and Cognitive Eng., Korea Univ., Seoul, Korea", 
          "id": "http://www.grid.ac/institutes/grid.222754.4", 
          "name": [
            "Dept. of Brain and Cognitive Eng., Korea Univ., Seoul, Korea"
          ], 
          "type": "Organization"
        }, 
        "familyName": "Maeng", 
        "givenName": "Hyunju", 
        "id": "sg:person.011352500542.64", 
        "sameAs": [
          "https://app.dimensions.ai/discover/publication?and_facet_researcher=ur.011352500542.64"
        ], 
        "type": "Person"
      }, 
      {
        "affiliation": {
          "alternateName": "Dept. of Comp. Sci. & Eng., Michigan State Univ., 48824, E. Lansing, MI, USA", 
          "id": "http://www.grid.ac/institutes/grid.17088.36", 
          "name": [
            "Dept. of Comp. Sci. & Eng., Michigan State Univ., 48824, E. Lansing, MI, USA"
          ], 
          "type": "Organization"
        }, 
        "familyName": "Liao", 
        "givenName": "Shengcai", 
        "id": "sg:person.07676740373.20", 
        "sameAs": [
          "https://app.dimensions.ai/discover/publication?and_facet_researcher=ur.07676740373.20"
        ], 
        "type": "Person"
      }, 
      {
        "affiliation": {
          "alternateName": "Dept. of Brain and Cognitive Eng., Korea Univ., Seoul, Korea", 
          "id": "http://www.grid.ac/institutes/grid.222754.4", 
          "name": [
            "Dept. of Brain and Cognitive Eng., Korea Univ., Seoul, Korea"
          ], 
          "type": "Organization"
        }, 
        "familyName": "Kang", 
        "givenName": "Dongoh", 
        "id": "sg:person.010053136712.99", 
        "sameAs": [
          "https://app.dimensions.ai/discover/publication?and_facet_researcher=ur.010053136712.99"
        ], 
        "type": "Person"
      }, 
      {
        "affiliation": {
          "alternateName": "Dept. of Brain and Cognitive Eng., Korea Univ., Seoul, Korea", 
          "id": "http://www.grid.ac/institutes/grid.222754.4", 
          "name": [
            "Dept. of Brain and Cognitive Eng., Korea Univ., Seoul, Korea"
          ], 
          "type": "Organization"
        }, 
        "familyName": "Lee", 
        "givenName": "Seong-Whan", 
        "id": "sg:person.01042611654.44", 
        "sameAs": [
          "https://app.dimensions.ai/discover/publication?and_facet_researcher=ur.01042611654.44"
        ], 
        "type": "Person"
      }, 
      {
        "affiliation": {
          "alternateName": "Dept. of Comp. Sci. & Eng., Michigan State Univ., 48824, E. Lansing, MI, USA", 
          "id": "http://www.grid.ac/institutes/grid.17088.36", 
          "name": [
            "Dept. of Brain and Cognitive Eng., Korea Univ., Seoul, Korea", 
            "Dept. of Comp. Sci. & Eng., Michigan State Univ., 48824, E. 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"
      }
    ], 
    "datePublished": "2013", 
    "datePublishedReg": "2013-01-01", 
    "description": "Automatic face recognition capability in surveillance systems is important for security applications. However, few studies have addressed the problem of outdoor face recognition at a long distance (over 100 meters) in both daytime and nighttime environments. In this paper, we first report on a system that we have designed to collect face image database at a long distance, called the Long Distance Heterogeneous Face Database (LDHF-DB) to advance research on this topic. The LDHF-DB contains face images collected in an outdoor environment at distances of 60 meters, 100 meters, and 150 meters, with both visible light (VIS) face images captured in daytime and near infrared (NIR) face images captured in nighttime. Given this database, we have conducted two types of cross-distance face matching (matching long-distance probe to 1-meter gallery) experiments: (i) intra-spectral (VIS to VIS) face matching, and (ii) cross-spectral (NIR to VIS) face matching. The proposed face recognition algorithm consists of following three major steps: (i) Gaussian filtering to remove high frequency noise, (ii) Scale Invariant Feature Transform (SIFT) in local image regions for feature representation, and (iii) a random subspace method to build discriminant subspaces for face recognition. Experimental results show that the proposed face recognition algorithm outperforms two commercial state-of-the-art face recognition SDKs (FaceVACS and PittPatt) for long distance face recognition in both daytime and nighttime operations. These results highlight the need for better data capture setup and robust face matching algorithms for cross spectral matching at distances greater than 100 meters.", 
    "editor": [
      {
        "familyName": "Lee", 
        "givenName": "Kyoung Mu", 
        "type": "Person"
      }, 
      {
        "familyName": "Matsushita", 
        "givenName": "Yasuyuki", 
        "type": "Person"
      }, 
      {
        "familyName": "Rehg", 
        "givenName": "James M.", 
        "type": "Person"
      }, 
      {
        "familyName": "Hu", 
        "givenName": "Zhanyi", 
        "type": "Person"
      }
    ], 
    "genre": "chapter", 
    "id": "sg:pub.10.1007/978-3-642-37444-9_55", 
    "isAccessibleForFree": false, 
    "isPartOf": {
      "isbn": [
        "978-3-642-37443-2", 
        "978-3-642-37444-9"
      ], 
      "name": "Computer Vision \u2013 ACCV 2012", 
      "type": "Book"
    }, 
    "keywords": [
      "face recognition algorithm", 
      "face recognition", 
      "recognition algorithm", 
      "face images", 
      "cross-spectral matching", 
      "Long Distance Face Recognition", 
      "heterogeneous face databases", 
      "face recognition capabilities", 
      "Invariant Feature Transform", 
      "face image databases", 
      "local image regions", 
      "outdoor face recognition", 
      "infrared face images", 
      "random subspace method", 
      "image database", 
      "feature representation", 
      "feature transform", 
      "security applications", 
      "image regions", 
      "face databases", 
      "robust face", 
      "Gaussian filtering", 
      "capture setup", 
      "discriminant subspace", 
      "recognition capability", 
      "outdoor environments", 
      "algorithm", 
      "surveillance system", 
      "nighttime environment", 
      "experimental results", 
      "images", 
      "commercial state", 
      "recognition", 
      "subspace method", 
      "matching", 
      "cross distances", 
      "database", 
      "SDK", 
      "major step", 
      "environment", 
      "filtering", 
      "system", 
      "long distances", 
      "capability", 
      "representation", 
      "nighttime operations", 
      "subspace", 
      "applications", 
      "meters", 
      "spectral matching", 
      "distance", 
      "operation", 
      "high-frequency noise", 
      "noise", 
      "transform", 
      "topic", 
      "face", 
      "setup", 
      "step", 
      "need", 
      "experiments", 
      "results", 
      "method", 
      "research", 
      "state", 
      "types", 
      "frequency noise", 
      "nighttime", 
      "region", 
      "study", 
      "light", 
      "daytime", 
      "visible light", 
      "paper", 
      "problem"
    ], 
    "name": "Nighttime Face Recognition at Long Distance: Cross-Distance and Cross-Spectral Matching", 
    "pagination": "708-721", 
    "productId": [
      {
        "name": "dimensions_id", 
        "type": "PropertyValue", 
        "value": [
          "pub.1019593791"
        ]
      }, 
      {
        "name": "doi", 
        "type": "PropertyValue", 
        "value": [
          "10.1007/978-3-642-37444-9_55"
        ]
      }
    ], 
    "publisher": {
      "name": "Springer Nature", 
      "type": "Organisation"
    }, 
    "sameAs": [
      "https://doi.org/10.1007/978-3-642-37444-9_55", 
      "https://app.dimensions.ai/details/publication/pub.1019593791"
    ], 
    "sdDataset": "chapters", 
    "sdDatePublished": "2022-11-24T21:13", 
    "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_199.jsonl", 
    "type": "Chapter", 
    "url": "https://doi.org/10.1007/978-3-642-37444-9_55"
  }
]
 

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.10.1007/978-3-642-37444-9_55'

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

curl -H 'Accept: application/n-triples' 'https://scigraph.springernature.com/pub.10.1007/978-3-642-37444-9_55'

Turtle is a human-readable linked data format.

curl -H 'Accept: text/turtle' 'https://scigraph.springernature.com/pub.10.1007/978-3-642-37444-9_55'

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

curl -H 'Accept: application/rdf+xml' 'https://scigraph.springernature.com/pub.10.1007/978-3-642-37444-9_55'


 

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

181 TRIPLES      22 PREDICATES      100 URIs      93 LITERALS      7 BLANK NODES

Subject Predicate Object
1 sg:pub.10.1007/978-3-642-37444-9_55 schema:about anzsrc-for:08
2 anzsrc-for:0801
3 schema:author N720e0110b27649eeb6e2af3679d34a10
4 schema:datePublished 2013
5 schema:datePublishedReg 2013-01-01
6 schema:description Automatic face recognition capability in surveillance systems is important for security applications. However, few studies have addressed the problem of outdoor face recognition at a long distance (over 100 meters) in both daytime and nighttime environments. In this paper, we first report on a system that we have designed to collect face image database at a long distance, called the Long Distance Heterogeneous Face Database (LDHF-DB) to advance research on this topic. The LDHF-DB contains face images collected in an outdoor environment at distances of 60 meters, 100 meters, and 150 meters, with both visible light (VIS) face images captured in daytime and near infrared (NIR) face images captured in nighttime. Given this database, we have conducted two types of cross-distance face matching (matching long-distance probe to 1-meter gallery) experiments: (i) intra-spectral (VIS to VIS) face matching, and (ii) cross-spectral (NIR to VIS) face matching. The proposed face recognition algorithm consists of following three major steps: (i) Gaussian filtering to remove high frequency noise, (ii) Scale Invariant Feature Transform (SIFT) in local image regions for feature representation, and (iii) a random subspace method to build discriminant subspaces for face recognition. Experimental results show that the proposed face recognition algorithm outperforms two commercial state-of-the-art face recognition SDKs (FaceVACS and PittPatt) for long distance face recognition in both daytime and nighttime operations. These results highlight the need for better data capture setup and robust face matching algorithms for cross spectral matching at distances greater than 100 meters.
7 schema:editor N23cf0574683d486e8ac1e561afa58515
8 schema:genre chapter
9 schema:isAccessibleForFree false
10 schema:isPartOf N60188dafa70b44a396a4465b262c329c
11 schema:keywords Gaussian filtering
12 Invariant Feature Transform
13 Long Distance Face Recognition
14 SDK
15 algorithm
16 applications
17 capability
18 capture setup
19 commercial state
20 cross distances
21 cross-spectral matching
22 database
23 daytime
24 discriminant subspace
25 distance
26 environment
27 experimental results
28 experiments
29 face
30 face databases
31 face image databases
32 face images
33 face recognition
34 face recognition algorithm
35 face recognition capabilities
36 feature representation
37 feature transform
38 filtering
39 frequency noise
40 heterogeneous face databases
41 high-frequency noise
42 image database
43 image regions
44 images
45 infrared face images
46 light
47 local image regions
48 long distances
49 major step
50 matching
51 meters
52 method
53 need
54 nighttime
55 nighttime environment
56 nighttime operations
57 noise
58 operation
59 outdoor environments
60 outdoor face recognition
61 paper
62 problem
63 random subspace method
64 recognition
65 recognition algorithm
66 recognition capability
67 region
68 representation
69 research
70 results
71 robust face
72 security applications
73 setup
74 spectral matching
75 state
76 step
77 study
78 subspace
79 subspace method
80 surveillance system
81 system
82 topic
83 transform
84 types
85 visible light
86 schema:name Nighttime Face Recognition at Long Distance: Cross-Distance and Cross-Spectral Matching
87 schema:pagination 708-721
88 schema:productId N2eab498fee064636a30603efdf1a5122
89 N7f4227d3b2fa48c7aea59813d773b3a7
90 schema:publisher N164ab9f38a1b488e893af7263af3d5e4
91 schema:sameAs https://app.dimensions.ai/details/publication/pub.1019593791
92 https://doi.org/10.1007/978-3-642-37444-9_55
93 schema:sdDatePublished 2022-11-24T21:13
94 schema:sdLicense https://scigraph.springernature.com/explorer/license/
95 schema:sdPublisher N807a60c8b1194797a87736cd778c3d4c
96 schema:url https://doi.org/10.1007/978-3-642-37444-9_55
97 sgo:license sg:explorer/license/
98 sgo:sdDataset chapters
99 rdf:type schema:Chapter
100 N0e1cff9570a649209a04d39ca63fbc7f schema:familyName Hu
101 schema:givenName Zhanyi
102 rdf:type schema:Person
103 N164ab9f38a1b488e893af7263af3d5e4 schema:name Springer Nature
104 rdf:type schema:Organisation
105 N212ef7b8050a48948760657e527f2557 rdf:first N0e1cff9570a649209a04d39ca63fbc7f
106 rdf:rest rdf:nil
107 N23cf0574683d486e8ac1e561afa58515 rdf:first N6e06602dcc574f39b64b260bb7e46771
108 rdf:rest Ne6d36ae8004a4081b84c6c78d0f029de
109 N2ddcd9c848d849819fb6ef10c33fa769 rdf:first sg:person.07676740373.20
110 rdf:rest N94a61f15e8b64b62acb32914dd30621b
111 N2eab498fee064636a30603efdf1a5122 schema:name doi
112 schema:value 10.1007/978-3-642-37444-9_55
113 rdf:type schema:PropertyValue
114 N46f763a789a443ffb20a5d0548b12cff rdf:first sg:person.01031110710.30
115 rdf:rest rdf:nil
116 N60188dafa70b44a396a4465b262c329c schema:isbn 978-3-642-37443-2
117 978-3-642-37444-9
118 schema:name Computer Vision – ACCV 2012
119 rdf:type schema:Book
120 N63cb0b04398a48d2b41a17e799fb3420 schema:familyName Rehg
121 schema:givenName James M.
122 rdf:type schema:Person
123 N6499803c6fc44a3d8c134d25102ee816 rdf:first sg:person.01042611654.44
124 rdf:rest N46f763a789a443ffb20a5d0548b12cff
125 N6e06602dcc574f39b64b260bb7e46771 schema:familyName Lee
126 schema:givenName Kyoung Mu
127 rdf:type schema:Person
128 N720e0110b27649eeb6e2af3679d34a10 rdf:first sg:person.011352500542.64
129 rdf:rest N2ddcd9c848d849819fb6ef10c33fa769
130 N7f4227d3b2fa48c7aea59813d773b3a7 schema:name dimensions_id
131 schema:value pub.1019593791
132 rdf:type schema:PropertyValue
133 N807a60c8b1194797a87736cd778c3d4c schema:name Springer Nature - SN SciGraph project
134 rdf:type schema:Organization
135 N94a61f15e8b64b62acb32914dd30621b rdf:first sg:person.010053136712.99
136 rdf:rest N6499803c6fc44a3d8c134d25102ee816
137 Ne6d36ae8004a4081b84c6c78d0f029de rdf:first Nf27a1fdececd46af8a4e8dfbb6edfdf2
138 rdf:rest Nfabb9b672be94c1db647a042beaa0bf5
139 Nf27a1fdececd46af8a4e8dfbb6edfdf2 schema:familyName Matsushita
140 schema:givenName Yasuyuki
141 rdf:type schema:Person
142 Nfabb9b672be94c1db647a042beaa0bf5 rdf:first N63cb0b04398a48d2b41a17e799fb3420
143 rdf:rest N212ef7b8050a48948760657e527f2557
144 anzsrc-for:08 schema:inDefinedTermSet anzsrc-for:
145 schema:name Information and Computing Sciences
146 rdf:type schema:DefinedTerm
147 anzsrc-for:0801 schema:inDefinedTermSet anzsrc-for:
148 schema:name Artificial Intelligence and Image Processing
149 rdf:type schema:DefinedTerm
150 sg:person.010053136712.99 schema:affiliation grid-institutes:grid.222754.4
151 schema:familyName Kang
152 schema:givenName Dongoh
153 schema:sameAs https://app.dimensions.ai/discover/publication?and_facet_researcher=ur.010053136712.99
154 rdf:type schema:Person
155 sg:person.01031110710.30 schema:affiliation grid-institutes:grid.17088.36
156 schema:familyName Jain
157 schema:givenName Anil K.
158 schema:sameAs https://app.dimensions.ai/discover/publication?and_facet_researcher=ur.01031110710.30
159 rdf:type schema:Person
160 sg:person.01042611654.44 schema:affiliation grid-institutes:grid.222754.4
161 schema:familyName Lee
162 schema:givenName Seong-Whan
163 schema:sameAs https://app.dimensions.ai/discover/publication?and_facet_researcher=ur.01042611654.44
164 rdf:type schema:Person
165 sg:person.011352500542.64 schema:affiliation grid-institutes:grid.222754.4
166 schema:familyName Maeng
167 schema:givenName Hyunju
168 schema:sameAs https://app.dimensions.ai/discover/publication?and_facet_researcher=ur.011352500542.64
169 rdf:type schema:Person
170 sg:person.07676740373.20 schema:affiliation grid-institutes:grid.17088.36
171 schema:familyName Liao
172 schema:givenName Shengcai
173 schema:sameAs https://app.dimensions.ai/discover/publication?and_facet_researcher=ur.07676740373.20
174 rdf:type schema:Person
175 grid-institutes:grid.17088.36 schema:alternateName Dept. of Comp. Sci. & Eng., Michigan State Univ., 48824, E. Lansing, MI, USA
176 schema:name Dept. of Brain and Cognitive Eng., Korea Univ., Seoul, Korea
177 Dept. of Comp. Sci. & Eng., Michigan State Univ., 48824, E. Lansing, MI, USA
178 rdf:type schema:Organization
179 grid-institutes:grid.222754.4 schema:alternateName Dept. of Brain and Cognitive Eng., Korea Univ., Seoul, Korea
180 schema:name Dept. of Brain and Cognitive Eng., Korea Univ., Seoul, Korea
181 rdf:type schema:Organization
 




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


...