An Efficient Algorithm for Detecting Faces from Color Images View Full Text


Ontology type: schema:Chapter     


Chapter Info

DATE

2002-12-16

AUTHORS

Wei Shou-Der , Lai Shang-Hong

ABSTRACT

In this paper, we propose an efficient face detection algorithm based on integrating multiple features in face images. The proposed algorithm combines many simple methods to achieve a reasonable detection rate with an acceptable false alarm rate. There are four main components in our face detection algorithm; namely, skin-color filtering, face template search, face verification and overlapped-detection merging. A skin-color filtering process is first applied to eliminate image regions with corresponding color distributions unlikely to be face regions. For regions passing the skin-color test, we find the face candidates by a hierarchical nearest-neighbor search of multiple face templates under a limited range of geometric transformations. Subsequently, the face candidates are further checked via some face verification criteria, which are derived from the face symmetry property and the relatively positional constrains of facial features. Finally, the overlapped face candidate regions are merged to obtain the final face detection results. More... »

PAGES

1177-1184

Book

TITLE

Advances in Multimedia Information Processing — PCM 2002

ISBN

978-3-540-00262-8
978-3-540-36228-9

Identifiers

URI

http://scigraph.springernature.com/pub.10.1007/3-540-36228-2_146

DOI

http://dx.doi.org/10.1007/3-540-36228-2_146

DIMENSIONS

https://app.dimensions.ai/details/publication/pub.1022520700


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 Computer Science, National Tsing Hua University, Hsinchu, Taiwan", 
          "id": "http://www.grid.ac/institutes/grid.38348.34", 
          "name": [
            "Dept. of Computer Science, National Tsing Hua University, Hsinchu, Taiwan"
          ], 
          "type": "Organization"
        }, 
        "familyName": "Shou-Der", 
        "givenName": "Wei", 
        "type": "Person"
      }, 
      {
        "affiliation": {
          "alternateName": "Dept. of Computer Science, National Tsing Hua University, Hsinchu, Taiwan", 
          "id": "http://www.grid.ac/institutes/grid.38348.34", 
          "name": [
            "Dept. of Computer Science, National Tsing Hua University, Hsinchu, Taiwan"
          ], 
          "type": "Organization"
        }, 
        "familyName": "Shang-Hong", 
        "givenName": "Lai", 
        "id": "sg:person.014153211135.94", 
        "sameAs": [
          "https://app.dimensions.ai/discover/publication?and_facet_researcher=ur.014153211135.94"
        ], 
        "type": "Person"
      }
    ], 
    "datePublished": "2002-12-16", 
    "datePublishedReg": "2002-12-16", 
    "description": "In this paper, we propose an efficient face detection algorithm based on integrating multiple features in face images. The proposed algorithm combines many simple methods to achieve a reasonable detection rate with an acceptable false alarm rate. There are four main components in our face detection algorithm; namely, skin-color filtering, face template search, face verification and overlapped-detection merging. A skin-color filtering process is first applied to eliminate image regions with corresponding color distributions unlikely to be face regions. For regions passing the skin-color test, we find the face candidates by a hierarchical nearest-neighbor search of multiple face templates under a limited range of geometric transformations. Subsequently, the face candidates are further checked via some face verification criteria, which are derived from the face symmetry property and the relatively positional constrains of facial features. Finally, the overlapped face candidate regions are merged to obtain the final face detection results.", 
    "editor": [
      {
        "familyName": "Chen", 
        "givenName": "Yung-Chang", 
        "type": "Person"
      }, 
      {
        "familyName": "Chang", 
        "givenName": "Long-Wen", 
        "type": "Person"
      }, 
      {
        "familyName": "Hsu", 
        "givenName": "Chiou-Ting", 
        "type": "Person"
      }
    ], 
    "genre": "chapter", 
    "id": "sg:pub.10.1007/3-540-36228-2_146", 
    "inLanguage": "en", 
    "isAccessibleForFree": false, 
    "isPartOf": {
      "isbn": [
        "978-3-540-00262-8", 
        "978-3-540-36228-9"
      ], 
      "name": "Advances in Multimedia Information Processing \u2014 PCM 2002", 
      "type": "Book"
    }, 
    "keywords": [
      "face detection algorithm", 
      "face candidates", 
      "detection algorithm", 
      "efficient face detection algorithm", 
      "nearest-neighbor search", 
      "face detection results", 
      "multiple face templates", 
      "face candidate regions", 
      "reasonable detection rates", 
      "acceptable false alarm rate", 
      "skin-color filtering", 
      "false alarm rate", 
      "image regions", 
      "face template", 
      "face images", 
      "color images", 
      "efficient algorithm", 
      "face region", 
      "geometric transformations", 
      "multiple features", 
      "detection results", 
      "alarm rate", 
      "color distribution", 
      "algorithm", 
      "template search", 
      "verification criteria", 
      "filtering process", 
      "facial features", 
      "candidate regions", 
      "detection rate", 
      "images", 
      "search", 
      "verification", 
      "filtering", 
      "features", 
      "main components", 
      "merging", 
      "constrains", 
      "template", 
      "method", 
      "limited range", 
      "process", 
      "face", 
      "transformation", 
      "candidates", 
      "components", 
      "symmetry properties", 
      "results", 
      "simple method", 
      "criteria", 
      "rate", 
      "region", 
      "distribution", 
      "range", 
      "properties", 
      "test", 
      "paper", 
      "overlapped-detection merging", 
      "skin-color filtering process", 
      "skin-color test", 
      "hierarchical nearest-neighbor search", 
      "face verification criteria", 
      "face symmetry property", 
      "positional constrains", 
      "final face detection results"
    ], 
    "name": "An Efficient Algorithm for Detecting Faces from Color Images", 
    "pagination": "1177-1184", 
    "productId": [
      {
        "name": "dimensions_id", 
        "type": "PropertyValue", 
        "value": [
          "pub.1022520700"
        ]
      }, 
      {
        "name": "doi", 
        "type": "PropertyValue", 
        "value": [
          "10.1007/3-540-36228-2_146"
        ]
      }
    ], 
    "publisher": {
      "name": "Springer Nature", 
      "type": "Organisation"
    }, 
    "sameAs": [
      "https://doi.org/10.1007/3-540-36228-2_146", 
      "https://app.dimensions.ai/details/publication/pub.1022520700"
    ], 
    "sdDataset": "chapters", 
    "sdDatePublished": "2021-12-01T20:01", 
    "sdLicense": "https://scigraph.springernature.com/explorer/license/", 
    "sdPublisher": {
      "name": "Springer Nature - SN SciGraph project", 
      "type": "Organization"
    }, 
    "sdSource": "s3://com-springernature-scigraph/baseset/20211201/entities/gbq_results/chapter/chapter_231.jsonl", 
    "type": "Chapter", 
    "url": "https://doi.org/10.1007/3-540-36228-2_146"
  }
]
 

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.10.1007/3-540-36228-2_146'

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

curl -H 'Accept: application/n-triples' 'https://scigraph.springernature.com/pub.10.1007/3-540-36228-2_146'

Turtle is a human-readable linked data format.

curl -H 'Accept: text/turtle' 'https://scigraph.springernature.com/pub.10.1007/3-540-36228-2_146'

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

curl -H 'Accept: application/rdf+xml' 'https://scigraph.springernature.com/pub.10.1007/3-540-36228-2_146'


 

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

141 TRIPLES      23 PREDICATES      90 URIs      83 LITERALS      7 BLANK NODES

Subject Predicate Object
1 sg:pub.10.1007/3-540-36228-2_146 schema:about anzsrc-for:08
2 anzsrc-for:0801
3 schema:author N261ec72f72f248129e9d106dbbeaeb7b
4 schema:datePublished 2002-12-16
5 schema:datePublishedReg 2002-12-16
6 schema:description In this paper, we propose an efficient face detection algorithm based on integrating multiple features in face images. The proposed algorithm combines many simple methods to achieve a reasonable detection rate with an acceptable false alarm rate. There are four main components in our face detection algorithm; namely, skin-color filtering, face template search, face verification and overlapped-detection merging. A skin-color filtering process is first applied to eliminate image regions with corresponding color distributions unlikely to be face regions. For regions passing the skin-color test, we find the face candidates by a hierarchical nearest-neighbor search of multiple face templates under a limited range of geometric transformations. Subsequently, the face candidates are further checked via some face verification criteria, which are derived from the face symmetry property and the relatively positional constrains of facial features. Finally, the overlapped face candidate regions are merged to obtain the final face detection results.
7 schema:editor Nb7841235e57b4df79bd1568c48e45eda
8 schema:genre chapter
9 schema:inLanguage en
10 schema:isAccessibleForFree false
11 schema:isPartOf Ne525ea4b1ccb44cf86784164459b4d9b
12 schema:keywords acceptable false alarm rate
13 alarm rate
14 algorithm
15 candidate regions
16 candidates
17 color distribution
18 color images
19 components
20 constrains
21 criteria
22 detection algorithm
23 detection rate
24 detection results
25 distribution
26 efficient algorithm
27 efficient face detection algorithm
28 face
29 face candidate regions
30 face candidates
31 face detection algorithm
32 face detection results
33 face images
34 face region
35 face symmetry property
36 face template
37 face verification criteria
38 facial features
39 false alarm rate
40 features
41 filtering
42 filtering process
43 final face detection results
44 geometric transformations
45 hierarchical nearest-neighbor search
46 image regions
47 images
48 limited range
49 main components
50 merging
51 method
52 multiple face templates
53 multiple features
54 nearest-neighbor search
55 overlapped-detection merging
56 paper
57 positional constrains
58 process
59 properties
60 range
61 rate
62 reasonable detection rates
63 region
64 results
65 search
66 simple method
67 skin-color filtering
68 skin-color filtering process
69 skin-color test
70 symmetry properties
71 template
72 template search
73 test
74 transformation
75 verification
76 verification criteria
77 schema:name An Efficient Algorithm for Detecting Faces from Color Images
78 schema:pagination 1177-1184
79 schema:productId N41ae29feab334079ad8bf86b10ed4e37
80 N787c176a567d463abf99d7f8f92a4cbf
81 schema:publisher N89a60bdad318408a9bc985114951737d
82 schema:sameAs https://app.dimensions.ai/details/publication/pub.1022520700
83 https://doi.org/10.1007/3-540-36228-2_146
84 schema:sdDatePublished 2021-12-01T20:01
85 schema:sdLicense https://scigraph.springernature.com/explorer/license/
86 schema:sdPublisher Ncb688bf93b0f46ea9aa5eeed25bbb55e
87 schema:url https://doi.org/10.1007/3-540-36228-2_146
88 sgo:license sg:explorer/license/
89 sgo:sdDataset chapters
90 rdf:type schema:Chapter
91 N099f935aee5b4565b8f5ff8513ab3b7c rdf:first sg:person.014153211135.94
92 rdf:rest rdf:nil
93 N261ec72f72f248129e9d106dbbeaeb7b rdf:first N8f66cc05323e485b9ef1457c92ed0d0d
94 rdf:rest N099f935aee5b4565b8f5ff8513ab3b7c
95 N30671341ff3149569c7ba681a43e5a46 schema:familyName Chen
96 schema:givenName Yung-Chang
97 rdf:type schema:Person
98 N4154833b2739415e8a5d6bbf492623b0 rdf:first Ndbb8207ecfbb45478115750f1e250d5c
99 rdf:rest N7eb7beef57bf48c096844e8a008eb137
100 N41ae29feab334079ad8bf86b10ed4e37 schema:name doi
101 schema:value 10.1007/3-540-36228-2_146
102 rdf:type schema:PropertyValue
103 N787c176a567d463abf99d7f8f92a4cbf schema:name dimensions_id
104 schema:value pub.1022520700
105 rdf:type schema:PropertyValue
106 N7eb7beef57bf48c096844e8a008eb137 rdf:first Ndfdefe5198b54e0d942d1967a027545a
107 rdf:rest rdf:nil
108 N89a60bdad318408a9bc985114951737d schema:name Springer Nature
109 rdf:type schema:Organisation
110 N8f66cc05323e485b9ef1457c92ed0d0d schema:affiliation grid-institutes:grid.38348.34
111 schema:familyName Shou-Der
112 schema:givenName Wei
113 rdf:type schema:Person
114 Nb7841235e57b4df79bd1568c48e45eda rdf:first N30671341ff3149569c7ba681a43e5a46
115 rdf:rest N4154833b2739415e8a5d6bbf492623b0
116 Ncb688bf93b0f46ea9aa5eeed25bbb55e schema:name Springer Nature - SN SciGraph project
117 rdf:type schema:Organization
118 Ndbb8207ecfbb45478115750f1e250d5c schema:familyName Chang
119 schema:givenName Long-Wen
120 rdf:type schema:Person
121 Ndfdefe5198b54e0d942d1967a027545a schema:familyName Hsu
122 schema:givenName Chiou-Ting
123 rdf:type schema:Person
124 Ne525ea4b1ccb44cf86784164459b4d9b schema:isbn 978-3-540-00262-8
125 978-3-540-36228-9
126 schema:name Advances in Multimedia Information Processing — PCM 2002
127 rdf:type schema:Book
128 anzsrc-for:08 schema:inDefinedTermSet anzsrc-for:
129 schema:name Information and Computing Sciences
130 rdf:type schema:DefinedTerm
131 anzsrc-for:0801 schema:inDefinedTermSet anzsrc-for:
132 schema:name Artificial Intelligence and Image Processing
133 rdf:type schema:DefinedTerm
134 sg:person.014153211135.94 schema:affiliation grid-institutes:grid.38348.34
135 schema:familyName Shang-Hong
136 schema:givenName Lai
137 schema:sameAs https://app.dimensions.ai/discover/publication?and_facet_researcher=ur.014153211135.94
138 rdf:type schema:Person
139 grid-institutes:grid.38348.34 schema:alternateName Dept. of Computer Science, National Tsing Hua University, Hsinchu, Taiwan
140 schema:name Dept. of Computer Science, National Tsing Hua University, Hsinchu, Taiwan
141 rdf:type schema:Organization
 




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


...