Example Based Non-rigid Shape Detection View Full Text


Ontology type: schema:Chapter     


Chapter Info

DATE

2006

AUTHORS

Yefeng Zheng , Xiang Sean Zhou , Bogdan Georgescu , Shaohua Kevin Zhou , Dorin Comaniciu

ABSTRACT

Since it is hard to handcraft the prior knowledge in a shape detection framework, machine learning methods are preferred to exploit the expert annotation of the target shape in a database. In the previous approaches [1,2] , an optimal similarity transformation is exhaustively searched for to maximize the response of a trained classification model. At best, these approaches only give a rough estimate of the position of a non-rigid shape. In this paper, we propose a novel machine learning based approach to achieve a refined shape detection result. We train a model that has the largest response on a reference shape and a smaller response on other shapes. During shape detection, we search for an optimal non-rigid deformation to maximize the response of the trained model on the deformed image block. Since exhaustive searching is inapplicable for a non-rigid deformation space with a high dimension, currently, example based searching is used instead. Experiments on two applications, left ventricle endocardial border detection and facial feature detection, demonstrate the robustness of our approach. It outperforms the well-known ASM and AAM approaches on challenging samples. More... »

PAGES

423-436

Identifiers

URI

http://scigraph.springernature.com/pub.10.1007/11744085_33

DOI

http://dx.doi.org/10.1007/11744085_33

DIMENSIONS

https://app.dimensions.ai/details/publication/pub.1032770298


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": "Siemens Corporate Research, 08540, Princeton, NJ, USA", 
          "id": "http://www.grid.ac/institutes/grid.419233.e", 
          "name": [
            "Siemens Corporate Research, 08540, Princeton, NJ, USA"
          ], 
          "type": "Organization"
        }, 
        "familyName": "Zheng", 
        "givenName": "Yefeng", 
        "id": "sg:person.0767211426.21", 
        "sameAs": [
          "https://app.dimensions.ai/discover/publication?and_facet_researcher=ur.0767211426.21"
        ], 
        "type": "Person"
      }, 
      {
        "affiliation": {
          "alternateName": "Siemens Medical Solutions, 19355, Malvern, PA, USA", 
          "id": "http://www.grid.ac/institutes/grid.415886.6", 
          "name": [
            "Siemens Medical Solutions, 19355, Malvern, PA, USA"
          ], 
          "type": "Organization"
        }, 
        "familyName": "Zhou", 
        "givenName": "Xiang Sean", 
        "id": "sg:person.016461275373.08", 
        "sameAs": [
          "https://app.dimensions.ai/discover/publication?and_facet_researcher=ur.016461275373.08"
        ], 
        "type": "Person"
      }, 
      {
        "affiliation": {
          "alternateName": "Siemens Corporate Research, 08540, Princeton, NJ, USA", 
          "id": "http://www.grid.ac/institutes/grid.419233.e", 
          "name": [
            "Siemens Corporate Research, 08540, Princeton, NJ, USA"
          ], 
          "type": "Organization"
        }, 
        "familyName": "Georgescu", 
        "givenName": "Bogdan", 
        "id": "sg:person.0703547214.37", 
        "sameAs": [
          "https://app.dimensions.ai/discover/publication?and_facet_researcher=ur.0703547214.37"
        ], 
        "type": "Person"
      }, 
      {
        "affiliation": {
          "alternateName": "Siemens Corporate Research, 08540, Princeton, NJ, USA", 
          "id": "http://www.grid.ac/institutes/grid.419233.e", 
          "name": [
            "Siemens Corporate Research, 08540, Princeton, NJ, USA"
          ], 
          "type": "Organization"
        }, 
        "familyName": "Zhou", 
        "givenName": "Shaohua Kevin", 
        "id": "sg:person.01372425362.30", 
        "sameAs": [
          "https://app.dimensions.ai/discover/publication?and_facet_researcher=ur.01372425362.30"
        ], 
        "type": "Person"
      }, 
      {
        "affiliation": {
          "alternateName": "Siemens Corporate Research, 08540, Princeton, NJ, USA", 
          "id": "http://www.grid.ac/institutes/grid.419233.e", 
          "name": [
            "Siemens Corporate Research, 08540, Princeton, NJ, USA"
          ], 
          "type": "Organization"
        }, 
        "familyName": "Comaniciu", 
        "givenName": "Dorin", 
        "id": "sg:person.01066111014.77", 
        "sameAs": [
          "https://app.dimensions.ai/discover/publication?and_facet_researcher=ur.01066111014.77"
        ], 
        "type": "Person"
      }
    ], 
    "datePublished": "2006", 
    "datePublishedReg": "2006-01-01", 
    "description": "Since it is hard to handcraft the prior knowledge in a shape detection framework, machine learning methods are preferred to exploit the expert annotation of the target shape in a database. In the previous approaches [1,2] , an optimal similarity transformation is exhaustively searched for to maximize the response of a trained classification model. At best, these approaches only give a rough estimate of the position of a non-rigid shape. In this paper, we propose a novel machine learning based approach to achieve a refined shape detection result. We train a model that has the largest response on a reference shape and a smaller response on other shapes. During shape detection, we search for an optimal non-rigid deformation to maximize the response of the trained model on the deformed image block. Since exhaustive searching is inapplicable for a non-rigid deformation space with a high dimension, currently, example based searching is used instead. Experiments on two applications, left ventricle endocardial border detection and facial feature detection, demonstrate the robustness of our approach. It outperforms the well-known ASM and AAM approaches on challenging samples.", 
    "editor": [
      {
        "familyName": "Leonardis", 
        "givenName": "Ale\u0161", 
        "type": "Person"
      }, 
      {
        "familyName": "Bischof", 
        "givenName": "Horst", 
        "type": "Person"
      }, 
      {
        "familyName": "Pinz", 
        "givenName": "Axel", 
        "type": "Person"
      }
    ], 
    "genre": "chapter", 
    "id": "sg:pub.10.1007/11744085_33", 
    "inLanguage": "en", 
    "isAccessibleForFree": false, 
    "isPartOf": {
      "isbn": [
        "978-3-540-33838-3", 
        "978-3-540-33839-0"
      ], 
      "name": "Computer Vision \u2013 ECCV 2006", 
      "type": "Book"
    }, 
    "keywords": [
      "shape detection", 
      "facial feature detection", 
      "machine learning methods", 
      "non-rigid deformations", 
      "optimal similarity transformation", 
      "non-rigid shapes", 
      "detection framework", 
      "image blocks", 
      "feature detection", 
      "AAM approach", 
      "expert annotations", 
      "novel machine", 
      "learning method", 
      "exhaustive searching", 
      "detection results", 
      "previous approaches", 
      "classification model", 
      "border detection", 
      "endocardial border detection", 
      "prior knowledge", 
      "reference shape", 
      "searching", 
      "higher dimensions", 
      "target shape", 
      "detection", 
      "annotation", 
      "machine", 
      "robustness", 
      "framework", 
      "database", 
      "example", 
      "model", 
      "applications", 
      "space", 
      "rough estimate", 
      "block", 
      "ASM", 
      "deformation space", 
      "knowledge", 
      "method", 
      "experiments", 
      "shape", 
      "similarity transformation", 
      "transformation", 
      "results", 
      "position", 
      "dimensions", 
      "estimates", 
      "deformation", 
      "response", 
      "samples", 
      "larger responses", 
      "approach", 
      "paper", 
      "small response", 
      "shape detection framework", 
      "refined shape detection result", 
      "shape detection result", 
      "optimal non-rigid deformation", 
      "deformed image block", 
      "non-rigid deformation space", 
      "ventricle endocardial border detection", 
      "Non-rigid Shape Detection"
    ], 
    "name": "Example Based Non-rigid Shape Detection", 
    "pagination": "423-436", 
    "productId": [
      {
        "name": "dimensions_id", 
        "type": "PropertyValue", 
        "value": [
          "pub.1032770298"
        ]
      }, 
      {
        "name": "doi", 
        "type": "PropertyValue", 
        "value": [
          "10.1007/11744085_33"
        ]
      }
    ], 
    "publisher": {
      "name": "Springer Nature", 
      "type": "Organisation"
    }, 
    "sameAs": [
      "https://doi.org/10.1007/11744085_33", 
      "https://app.dimensions.ai/details/publication/pub.1032770298"
    ], 
    "sdDataset": "chapters", 
    "sdDatePublished": "2022-01-01T19:18", 
    "sdLicense": "https://scigraph.springernature.com/explorer/license/", 
    "sdPublisher": {
      "name": "Springer Nature - SN SciGraph project", 
      "type": "Organization"
    }, 
    "sdSource": "s3://com-springernature-scigraph/baseset/20220101/entities/gbq_results/chapter/chapter_313.jsonl", 
    "type": "Chapter", 
    "url": "https://doi.org/10.1007/11744085_33"
  }
]
 

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.10.1007/11744085_33'

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

curl -H 'Accept: application/n-triples' 'https://scigraph.springernature.com/pub.10.1007/11744085_33'

Turtle is a human-readable linked data format.

curl -H 'Accept: text/turtle' 'https://scigraph.springernature.com/pub.10.1007/11744085_33'

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

curl -H 'Accept: application/rdf+xml' 'https://scigraph.springernature.com/pub.10.1007/11744085_33'


 

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

164 TRIPLES      23 PREDICATES      89 URIs      82 LITERALS      7 BLANK NODES

Subject Predicate Object
1 sg:pub.10.1007/11744085_33 schema:about anzsrc-for:08
2 anzsrc-for:0801
3 schema:author Ndad3dc84807847e891f7614748cf0ef9
4 schema:datePublished 2006
5 schema:datePublishedReg 2006-01-01
6 schema:description Since it is hard to handcraft the prior knowledge in a shape detection framework, machine learning methods are preferred to exploit the expert annotation of the target shape in a database. In the previous approaches [1,2] , an optimal similarity transformation is exhaustively searched for to maximize the response of a trained classification model. At best, these approaches only give a rough estimate of the position of a non-rigid shape. In this paper, we propose a novel machine learning based approach to achieve a refined shape detection result. We train a model that has the largest response on a reference shape and a smaller response on other shapes. During shape detection, we search for an optimal non-rigid deformation to maximize the response of the trained model on the deformed image block. Since exhaustive searching is inapplicable for a non-rigid deformation space with a high dimension, currently, example based searching is used instead. Experiments on two applications, left ventricle endocardial border detection and facial feature detection, demonstrate the robustness of our approach. It outperforms the well-known ASM and AAM approaches on challenging samples.
7 schema:editor N769a23c3497d41b59edae02dd8792589
8 schema:genre chapter
9 schema:inLanguage en
10 schema:isAccessibleForFree false
11 schema:isPartOf Ne6c828308e7a4e8e9a2607dadc2cc810
12 schema:keywords AAM approach
13 ASM
14 Non-rigid Shape Detection
15 annotation
16 applications
17 approach
18 block
19 border detection
20 classification model
21 database
22 deformation
23 deformation space
24 deformed image block
25 detection
26 detection framework
27 detection results
28 dimensions
29 endocardial border detection
30 estimates
31 example
32 exhaustive searching
33 experiments
34 expert annotations
35 facial feature detection
36 feature detection
37 framework
38 higher dimensions
39 image blocks
40 knowledge
41 larger responses
42 learning method
43 machine
44 machine learning methods
45 method
46 model
47 non-rigid deformation space
48 non-rigid deformations
49 non-rigid shapes
50 novel machine
51 optimal non-rigid deformation
52 optimal similarity transformation
53 paper
54 position
55 previous approaches
56 prior knowledge
57 reference shape
58 refined shape detection result
59 response
60 results
61 robustness
62 rough estimate
63 samples
64 searching
65 shape
66 shape detection
67 shape detection framework
68 shape detection result
69 similarity transformation
70 small response
71 space
72 target shape
73 transformation
74 ventricle endocardial border detection
75 schema:name Example Based Non-rigid Shape Detection
76 schema:pagination 423-436
77 schema:productId Nd7cf752eed504d00ba07ff0764124457
78 Nd929267e83cb41f59ceb0a2f0fb6414c
79 schema:publisher N3ffc1218dba1480f99bcbdac305bbd70
80 schema:sameAs https://app.dimensions.ai/details/publication/pub.1032770298
81 https://doi.org/10.1007/11744085_33
82 schema:sdDatePublished 2022-01-01T19:18
83 schema:sdLicense https://scigraph.springernature.com/explorer/license/
84 schema:sdPublisher N44af6ac0d73749369b5c9586d35b0a3e
85 schema:url https://doi.org/10.1007/11744085_33
86 sgo:license sg:explorer/license/
87 sgo:sdDataset chapters
88 rdf:type schema:Chapter
89 N07f4683f625b4aea84f1c7d83aca0620 schema:familyName Leonardis
90 schema:givenName Aleš
91 rdf:type schema:Person
92 N3ffc1218dba1480f99bcbdac305bbd70 schema:name Springer Nature
93 rdf:type schema:Organisation
94 N44af6ac0d73749369b5c9586d35b0a3e schema:name Springer Nature - SN SciGraph project
95 rdf:type schema:Organization
96 N45bcf06dae4c459c9d8f4ef8e1dd4569 rdf:first sg:person.01372425362.30
97 rdf:rest Nf4acfb3a6c1340bf8dd8b3ecbbc833e7
98 N490f754224e4481a8e84865e1d038faa rdf:first sg:person.0703547214.37
99 rdf:rest N45bcf06dae4c459c9d8f4ef8e1dd4569
100 N4d41daab9e0340988d4c668f8794241f schema:familyName Pinz
101 schema:givenName Axel
102 rdf:type schema:Person
103 N769a23c3497d41b59edae02dd8792589 rdf:first N07f4683f625b4aea84f1c7d83aca0620
104 rdf:rest Na0df06518ab14ecb926f9e23cf6103e5
105 N78574d23c30540a2881a3a894dd28a22 rdf:first sg:person.016461275373.08
106 rdf:rest N490f754224e4481a8e84865e1d038faa
107 N990362e8098c4600a7cbba5616bbc709 rdf:first N4d41daab9e0340988d4c668f8794241f
108 rdf:rest rdf:nil
109 Na0df06518ab14ecb926f9e23cf6103e5 rdf:first Nf37f4c07a1f74a508034e0c30f90e3c8
110 rdf:rest N990362e8098c4600a7cbba5616bbc709
111 Nd7cf752eed504d00ba07ff0764124457 schema:name doi
112 schema:value 10.1007/11744085_33
113 rdf:type schema:PropertyValue
114 Nd929267e83cb41f59ceb0a2f0fb6414c schema:name dimensions_id
115 schema:value pub.1032770298
116 rdf:type schema:PropertyValue
117 Ndad3dc84807847e891f7614748cf0ef9 rdf:first sg:person.0767211426.21
118 rdf:rest N78574d23c30540a2881a3a894dd28a22
119 Ne6c828308e7a4e8e9a2607dadc2cc810 schema:isbn 978-3-540-33838-3
120 978-3-540-33839-0
121 schema:name Computer Vision – ECCV 2006
122 rdf:type schema:Book
123 Nf37f4c07a1f74a508034e0c30f90e3c8 schema:familyName Bischof
124 schema:givenName Horst
125 rdf:type schema:Person
126 Nf4acfb3a6c1340bf8dd8b3ecbbc833e7 rdf:first sg:person.01066111014.77
127 rdf:rest rdf:nil
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.01066111014.77 schema:affiliation grid-institutes:grid.419233.e
135 schema:familyName Comaniciu
136 schema:givenName Dorin
137 schema:sameAs https://app.dimensions.ai/discover/publication?and_facet_researcher=ur.01066111014.77
138 rdf:type schema:Person
139 sg:person.01372425362.30 schema:affiliation grid-institutes:grid.419233.e
140 schema:familyName Zhou
141 schema:givenName Shaohua Kevin
142 schema:sameAs https://app.dimensions.ai/discover/publication?and_facet_researcher=ur.01372425362.30
143 rdf:type schema:Person
144 sg:person.016461275373.08 schema:affiliation grid-institutes:grid.415886.6
145 schema:familyName Zhou
146 schema:givenName Xiang Sean
147 schema:sameAs https://app.dimensions.ai/discover/publication?and_facet_researcher=ur.016461275373.08
148 rdf:type schema:Person
149 sg:person.0703547214.37 schema:affiliation grid-institutes:grid.419233.e
150 schema:familyName Georgescu
151 schema:givenName Bogdan
152 schema:sameAs https://app.dimensions.ai/discover/publication?and_facet_researcher=ur.0703547214.37
153 rdf:type schema:Person
154 sg:person.0767211426.21 schema:affiliation grid-institutes:grid.419233.e
155 schema:familyName Zheng
156 schema:givenName Yefeng
157 schema:sameAs https://app.dimensions.ai/discover/publication?and_facet_researcher=ur.0767211426.21
158 rdf:type schema:Person
159 grid-institutes:grid.415886.6 schema:alternateName Siemens Medical Solutions, 19355, Malvern, PA, USA
160 schema:name Siemens Medical Solutions, 19355, Malvern, PA, USA
161 rdf:type schema:Organization
162 grid-institutes:grid.419233.e schema:alternateName Siemens Corporate Research, 08540, Princeton, NJ, USA
163 schema:name Siemens Corporate Research, 08540, Princeton, NJ, USA
164 rdf:type schema:Organization
 




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


...