Efficient Spatial Segmentation of Hyper-spectral 3D Volume Data View Full Text


Ontology type: schema:Chapter     


Chapter Info

DATE

2013-07-16

AUTHORS

Jan Hendrik Kobarg , Theodore Alexandrov

ABSTRACT

Segmentation of noisy hyper-spectral imaging data using clustering requires special algorithms. Such algorithms should consider spatial relations between the pixels, since neighbor pixels should usually be clustered into one group. However, in case of large spectral dimension (p), cluster algorithms suffer from the curse of dimensionality and have high memory requirements as well as long run-times. We propose to embed pixels from a window of w ×w pixels to a feature space of dimension pw2. The effect of implicit denoising due to the window is controlled by weights depending on the spatial distance. We propose either using Gaussian weights or data-adaptive weights based on the similarity of pixels. Finally, any vectorial clustering algorithm, like k-means, can be applied in this feature space. Then, we use the FastMap algorithm for dimensionality reduction. The proposed algorithm is evaluated on a large simulated imaging mass spectrometry dataset. More... »

PAGES

95-103

Identifiers

URI

http://scigraph.springernature.com/pub.10.1007/978-3-319-00035-0_9

DOI

http://dx.doi.org/10.1007/978-3-319-00035-0_9

DIMENSIONS

https://app.dimensions.ai/details/publication/pub.1051786553


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": "Center for Industrial Mathematics, University of Bremen, 28359, Bremen, Germany", 
          "id": "http://www.grid.ac/institutes/grid.7704.4", 
          "name": [
            "Center for Industrial Mathematics, University of Bremen, 28359, Bremen, Germany"
          ], 
          "type": "Organization"
        }, 
        "familyName": "Kobarg", 
        "givenName": "Jan Hendrik", 
        "id": "sg:person.0775467771.25", 
        "sameAs": [
          "https://app.dimensions.ai/discover/publication?and_facet_researcher=ur.0775467771.25"
        ], 
        "type": "Person"
      }, 
      {
        "affiliation": {
          "alternateName": "Steinbeis Innovation Center SCiLS Research, 28211, Bremen, Germany", 
          "id": "http://www.grid.ac/institutes/None", 
          "name": [
            "Center for Industrial Mathematics, University of Bremen, 28359, Bremen, Germany", 
            "Steinbeis Innovation Center SCiLS Research, 28211, Bremen, Germany"
          ], 
          "type": "Organization"
        }, 
        "familyName": "Alexandrov", 
        "givenName": "Theodore", 
        "id": "sg:person.01204640152.10", 
        "sameAs": [
          "https://app.dimensions.ai/discover/publication?and_facet_researcher=ur.01204640152.10"
        ], 
        "type": "Person"
      }
    ], 
    "datePublished": "2013-07-16", 
    "datePublishedReg": "2013-07-16", 
    "description": "Segmentation of noisy hyper-spectral imaging data using clustering requires special algorithms. Such algorithms should consider spatial relations between the pixels, since neighbor pixels should usually be clustered into one group. However, in case of large spectral dimension (p), cluster algorithms suffer from the curse of dimensionality and have high memory requirements as well as long run-times. We propose to embed pixels from a window of w \u00d7w pixels to a feature space of dimension pw2. The effect of implicit denoising due to the window is controlled by weights depending on the spatial distance. We propose either using Gaussian weights or data-adaptive weights based on the similarity of pixels. Finally, any vectorial clustering algorithm, like k-means, can be applied in this feature space. Then, we use the FastMap algorithm for dimensionality reduction. The proposed algorithm is evaluated on a large simulated imaging mass spectrometry dataset.", 
    "editor": [
      {
        "familyName": "Lausen", 
        "givenName": "Berthold", 
        "type": "Person"
      }, 
      {
        "familyName": "Van den Poel", 
        "givenName": "Dirk", 
        "type": "Person"
      }, 
      {
        "familyName": "Ultsch", 
        "givenName": "Alfred", 
        "type": "Person"
      }
    ], 
    "genre": "chapter", 
    "id": "sg:pub.10.1007/978-3-319-00035-0_9", 
    "isAccessibleForFree": false, 
    "isPartOf": {
      "isbn": [
        "978-3-319-00034-3", 
        "978-3-319-00035-0"
      ], 
      "name": "Algorithms from and for Nature and Life", 
      "type": "Book"
    }, 
    "keywords": [
      "feature space", 
      "high memory requirements", 
      "similarity of pixels", 
      "curse of dimensionality", 
      "such algorithms", 
      "clustering algorithm", 
      "k-means", 
      "memory requirements", 
      "FastMap algorithm", 
      "dimensionality reduction", 
      "spatial segmentation", 
      "cluster algorithm", 
      "neighbor pixels", 
      "algorithm", 
      "mass spectrometry datasets", 
      "pixels", 
      "volume data", 
      "special algorithm", 
      "spatial relations", 
      "segmentation", 
      "data-adaptive weights", 
      "imaging data", 
      "Gaussian weight", 
      "spectral dimension", 
      "dataset", 
      "denoising", 
      "clustering", 
      "spatial distance", 
      "curse", 
      "dimensionality", 
      "space", 
      "requirements", 
      "window", 
      "data", 
      "similarity", 
      "distance", 
      "dimensions", 
      "weight", 
      "cases", 
      "relation", 
      "reduction", 
      "group", 
      "PW2", 
      "effect"
    ], 
    "name": "Efficient Spatial Segmentation of Hyper-spectral 3D Volume Data", 
    "pagination": "95-103", 
    "productId": [
      {
        "name": "dimensions_id", 
        "type": "PropertyValue", 
        "value": [
          "pub.1051786553"
        ]
      }, 
      {
        "name": "doi", 
        "type": "PropertyValue", 
        "value": [
          "10.1007/978-3-319-00035-0_9"
        ]
      }
    ], 
    "publisher": {
      "name": "Springer Nature", 
      "type": "Organisation"
    }, 
    "sameAs": [
      "https://doi.org/10.1007/978-3-319-00035-0_9", 
      "https://app.dimensions.ai/details/publication/pub.1051786553"
    ], 
    "sdDataset": "chapters", 
    "sdDatePublished": "2022-10-01T07:00", 
    "sdLicense": "https://scigraph.springernature.com/explorer/license/", 
    "sdPublisher": {
      "name": "Springer Nature - SN SciGraph project", 
      "type": "Organization"
    }, 
    "sdSource": "s3://com-springernature-scigraph/baseset/20221001/entities/gbq_results/chapter/chapter_67.jsonl", 
    "type": "Chapter", 
    "url": "https://doi.org/10.1007/978-3-319-00035-0_9"
  }
]
 

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.10.1007/978-3-319-00035-0_9'

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

curl -H 'Accept: application/n-triples' 'https://scigraph.springernature.com/pub.10.1007/978-3-319-00035-0_9'

Turtle is a human-readable linked data format.

curl -H 'Accept: text/turtle' 'https://scigraph.springernature.com/pub.10.1007/978-3-319-00035-0_9'

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

curl -H 'Accept: application/rdf+xml' 'https://scigraph.springernature.com/pub.10.1007/978-3-319-00035-0_9'


 

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

124 TRIPLES      22 PREDICATES      68 URIs      61 LITERALS      7 BLANK NODES

Subject Predicate Object
1 sg:pub.10.1007/978-3-319-00035-0_9 schema:about anzsrc-for:08
2 anzsrc-for:0801
3 schema:author Nb67d58b3aef44d8388551bc3a72bc17f
4 schema:datePublished 2013-07-16
5 schema:datePublishedReg 2013-07-16
6 schema:description Segmentation of noisy hyper-spectral imaging data using clustering requires special algorithms. Such algorithms should consider spatial relations between the pixels, since neighbor pixels should usually be clustered into one group. However, in case of large spectral dimension (p), cluster algorithms suffer from the curse of dimensionality and have high memory requirements as well as long run-times. We propose to embed pixels from a window of w ×w pixels to a feature space of dimension pw2. The effect of implicit denoising due to the window is controlled by weights depending on the spatial distance. We propose either using Gaussian weights or data-adaptive weights based on the similarity of pixels. Finally, any vectorial clustering algorithm, like k-means, can be applied in this feature space. Then, we use the FastMap algorithm for dimensionality reduction. The proposed algorithm is evaluated on a large simulated imaging mass spectrometry dataset.
7 schema:editor Na04f691fb3984ec7b68392baebe3b91f
8 schema:genre chapter
9 schema:isAccessibleForFree false
10 schema:isPartOf N131ac745697c4ad8a0bb56094ecc4d53
11 schema:keywords FastMap algorithm
12 Gaussian weight
13 PW2
14 algorithm
15 cases
16 cluster algorithm
17 clustering
18 clustering algorithm
19 curse
20 curse of dimensionality
21 data
22 data-adaptive weights
23 dataset
24 denoising
25 dimensionality
26 dimensionality reduction
27 dimensions
28 distance
29 effect
30 feature space
31 group
32 high memory requirements
33 imaging data
34 k-means
35 mass spectrometry datasets
36 memory requirements
37 neighbor pixels
38 pixels
39 reduction
40 relation
41 requirements
42 segmentation
43 similarity
44 similarity of pixels
45 space
46 spatial distance
47 spatial relations
48 spatial segmentation
49 special algorithm
50 spectral dimension
51 such algorithms
52 volume data
53 weight
54 window
55 schema:name Efficient Spatial Segmentation of Hyper-spectral 3D Volume Data
56 schema:pagination 95-103
57 schema:productId N48f8ea658b8c4260b8a48d65e050022e
58 Nf9c028f94dc244499fb45d178c4d37b4
59 schema:publisher N6bbf1dbaf1344ac6860e469cf7e45374
60 schema:sameAs https://app.dimensions.ai/details/publication/pub.1051786553
61 https://doi.org/10.1007/978-3-319-00035-0_9
62 schema:sdDatePublished 2022-10-01T07:00
63 schema:sdLicense https://scigraph.springernature.com/explorer/license/
64 schema:sdPublisher Nc5ddb26b6db94106a403f89c1bace0a3
65 schema:url https://doi.org/10.1007/978-3-319-00035-0_9
66 sgo:license sg:explorer/license/
67 sgo:sdDataset chapters
68 rdf:type schema:Chapter
69 N131ac745697c4ad8a0bb56094ecc4d53 schema:isbn 978-3-319-00034-3
70 978-3-319-00035-0
71 schema:name Algorithms from and for Nature and Life
72 rdf:type schema:Book
73 N48f8ea658b8c4260b8a48d65e050022e schema:name dimensions_id
74 schema:value pub.1051786553
75 rdf:type schema:PropertyValue
76 N5d19e168797f4cadbbe70b81173dd882 rdf:first sg:person.01204640152.10
77 rdf:rest rdf:nil
78 N6bbf1dbaf1344ac6860e469cf7e45374 schema:name Springer Nature
79 rdf:type schema:Organisation
80 N87eee22b02c1413c9e187cfe6c14a7c8 rdf:first Nbacf0f251180474d97712bedf6a93a7e
81 rdf:rest Nbde582e500ea4264b2b176cb095a3647
82 N8a26c0204a3f4fbebf2dc9405e65091f schema:familyName Lausen
83 schema:givenName Berthold
84 rdf:type schema:Person
85 Na04f691fb3984ec7b68392baebe3b91f rdf:first N8a26c0204a3f4fbebf2dc9405e65091f
86 rdf:rest N87eee22b02c1413c9e187cfe6c14a7c8
87 Nb67d58b3aef44d8388551bc3a72bc17f rdf:first sg:person.0775467771.25
88 rdf:rest N5d19e168797f4cadbbe70b81173dd882
89 Nbacf0f251180474d97712bedf6a93a7e schema:familyName Van den Poel
90 schema:givenName Dirk
91 rdf:type schema:Person
92 Nbde582e500ea4264b2b176cb095a3647 rdf:first Nd8c312312cc14d88be0b36c2c97c3c3f
93 rdf:rest rdf:nil
94 Nc5ddb26b6db94106a403f89c1bace0a3 schema:name Springer Nature - SN SciGraph project
95 rdf:type schema:Organization
96 Nd8c312312cc14d88be0b36c2c97c3c3f schema:familyName Ultsch
97 schema:givenName Alfred
98 rdf:type schema:Person
99 Nf9c028f94dc244499fb45d178c4d37b4 schema:name doi
100 schema:value 10.1007/978-3-319-00035-0_9
101 rdf:type schema:PropertyValue
102 anzsrc-for:08 schema:inDefinedTermSet anzsrc-for:
103 schema:name Information and Computing Sciences
104 rdf:type schema:DefinedTerm
105 anzsrc-for:0801 schema:inDefinedTermSet anzsrc-for:
106 schema:name Artificial Intelligence and Image Processing
107 rdf:type schema:DefinedTerm
108 sg:person.01204640152.10 schema:affiliation grid-institutes:None
109 schema:familyName Alexandrov
110 schema:givenName Theodore
111 schema:sameAs https://app.dimensions.ai/discover/publication?and_facet_researcher=ur.01204640152.10
112 rdf:type schema:Person
113 sg:person.0775467771.25 schema:affiliation grid-institutes:grid.7704.4
114 schema:familyName Kobarg
115 schema:givenName Jan Hendrik
116 schema:sameAs https://app.dimensions.ai/discover/publication?and_facet_researcher=ur.0775467771.25
117 rdf:type schema:Person
118 grid-institutes:None schema:alternateName Steinbeis Innovation Center SCiLS Research, 28211, Bremen, Germany
119 schema:name Center for Industrial Mathematics, University of Bremen, 28359, Bremen, Germany
120 Steinbeis Innovation Center SCiLS Research, 28211, Bremen, Germany
121 rdf:type schema:Organization
122 grid-institutes:grid.7704.4 schema:alternateName Center for Industrial Mathematics, University of Bremen, 28359, Bremen, Germany
123 schema:name Center for Industrial Mathematics, University of Bremen, 28359, Bremen, Germany
124 rdf:type schema:Organization
 




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


...