Logo and Text Removal for Medical Image Retrieval View Full Text


Ontology type: schema:Chapter     


Chapter Info

DATE

2005-01-01

AUTHORS

Henning Müller , Joris Heuberger , Antoine Geissbuhler

ABSTRACT

The amount of visual medical information being produced in large hospitals is exploding. Most University hospitals produce Millions of images per year (Geneva Radiology: 20'000 images per day). Currently, the access to these images is most often limited to an access by patient identification. Sometimes search by text in the radiology report or in the DICOM headers is possible. Still, all the implicit information potentially available through the image and the accompanying case report is discarded in this case. Content—based visual data access is based on direct visual properties of the images that are extracted automatically from all images in a database. This delivers objective features for searching images but the features are commonly on a very low semantic level (colour histograms, simple texture analysis such as wavelet filter responses). Another problem that especially occurs in medical teaching files but also in routine images is text and logos around the main object in the image. For retrieval this is mainly noise that can have a negative influence on retrieval quality. In our approach, we extract the main object from the image by removing logos that are added to the images as well as frames around the images and text fields or other elements that are not needed. This is mainly based on properties of the text that occurs on the images, and especially of the logo of the university hospitals of Geneva. Frames around the images are removed reliably. First results show that the retrieval quality can be augmented well with such an approach. Especially queries with relevance feedback deliver much better results as the query is more focused. Proper, quantitative evaluation on a large data set is still missing but will be performed shortly. More... »

PAGES

35-39

Identifiers

URI

http://scigraph.springernature.com/pub.10.1007/3-540-26431-0_8

DOI

http://dx.doi.org/10.1007/3-540-26431-0_8

DIMENSIONS

https://app.dimensions.ai/details/publication/pub.1037691323


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"
      }, 
      {
        "id": "http://purl.org/au-research/vocabulary/anzsrc-for/2008/0806", 
        "inDefinedTermSet": "http://purl.org/au-research/vocabulary/anzsrc-for/2008/", 
        "name": "Information Systems", 
        "type": "DefinedTerm"
      }
    ], 
    "author": [
      {
        "affiliation": {
          "alternateName": "University and University Hospitals of Geneva, 24, Rue Micheli-du-Crest, 1211, Geneva 14, Switzerland", 
          "id": "http://www.grid.ac/institutes/grid.150338.c", 
          "name": [
            "University and University Hospitals of Geneva, 24, Rue Micheli-du-Crest, 1211, Geneva 14, Switzerland"
          ], 
          "type": "Organization"
        }, 
        "familyName": "M\u00fcller", 
        "givenName": "Henning", 
        "id": "sg:person.07552063233.67", 
        "sameAs": [
          "https://app.dimensions.ai/discover/publication?and_facet_researcher=ur.07552063233.67"
        ], 
        "type": "Person"
      }, 
      {
        "affiliation": {
          "alternateName": "University and University Hospitals of Geneva, 24, Rue Micheli-du-Crest, 1211, Geneva 14, Switzerland", 
          "id": "http://www.grid.ac/institutes/grid.150338.c", 
          "name": [
            "University and University Hospitals of Geneva, 24, Rue Micheli-du-Crest, 1211, Geneva 14, Switzerland"
          ], 
          "type": "Organization"
        }, 
        "familyName": "Heuberger", 
        "givenName": "Joris", 
        "id": "sg:person.0577112016.65", 
        "sameAs": [
          "https://app.dimensions.ai/discover/publication?and_facet_researcher=ur.0577112016.65"
        ], 
        "type": "Person"
      }, 
      {
        "affiliation": {
          "alternateName": "University and University Hospitals of Geneva, 24, Rue Micheli-du-Crest, 1211, Geneva 14, Switzerland", 
          "id": "http://www.grid.ac/institutes/grid.150338.c", 
          "name": [
            "University and University Hospitals of Geneva, 24, Rue Micheli-du-Crest, 1211, Geneva 14, Switzerland"
          ], 
          "type": "Organization"
        }, 
        "familyName": "Geissbuhler", 
        "givenName": "Antoine", 
        "id": "sg:person.0600360343.20", 
        "sameAs": [
          "https://app.dimensions.ai/discover/publication?and_facet_researcher=ur.0600360343.20"
        ], 
        "type": "Person"
      }
    ], 
    "datePublished": "2005-01-01", 
    "datePublishedReg": "2005-01-01", 
    "description": "The amount of visual medical information being produced in large hospitals is exploding. Most University hospitals produce Millions of images per year (Geneva Radiology: 20'000 images per day). Currently, the access to these images is most often limited to an access by patient identification. Sometimes search by text in the radiology report or in the DICOM headers is possible. Still, all the implicit information potentially available through the image and the accompanying case report is discarded in this case. Content\u2014based visual data access is based on direct visual properties of the images that are extracted automatically from all images in a database. This delivers objective features for searching images but the features are commonly on a very low semantic level (colour histograms, simple texture analysis such as wavelet filter responses). Another problem that especially occurs in medical teaching files but also in routine images is text and logos around the main object in the image. For retrieval this is mainly noise that can have a negative influence on retrieval quality. In our approach, we extract the main object from the image by removing logos that are added to the images as well as frames around the images and text fields or other elements that are not needed. This is mainly based on properties of the text that occurs on the images, and especially of the logo of the university hospitals of Geneva. Frames around the images are removed reliably. First results show that the retrieval quality can be augmented well with such an approach. Especially queries with relevance feedback deliver much better results as the query is more focused. Proper, quantitative evaluation on a large data set is still missing but will be performed shortly.", 
    "editor": [
      {
        "familyName": "Meinzer", 
        "givenName": "Hans-Peter", 
        "type": "Person"
      }, 
      {
        "familyName": "Handels", 
        "givenName": "Heinz", 
        "type": "Person"
      }, 
      {
        "familyName": "Horsch", 
        "givenName": "Alexander", 
        "type": "Person"
      }, 
      {
        "familyName": "Tolxdorff", 
        "givenName": "Thomas", 
        "type": "Person"
      }
    ], 
    "genre": "chapter", 
    "id": "sg:pub.10.1007/3-540-26431-0_8", 
    "inLanguage": "en", 
    "isAccessibleForFree": false, 
    "isPartOf": {
      "isbn": [
        "978-3-540-25052-4", 
        "978-3-540-26431-6"
      ], 
      "name": "Bildverarbeitung f\u00fcr die Medizin 2005", 
      "type": "Book"
    }, 
    "keywords": [
      "retrieval quality", 
      "low semantic level", 
      "medical image retrieval", 
      "millions of images", 
      "visual medical information", 
      "large data sets", 
      "image retrieval", 
      "relevance feedback", 
      "most university hospitals", 
      "data access", 
      "text removal", 
      "implicit information", 
      "semantic level", 
      "text fields", 
      "teaching files", 
      "DICOM header", 
      "medical information", 
      "queries", 
      "visual properties", 
      "routine images", 
      "data sets", 
      "images", 
      "retrieval", 
      "radiology reports", 
      "patient identification", 
      "objects", 
      "logos", 
      "access", 
      "good results", 
      "main object", 
      "text", 
      "information", 
      "header", 
      "quantitative evaluation", 
      "frame", 
      "files", 
      "objective features", 
      "features", 
      "database", 
      "first results", 
      "quality", 
      "set", 
      "noise", 
      "millions", 
      "feedback", 
      "large hospitals", 
      "results", 
      "evaluation", 
      "identification", 
      "field", 
      "elements", 
      "amount", 
      "cases", 
      "negative influence", 
      "properties", 
      "levels", 
      "Geneva", 
      "years", 
      "report", 
      "hospital", 
      "University Hospital", 
      "influence", 
      "removal", 
      "approach", 
      "problem", 
      "case report", 
      "Content\u2014based visual data access", 
      "visual data access", 
      "direct visual properties", 
      "medical teaching files"
    ], 
    "name": "Logo and Text Removal for Medical Image Retrieval", 
    "pagination": "35-39", 
    "productId": [
      {
        "name": "dimensions_id", 
        "type": "PropertyValue", 
        "value": [
          "pub.1037691323"
        ]
      }, 
      {
        "name": "doi", 
        "type": "PropertyValue", 
        "value": [
          "10.1007/3-540-26431-0_8"
        ]
      }
    ], 
    "publisher": {
      "name": "Springer Nature", 
      "type": "Organisation"
    }, 
    "sameAs": [
      "https://doi.org/10.1007/3-540-26431-0_8", 
      "https://app.dimensions.ai/details/publication/pub.1037691323"
    ], 
    "sdDataset": "chapters", 
    "sdDatePublished": "2021-11-01T18:53", 
    "sdLicense": "https://scigraph.springernature.com/explorer/license/", 
    "sdPublisher": {
      "name": "Springer Nature - SN SciGraph project", 
      "type": "Organization"
    }, 
    "sdSource": "s3://com-springernature-scigraph/baseset/20211101/entities/gbq_results/chapter/chapter_274.jsonl", 
    "type": "Chapter", 
    "url": "https://doi.org/10.1007/3-540-26431-0_8"
  }
]
 

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.10.1007/3-540-26431-0_8'

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

curl -H 'Accept: application/n-triples' 'https://scigraph.springernature.com/pub.10.1007/3-540-26431-0_8'

Turtle is a human-readable linked data format.

curl -H 'Accept: text/turtle' 'https://scigraph.springernature.com/pub.10.1007/3-540-26431-0_8'

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

curl -H 'Accept: application/rdf+xml' 'https://scigraph.springernature.com/pub.10.1007/3-540-26431-0_8'


 

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

163 TRIPLES      23 PREDICATES      96 URIs      88 LITERALS      7 BLANK NODES

Subject Predicate Object
1 sg:pub.10.1007/3-540-26431-0_8 schema:about anzsrc-for:08
2 anzsrc-for:0801
3 anzsrc-for:0806
4 schema:author Neab61f5a6f214146820e5dee31b3525d
5 schema:datePublished 2005-01-01
6 schema:datePublishedReg 2005-01-01
7 schema:description The amount of visual medical information being produced in large hospitals is exploding. Most University hospitals produce Millions of images per year (Geneva Radiology: 20'000 images per day). Currently, the access to these images is most often limited to an access by patient identification. Sometimes search by text in the radiology report or in the DICOM headers is possible. Still, all the implicit information potentially available through the image and the accompanying case report is discarded in this case. Content—based visual data access is based on direct visual properties of the images that are extracted automatically from all images in a database. This delivers objective features for searching images but the features are commonly on a very low semantic level (colour histograms, simple texture analysis such as wavelet filter responses). Another problem that especially occurs in medical teaching files but also in routine images is text and logos around the main object in the image. For retrieval this is mainly noise that can have a negative influence on retrieval quality. In our approach, we extract the main object from the image by removing logos that are added to the images as well as frames around the images and text fields or other elements that are not needed. This is mainly based on properties of the text that occurs on the images, and especially of the logo of the university hospitals of Geneva. Frames around the images are removed reliably. First results show that the retrieval quality can be augmented well with such an approach. Especially queries with relevance feedback deliver much better results as the query is more focused. Proper, quantitative evaluation on a large data set is still missing but will be performed shortly.
8 schema:editor Na0da8c51831d4bc880b1929cd4098b76
9 schema:genre chapter
10 schema:inLanguage en
11 schema:isAccessibleForFree false
12 schema:isPartOf N86a6372488444b49be881eca48f2f8f8
13 schema:keywords Content—based visual data access
14 DICOM header
15 Geneva
16 University Hospital
17 access
18 amount
19 approach
20 case report
21 cases
22 data access
23 data sets
24 database
25 direct visual properties
26 elements
27 evaluation
28 features
29 feedback
30 field
31 files
32 first results
33 frame
34 good results
35 header
36 hospital
37 identification
38 image retrieval
39 images
40 implicit information
41 influence
42 information
43 large data sets
44 large hospitals
45 levels
46 logos
47 low semantic level
48 main object
49 medical image retrieval
50 medical information
51 medical teaching files
52 millions
53 millions of images
54 most university hospitals
55 negative influence
56 noise
57 objective features
58 objects
59 patient identification
60 problem
61 properties
62 quality
63 quantitative evaluation
64 queries
65 radiology reports
66 relevance feedback
67 removal
68 report
69 results
70 retrieval
71 retrieval quality
72 routine images
73 semantic level
74 set
75 teaching files
76 text
77 text fields
78 text removal
79 visual data access
80 visual medical information
81 visual properties
82 years
83 schema:name Logo and Text Removal for Medical Image Retrieval
84 schema:pagination 35-39
85 schema:productId N2f89a0c48fc141c9be193fff706e774d
86 Nb28bf09f1428474bb88edc6743923ecb
87 schema:publisher N8282458acc404680b26da052cf658557
88 schema:sameAs https://app.dimensions.ai/details/publication/pub.1037691323
89 https://doi.org/10.1007/3-540-26431-0_8
90 schema:sdDatePublished 2021-11-01T18:53
91 schema:sdLicense https://scigraph.springernature.com/explorer/license/
92 schema:sdPublisher Nb97f29128bff4883ae09d95fa357aec8
93 schema:url https://doi.org/10.1007/3-540-26431-0_8
94 sgo:license sg:explorer/license/
95 sgo:sdDataset chapters
96 rdf:type schema:Chapter
97 N062781a6670644b6b848cc1493655e82 rdf:first sg:person.0600360343.20
98 rdf:rest rdf:nil
99 N208bacabaf214edab9b272729dd49a3d rdf:first N2875383cbf5d403db2ffd2268a26c324
100 rdf:rest rdf:nil
101 N2875383cbf5d403db2ffd2268a26c324 schema:familyName Tolxdorff
102 schema:givenName Thomas
103 rdf:type schema:Person
104 N2f89a0c48fc141c9be193fff706e774d schema:name doi
105 schema:value 10.1007/3-540-26431-0_8
106 rdf:type schema:PropertyValue
107 N434187ff92744011b6af65d80acc0dcf rdf:first Nb6d20a37c3a64dbb8a52c696cbd44ac5
108 rdf:rest N692a1b8978214eada9f070887df6a3d7
109 N59edde5db4084499abd21e33dd2cf37e schema:familyName Meinzer
110 schema:givenName Hans-Peter
111 rdf:type schema:Person
112 N692a1b8978214eada9f070887df6a3d7 rdf:first N97356771b04848329dc5704e482f2584
113 rdf:rest N208bacabaf214edab9b272729dd49a3d
114 N8282458acc404680b26da052cf658557 schema:name Springer Nature
115 rdf:type schema:Organisation
116 N86a6372488444b49be881eca48f2f8f8 schema:isbn 978-3-540-25052-4
117 978-3-540-26431-6
118 schema:name Bildverarbeitung für die Medizin 2005
119 rdf:type schema:Book
120 N97356771b04848329dc5704e482f2584 schema:familyName Horsch
121 schema:givenName Alexander
122 rdf:type schema:Person
123 Na0da8c51831d4bc880b1929cd4098b76 rdf:first N59edde5db4084499abd21e33dd2cf37e
124 rdf:rest N434187ff92744011b6af65d80acc0dcf
125 Nb28bf09f1428474bb88edc6743923ecb schema:name dimensions_id
126 schema:value pub.1037691323
127 rdf:type schema:PropertyValue
128 Nb6d20a37c3a64dbb8a52c696cbd44ac5 schema:familyName Handels
129 schema:givenName Heinz
130 rdf:type schema:Person
131 Nb97f29128bff4883ae09d95fa357aec8 schema:name Springer Nature - SN SciGraph project
132 rdf:type schema:Organization
133 Ndca7eb917b8d4566b9ed1c43791672d5 rdf:first sg:person.0577112016.65
134 rdf:rest N062781a6670644b6b848cc1493655e82
135 Neab61f5a6f214146820e5dee31b3525d rdf:first sg:person.07552063233.67
136 rdf:rest Ndca7eb917b8d4566b9ed1c43791672d5
137 anzsrc-for:08 schema:inDefinedTermSet anzsrc-for:
138 schema:name Information and Computing Sciences
139 rdf:type schema:DefinedTerm
140 anzsrc-for:0801 schema:inDefinedTermSet anzsrc-for:
141 schema:name Artificial Intelligence and Image Processing
142 rdf:type schema:DefinedTerm
143 anzsrc-for:0806 schema:inDefinedTermSet anzsrc-for:
144 schema:name Information Systems
145 rdf:type schema:DefinedTerm
146 sg:person.0577112016.65 schema:affiliation grid-institutes:grid.150338.c
147 schema:familyName Heuberger
148 schema:givenName Joris
149 schema:sameAs https://app.dimensions.ai/discover/publication?and_facet_researcher=ur.0577112016.65
150 rdf:type schema:Person
151 sg:person.0600360343.20 schema:affiliation grid-institutes:grid.150338.c
152 schema:familyName Geissbuhler
153 schema:givenName Antoine
154 schema:sameAs https://app.dimensions.ai/discover/publication?and_facet_researcher=ur.0600360343.20
155 rdf:type schema:Person
156 sg:person.07552063233.67 schema:affiliation grid-institutes:grid.150338.c
157 schema:familyName Müller
158 schema:givenName Henning
159 schema:sameAs https://app.dimensions.ai/discover/publication?and_facet_researcher=ur.07552063233.67
160 rdf:type schema:Person
161 grid-institutes:grid.150338.c schema:alternateName University and University Hospitals of Geneva, 24, Rue Micheli-du-Crest, 1211, Geneva 14, Switzerland
162 schema:name University and University Hospitals of Geneva, 24, Rue Micheli-du-Crest, 1211, Geneva 14, Switzerland
163 rdf:type schema:Organization
 




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


...