Extraction and recognition of artificial text in multimedia documents
Identifieur interne : 000552 ( PascalFrancis/Corpus ); précédent : 000551; suivant : 000553Extraction and recognition of artificial text in multimedia documents
Auteurs : C. Wolf ; J.-M. JolionSource :
- Pattern analysis and applications [ 1433-7541 ] ; 2004.
Descripteurs français
- Pascal (Inist)
English descriptors
- KwdEn :
Abstract
The systems currently available for content-based image and video retrieval work without semantic knowledge, i.e. they use image processing methods to extract low level features of the data. The similarity obtained by these approaches does not always correspond to the similarity a human user would expect. A way to include more semantic knowledge into the indexing process is to use the text included in the images and video sequences. It is rich in information but easy to use, e.g. by key word based queries. In this paper we present an algorithm to localise artificial text in images and videos using a measure of accumulated gradients and morphological processing. The quality of the localised text is improved by robust multiple frame integration. A new technique for the binarisation of the text boxes based on a criterion maximizing local contrast is proposed. Finally, detection and OCR results for a commercial OCR are presented, justifying the choice of the binarisation technique.
Notice en format standard (ISO 2709)
Pour connaître la documentation sur le format Inist Standard.
pA |
|
---|
Format Inist (serveur)
NO : | PASCAL 04-0205881 INIST |
---|---|
ET : | Extraction and recognition of artificial text in multimedia documents |
AU : | WOLF (C.); JOLION (J.-M.) |
AF : | Lyon Research Center for Images and Intelligent Information Systems, INSA de Lyon, Bat., Verne, 20, Av. Albert Einstein/69621 Villeurbanne/France (1 aut., 2 aut.) |
DT : | Publication en série; Niveau analytique |
SO : | Pattern analysis and applications; ISSN 1433-7541; Royaume-Uni; Da. 2004; Vol. 6; No. 4; Pp. 309-326; Bibl. 34 ref. |
LA : | Anglais |
EA : | The systems currently available for content-based image and video retrieval work without semantic knowledge, i.e. they use image processing methods to extract low level features of the data. The similarity obtained by these approaches does not always correspond to the similarity a human user would expect. A way to include more semantic knowledge into the indexing process is to use the text included in the images and video sequences. It is rich in information but easy to use, e.g. by key word based queries. In this paper we present an algorithm to localise artificial text in images and videos using a measure of accumulated gradients and morphological processing. The quality of the localised text is improved by robust multiple frame integration. A new technique for the binarisation of the text boxes based on a criterion maximizing local contrast is proposed. Finally, detection and OCR results for a commercial OCR are presented, justifying the choice of the binarisation technique. |
CC : | 001D02C02 |
FD : | Reconnaissance caractère; Multimédia; Signal vidéo; Traitement image; Similitude; Indexation; Texte; Séquence image; Utilisation information; Recherche par contenu; Sémantique; Homme; Choix; Extraction forme |
ED : | Character recognition; Multimedia; Video signal; Image processing; Similarity; Indexing; Text; Image sequence; Information use; Content-based retrieval; Semantics; Human; Choice; Pattern extraction |
SD : | Reconocimiento carácter; Multimedia; Señal video; Procesamiento imagen; Similitud; Indización; Texto; Secuencia imagen; Uso información; Semántica; Hombre; Elección; Extracción forma |
LO : | INIST-26865.354000115017570050 |
ID : | 04-0205881 |
Links to Exploration step
Pascal:04-0205881Le document en format XML
<record><TEI><teiHeader><fileDesc><titleStmt><title xml:lang="en" level="a">Extraction and recognition of artificial text in multimedia documents</title>
<author><name sortKey="Wolf, C" sort="Wolf, C" uniqKey="Wolf C" first="C." last="Wolf">C. Wolf</name>
<affiliation><inist:fA14 i1="01"><s1>Lyon Research Center for Images and Intelligent Information Systems, INSA de Lyon, Bat., Verne, 20, Av. Albert Einstein</s1>
<s2>69621 Villeurbanne</s2>
<s3>FRA</s3>
<sZ>1 aut.</sZ>
<sZ>2 aut.</sZ>
</inist:fA14>
</affiliation>
</author>
<author><name sortKey="Jolion, J M" sort="Jolion, J M" uniqKey="Jolion J" first="J.-M." last="Jolion">J.-M. Jolion</name>
<affiliation><inist:fA14 i1="01"><s1>Lyon Research Center for Images and Intelligent Information Systems, INSA de Lyon, Bat., Verne, 20, Av. Albert Einstein</s1>
<s2>69621 Villeurbanne</s2>
<s3>FRA</s3>
<sZ>1 aut.</sZ>
<sZ>2 aut.</sZ>
</inist:fA14>
</affiliation>
</author>
</titleStmt>
<publicationStmt><idno type="wicri:source">INIST</idno>
<idno type="inist">04-0205881</idno>
<date when="2004">2004</date>
<idno type="stanalyst">PASCAL 04-0205881 INIST</idno>
<idno type="RBID">Pascal:04-0205881</idno>
<idno type="wicri:Area/PascalFrancis/Corpus">000552</idno>
</publicationStmt>
<sourceDesc><biblStruct><analytic><title xml:lang="en" level="a">Extraction and recognition of artificial text in multimedia documents</title>
<author><name sortKey="Wolf, C" sort="Wolf, C" uniqKey="Wolf C" first="C." last="Wolf">C. Wolf</name>
<affiliation><inist:fA14 i1="01"><s1>Lyon Research Center for Images and Intelligent Information Systems, INSA de Lyon, Bat., Verne, 20, Av. Albert Einstein</s1>
<s2>69621 Villeurbanne</s2>
<s3>FRA</s3>
<sZ>1 aut.</sZ>
<sZ>2 aut.</sZ>
</inist:fA14>
</affiliation>
</author>
<author><name sortKey="Jolion, J M" sort="Jolion, J M" uniqKey="Jolion J" first="J.-M." last="Jolion">J.-M. Jolion</name>
<affiliation><inist:fA14 i1="01"><s1>Lyon Research Center for Images and Intelligent Information Systems, INSA de Lyon, Bat., Verne, 20, Av. Albert Einstein</s1>
<s2>69621 Villeurbanne</s2>
<s3>FRA</s3>
<sZ>1 aut.</sZ>
<sZ>2 aut.</sZ>
</inist:fA14>
</affiliation>
</author>
</analytic>
<series><title level="j" type="main">Pattern analysis and applications</title>
<idno type="ISSN">1433-7541</idno>
<imprint><date when="2004">2004</date>
</imprint>
</series>
</biblStruct>
</sourceDesc>
<seriesStmt><title level="j" type="main">Pattern analysis and applications</title>
<idno type="ISSN">1433-7541</idno>
</seriesStmt>
</fileDesc>
<profileDesc><textClass><keywords scheme="KwdEn" xml:lang="en"><term>Character recognition</term>
<term>Choice</term>
<term>Content-based retrieval</term>
<term>Human</term>
<term>Image processing</term>
<term>Image sequence</term>
<term>Indexing</term>
<term>Information use</term>
<term>Multimedia</term>
<term>Pattern extraction</term>
<term>Semantics</term>
<term>Similarity</term>
<term>Text</term>
<term>Video signal</term>
</keywords>
<keywords scheme="Pascal" xml:lang="fr"><term>Reconnaissance caractère</term>
<term>Multimédia</term>
<term>Signal vidéo</term>
<term>Traitement image</term>
<term>Similitude</term>
<term>Indexation</term>
<term>Texte</term>
<term>Séquence image</term>
<term>Utilisation information</term>
<term>Recherche par contenu</term>
<term>Sémantique</term>
<term>Homme</term>
<term>Choix</term>
<term>Extraction forme</term>
</keywords>
</textClass>
</profileDesc>
</teiHeader>
<front><div type="abstract" xml:lang="en">The systems currently available for content-based image and video retrieval work without semantic knowledge, i.e. they use image processing methods to extract low level features of the data. The similarity obtained by these approaches does not always correspond to the similarity a human user would expect. A way to include more semantic knowledge into the indexing process is to use the text included in the images and video sequences. It is rich in information but easy to use, e.g. by key word based queries. In this paper we present an algorithm to localise artificial text in images and videos using a measure of accumulated gradients and morphological processing. The quality of the localised text is improved by robust multiple frame integration. A new technique for the binarisation of the text boxes based on a criterion maximizing local contrast is proposed. Finally, detection and OCR results for a commercial OCR are presented, justifying the choice of the binarisation technique.</div>
</front>
</TEI>
<inist><standard h6="B"><pA><fA01 i1="01" i2="2"><s0>1433-7541</s0>
</fA01>
<fA05><s2>6</s2>
</fA05>
<fA06><s2>4</s2>
</fA06>
<fA08 i1="01" i2="1" l="ENG"><s1>Extraction and recognition of artificial text in multimedia documents</s1>
</fA08>
<fA11 i1="01" i2="1"><s1>WOLF (C.)</s1>
</fA11>
<fA11 i1="02" i2="1"><s1>JOLION (J.-M.)</s1>
</fA11>
<fA14 i1="01"><s1>Lyon Research Center for Images and Intelligent Information Systems, INSA de Lyon, Bat., Verne, 20, Av. Albert Einstein</s1>
<s2>69621 Villeurbanne</s2>
<s3>FRA</s3>
<sZ>1 aut.</sZ>
<sZ>2 aut.</sZ>
</fA14>
<fA20><s1>309-326</s1>
</fA20>
<fA21><s1>2004</s1>
</fA21>
<fA23 i1="01"><s0>ENG</s0>
</fA23>
<fA43 i1="01"><s1>INIST</s1>
<s2>26865</s2>
<s5>354000115017570050</s5>
</fA43>
<fA44><s0>0000</s0>
<s1>© 2004 INIST-CNRS. All rights reserved.</s1>
</fA44>
<fA45><s0>34 ref.</s0>
</fA45>
<fA47 i1="01" i2="1"><s0>04-0205881</s0>
</fA47>
<fA60><s1>P</s1>
</fA60>
<fA61><s0>A</s0>
</fA61>
<fA64 i1="01" i2="2"><s0>Pattern analysis and applications</s0>
</fA64>
<fA66 i1="01"><s0>GBR</s0>
</fA66>
<fC01 i1="01" l="ENG"><s0>The systems currently available for content-based image and video retrieval work without semantic knowledge, i.e. they use image processing methods to extract low level features of the data. The similarity obtained by these approaches does not always correspond to the similarity a human user would expect. A way to include more semantic knowledge into the indexing process is to use the text included in the images and video sequences. It is rich in information but easy to use, e.g. by key word based queries. In this paper we present an algorithm to localise artificial text in images and videos using a measure of accumulated gradients and morphological processing. The quality of the localised text is improved by robust multiple frame integration. A new technique for the binarisation of the text boxes based on a criterion maximizing local contrast is proposed. Finally, detection and OCR results for a commercial OCR are presented, justifying the choice of the binarisation technique.</s0>
</fC01>
<fC02 i1="01" i2="X"><s0>001D02C02</s0>
</fC02>
<fC03 i1="01" i2="X" l="FRE"><s0>Reconnaissance caractère</s0>
<s5>09</s5>
</fC03>
<fC03 i1="01" i2="X" l="ENG"><s0>Character recognition</s0>
<s5>09</s5>
</fC03>
<fC03 i1="01" i2="X" l="SPA"><s0>Reconocimiento carácter</s0>
<s5>09</s5>
</fC03>
<fC03 i1="02" i2="X" l="FRE"><s0>Multimédia</s0>
<s5>10</s5>
</fC03>
<fC03 i1="02" i2="X" l="ENG"><s0>Multimedia</s0>
<s5>10</s5>
</fC03>
<fC03 i1="02" i2="X" l="SPA"><s0>Multimedia</s0>
<s5>10</s5>
</fC03>
<fC03 i1="03" i2="X" l="FRE"><s0>Signal vidéo</s0>
<s5>11</s5>
</fC03>
<fC03 i1="03" i2="X" l="ENG"><s0>Video signal</s0>
<s5>11</s5>
</fC03>
<fC03 i1="03" i2="X" l="SPA"><s0>Señal video</s0>
<s5>11</s5>
</fC03>
<fC03 i1="04" i2="X" l="FRE"><s0>Traitement image</s0>
<s5>12</s5>
</fC03>
<fC03 i1="04" i2="X" l="ENG"><s0>Image processing</s0>
<s5>12</s5>
</fC03>
<fC03 i1="04" i2="X" l="SPA"><s0>Procesamiento imagen</s0>
<s5>12</s5>
</fC03>
<fC03 i1="05" i2="X" l="FRE"><s0>Similitude</s0>
<s5>13</s5>
</fC03>
<fC03 i1="05" i2="X" l="ENG"><s0>Similarity</s0>
<s5>13</s5>
</fC03>
<fC03 i1="05" i2="X" l="SPA"><s0>Similitud</s0>
<s5>13</s5>
</fC03>
<fC03 i1="06" i2="X" l="FRE"><s0>Indexation</s0>
<s5>14</s5>
</fC03>
<fC03 i1="06" i2="X" l="ENG"><s0>Indexing</s0>
<s5>14</s5>
</fC03>
<fC03 i1="06" i2="X" l="SPA"><s0>Indización</s0>
<s5>14</s5>
</fC03>
<fC03 i1="07" i2="X" l="FRE"><s0>Texte</s0>
<s5>15</s5>
</fC03>
<fC03 i1="07" i2="X" l="ENG"><s0>Text</s0>
<s5>15</s5>
</fC03>
<fC03 i1="07" i2="X" l="SPA"><s0>Texto</s0>
<s5>15</s5>
</fC03>
<fC03 i1="08" i2="X" l="FRE"><s0>Séquence image</s0>
<s5>16</s5>
</fC03>
<fC03 i1="08" i2="X" l="ENG"><s0>Image sequence</s0>
<s5>16</s5>
</fC03>
<fC03 i1="08" i2="X" l="SPA"><s0>Secuencia imagen</s0>
<s5>16</s5>
</fC03>
<fC03 i1="09" i2="X" l="FRE"><s0>Utilisation information</s0>
<s5>17</s5>
</fC03>
<fC03 i1="09" i2="X" l="ENG"><s0>Information use</s0>
<s5>17</s5>
</fC03>
<fC03 i1="09" i2="X" l="SPA"><s0>Uso información</s0>
<s5>17</s5>
</fC03>
<fC03 i1="10" i2="3" l="FRE"><s0>Recherche par contenu</s0>
<s5>18</s5>
</fC03>
<fC03 i1="10" i2="3" l="ENG"><s0>Content-based retrieval</s0>
<s5>18</s5>
</fC03>
<fC03 i1="11" i2="X" l="FRE"><s0>Sémantique</s0>
<s5>19</s5>
</fC03>
<fC03 i1="11" i2="X" l="ENG"><s0>Semantics</s0>
<s5>19</s5>
</fC03>
<fC03 i1="11" i2="X" l="SPA"><s0>Semántica</s0>
<s5>19</s5>
</fC03>
<fC03 i1="12" i2="X" l="FRE"><s0>Homme</s0>
<s5>20</s5>
</fC03>
<fC03 i1="12" i2="X" l="ENG"><s0>Human</s0>
<s5>20</s5>
</fC03>
<fC03 i1="12" i2="X" l="SPA"><s0>Hombre</s0>
<s5>20</s5>
</fC03>
<fC03 i1="13" i2="X" l="FRE"><s0>Choix</s0>
<s5>21</s5>
</fC03>
<fC03 i1="13" i2="X" l="ENG"><s0>Choice</s0>
<s5>21</s5>
</fC03>
<fC03 i1="13" i2="X" l="SPA"><s0>Elección</s0>
<s5>21</s5>
</fC03>
<fC03 i1="14" i2="X" l="FRE"><s0>Extraction forme</s0>
<s5>23</s5>
</fC03>
<fC03 i1="14" i2="X" l="ENG"><s0>Pattern extraction</s0>
<s5>23</s5>
</fC03>
<fC03 i1="14" i2="X" l="SPA"><s0>Extracción forma</s0>
<s5>23</s5>
</fC03>
<fN21><s1>138</s1>
</fN21>
<fN82><s1>OTO</s1>
</fN82>
</pA>
</standard>
<server><NO>PASCAL 04-0205881 INIST</NO>
<ET>Extraction and recognition of artificial text in multimedia documents</ET>
<AU>WOLF (C.); JOLION (J.-M.)</AU>
<AF>Lyon Research Center for Images and Intelligent Information Systems, INSA de Lyon, Bat., Verne, 20, Av. Albert Einstein/69621 Villeurbanne/France (1 aut., 2 aut.)</AF>
<DT>Publication en série; Niveau analytique</DT>
<SO>Pattern analysis and applications; ISSN 1433-7541; Royaume-Uni; Da. 2004; Vol. 6; No. 4; Pp. 309-326; Bibl. 34 ref.</SO>
<LA>Anglais</LA>
<EA>The systems currently available for content-based image and video retrieval work without semantic knowledge, i.e. they use image processing methods to extract low level features of the data. The similarity obtained by these approaches does not always correspond to the similarity a human user would expect. A way to include more semantic knowledge into the indexing process is to use the text included in the images and video sequences. It is rich in information but easy to use, e.g. by key word based queries. In this paper we present an algorithm to localise artificial text in images and videos using a measure of accumulated gradients and morphological processing. The quality of the localised text is improved by robust multiple frame integration. A new technique for the binarisation of the text boxes based on a criterion maximizing local contrast is proposed. Finally, detection and OCR results for a commercial OCR are presented, justifying the choice of the binarisation technique.</EA>
<CC>001D02C02</CC>
<FD>Reconnaissance caractère; Multimédia; Signal vidéo; Traitement image; Similitude; Indexation; Texte; Séquence image; Utilisation information; Recherche par contenu; Sémantique; Homme; Choix; Extraction forme</FD>
<ED>Character recognition; Multimedia; Video signal; Image processing; Similarity; Indexing; Text; Image sequence; Information use; Content-based retrieval; Semantics; Human; Choice; Pattern extraction</ED>
<SD>Reconocimiento carácter; Multimedia; Señal video; Procesamiento imagen; Similitud; Indización; Texto; Secuencia imagen; Uso información; Semántica; Hombre; Elección; Extracción forma</SD>
<LO>INIST-26865.354000115017570050</LO>
<ID>04-0205881</ID>
</server>
</inist>
</record>
Pour manipuler ce document sous Unix (Dilib)
EXPLOR_STEP=$WICRI_ROOT/Ticri/CIDE/explor/OcrV1/Data/PascalFrancis/Corpus
HfdSelect -h $EXPLOR_STEP/biblio.hfd -nk 000552 | SxmlIndent | more
Ou
HfdSelect -h $EXPLOR_AREA/Data/PascalFrancis/Corpus/biblio.hfd -nk 000552 | SxmlIndent | more
Pour mettre un lien sur cette page dans le réseau Wicri
{{Explor lien |wiki= Ticri/CIDE |area= OcrV1 |flux= PascalFrancis |étape= Corpus |type= RBID |clé= Pascal:04-0205881 |texte= Extraction and recognition of artificial text in multimedia documents }}
![]() | This area was generated with Dilib version V0.6.32. | ![]() |