Page segmentation and identification for intelligent signal processing
Identifieur interne : 002B01 ( Main/Merge ); précédent : 002B00; suivant : 002B02Page segmentation and identification for intelligent signal processing
Auteurs : Kuo-Chin Fan [République populaire de Chine, Taïwan] ; Liang-Shen Wang [République populaire de Chine] ; Yuan-Kai Wang [République populaire de Chine]Source :
- Signal Processing [ 0165-1684 ] ; 1994.
Abstract
Document analysis plays an important role in office automation, especially in intelligent signal processing. In this paper, we propose an intelligent document analysis system to achieve the document segmentation and identification goal. The proposed system consists of two modules: block segmentation and block identification. In our approach, we first segment a document into several non-overlapping blocks by utilizing a novel recursive segmentation technique, then extract the features embedded in each segmented block. Two kinds of features, connectivity histogram and multiresolution features, are extracted. The features are verified to be effective in characterizing document blocks. Last, a two-layer perceptron is adopted in the identification module to determine the identity of the considered block. Experiments with a wide varity of documents verify the feasibility of our approach.
Url:
DOI: 10.1016/0165-1684(95)00061-H
Links toward previous steps (curation, corpus...)
- to stream Istex, to step Corpus: 000910
- to stream Istex, to step Curation: 000900
- to stream Istex, to step Checkpoint: 001D01
Links to Exploration step
ISTEX:F54A35D32E2414C90B68141D4EDE9A2FBA0C02F1Le document en format XML
<record><TEI wicri:istexFullTextTei="biblStruct"><teiHeader><fileDesc><titleStmt><title>Page segmentation and identification for intelligent signal processing</title><author><name sortKey="Fan, Kuo Chin" sort="Fan, Kuo Chin" uniqKey="Fan K" first="Kuo-Chin" last="Fan">Kuo-Chin Fan</name></author><author><name sortKey="Wang, Liang Shen" sort="Wang, Liang Shen" uniqKey="Wang L" first="Liang-Shen" last="Wang">Liang-Shen Wang</name></author><author><name sortKey="Wang, Yuan Kai" sort="Wang, Yuan Kai" uniqKey="Wang Y" first="Yuan-Kai" last="Wang">Yuan-Kai Wang</name></author></titleStmt><publicationStmt><idno type="wicri:source">ISTEX</idno><idno type="RBID">ISTEX:F54A35D32E2414C90B68141D4EDE9A2FBA0C02F1</idno><date when="1995" year="1995">1995</date><idno type="doi">10.1016/0165-1684(95)00061-H</idno><idno type="url">https://api.istex.fr/document/F54A35D32E2414C90B68141D4EDE9A2FBA0C02F1/fulltext/pdf</idno><idno type="wicri:Area/Istex/Corpus">000910</idno><idno type="wicri:Area/Istex/Curation">000900</idno><idno type="wicri:Area/Istex/Checkpoint">001D01</idno><idno type="wicri:doubleKey">0165-1684:1995:Fan K:page:segmentation:and</idno><idno type="wicri:Area/Main/Merge">002B01</idno></publicationStmt><sourceDesc><biblStruct><analytic><title level="a">Page segmentation and identification for intelligent signal processing</title><author><name sortKey="Fan, Kuo Chin" sort="Fan, Kuo Chin" uniqKey="Fan K" first="Kuo-Chin" last="Fan">Kuo-Chin Fan</name><affiliation wicri:level="1"><country xml:lang="fr" wicri:curation="lc">République populaire de Chine</country><wicri:regionArea>Institute of Computer Science and Information Engineering, National Central University, Chung-Li, Taiwan 320</wicri:regionArea><wicri:noRegion>Taiwan 320</wicri:noRegion></affiliation><affiliation wicri:level="1"><country wicri:rule="url">Taïwan</country></affiliation></author><author><name sortKey="Wang, Liang Shen" sort="Wang, Liang Shen" uniqKey="Wang L" first="Liang-Shen" last="Wang">Liang-Shen Wang</name><affiliation wicri:level="1"><country xml:lang="fr" wicri:curation="lc">République populaire de Chine</country><wicri:regionArea>Institute of Computer Science and Information Engineering, National Central University, Chung-Li, Taiwan 320</wicri:regionArea><wicri:noRegion>Taiwan 320</wicri:noRegion></affiliation></author><author><name sortKey="Wang, Yuan Kai" sort="Wang, Yuan Kai" uniqKey="Wang Y" first="Yuan-Kai" last="Wang">Yuan-Kai Wang</name><affiliation wicri:level="1"><country xml:lang="fr" wicri:curation="lc">République populaire de Chine</country><wicri:regionArea>Institute of Computer Science and Information Engineering, National Central University, Chung-Li, Taiwan 320</wicri:regionArea><wicri:noRegion>Taiwan 320</wicri:noRegion></affiliation></author></analytic><monogr></monogr><series><title level="j">Signal Processing</title><title level="j" type="abbrev">SIGPRO</title><idno type="ISSN">0165-1684</idno><imprint><publisher>ELSEVIER</publisher><date type="published" when="1994">1994</date><biblScope unit="volume">45</biblScope><biblScope unit="issue">3</biblScope><biblScope unit="page" from="329">329</biblScope><biblScope unit="page" to="346">346</biblScope></imprint><idno type="ISSN">0165-1684</idno></series><idno type="istex">F54A35D32E2414C90B68141D4EDE9A2FBA0C02F1</idno><idno type="DOI">10.1016/0165-1684(95)00061-H</idno><idno type="PII">0165-1684(95)00061-H</idno></biblStruct></sourceDesc><seriesStmt><idno type="ISSN">0165-1684</idno></seriesStmt></fileDesc><profileDesc><textClass></textClass><langUsage><language ident="en">en</language></langUsage></profileDesc></teiHeader><front><div type="abstract" xml:lang="en">Document analysis plays an important role in office automation, especially in intelligent signal processing. In this paper, we propose an intelligent document analysis system to achieve the document segmentation and identification goal. The proposed system consists of two modules: block segmentation and block identification. In our approach, we first segment a document into several non-overlapping blocks by utilizing a novel recursive segmentation technique, then extract the features embedded in each segmented block. Two kinds of features, connectivity histogram and multiresolution features, are extracted. The features are verified to be effective in characterizing document blocks. Last, a two-layer perceptron is adopted in the identification module to determine the identity of the considered block. Experiments with a wide varity of documents verify the feasibility of our approach.</div></front></TEI></record>Pour manipuler ce document sous Unix (Dilib)
EXPLOR_STEP=$WICRI_ROOT/Ticri/CIDE/explor/OcrV1/Data/Main/Merge
HfdSelect -h $EXPLOR_STEP/biblio.hfd -nk 002B01 | SxmlIndent | more
Ou
HfdSelect -h $EXPLOR_AREA/Data/Main/Merge/biblio.hfd -nk 002B01 | SxmlIndent | more
Pour mettre un lien sur cette page dans le réseau Wicri
{{Explor lien
|wiki= Ticri/CIDE
|area= OcrV1
|flux= Main
|étape= Merge
|type= RBID
|clé= ISTEX:F54A35D32E2414C90B68141D4EDE9A2FBA0C02F1
|texte= Page segmentation and identification for intelligent signal processing
}}
| This area was generated with Dilib version V0.6.32. |  |