2-D histogram-based segmentation of postal envelopes

Mail sorting automation is yet a partially solved challenge. Due to no fixed positions of the semantic information in envelope images, part of this challenge is the automatic location of address blocks. We approach this problem by proposing a new postal envelope segmentation method based on 2D histo...

Full description

Saved in:
Bibliographic Details
Main Authors: Yonekura, E.A., Facon, J.
Format: Conference Proceeding
Language:English
Subjects:
Automation
Envelope detectors
Filtering
Gabor filters
Histograms
Image databases
Image segmentation
Postal services
Sorting
Spatial databases
Online Access:Request full text
Tags: Add Tag
No Tags, Be the first to tag this record!
cited_by
cites
container_end_page 253
container_issue
container_start_page 247
container_title
container_volume
creator Yonekura, E.A.
Facon, J.
description Mail sorting automation is yet a partially solved challenge. Due to no fixed positions of the semantic information in envelope images, part of this challenge is the automatic location of address blocks. We approach this problem by proposing a new postal envelope segmentation method based on 2D histogram clustering and watershed transform. Segmentation task consists in detecting the 2D histogram modes associated with homogeneous regions in envelope. A new filter used for 2D histogram calculation is proposed. The homogeneous modes in 2D histogram are segmented through the morphological watershed transform. Our approach is applied to complex postal envelopes. Very little a priori knowledge of the envelope images is required. The advantages of this approach are described and illustrated with tests carried out on 300 different images where there are no fixed position for the handwritten address block, postmarks and stamps. A groundtruth strategy is employed to evaluate the accuracy of segmentation.
doi_str_mv 10.1109/SIBGRA.2003.1241016
format conference_proceeding
fullrecord <record><control><sourceid>ieee_6IE</sourceid><recordid>TN_cdi_ieee_primary_1241016</recordid><sourceformat>XML</sourceformat><sourcesystem>PC</sourcesystem><ieee_id>1241016</ieee_id><sourcerecordid>1241016</sourcerecordid><originalsourceid>FETCH-LOGICAL-i175t-2f641afc1bfa41f29008bee960eb5262a383268e8ebb67d16183e06a3b233a533</originalsourceid><addsrcrecordid>eNotj8lKA0EUABsXcIz5glzmBzq-ZaaXY4waAwHB5Ry6zZs4MhvTg-DfK5hT3YoqpRYIS0Twt6_bu83LakkAvEQqENCcqYzYWl0WaM7V3FsH1viSgIkuVIYlg0bHxZW6TukLAL03LlMF6fv8s05TfxxDq2NIcsiTHFvppjDVfZf3VT70aQpNLt23NP0g6UZdVqFJMj9xpt4fH97WT3r3vNmuVztdoy0nTZUpMFQfGKtQYEUewEURb0BiSYYCOybjxEmMxh7Q_PUJmMCRmEPJPFOLf28tIvthrNsw_uxPw_wLP15G9w</addsrcrecordid><sourcetype>Publisher</sourcetype><iscdi>true</iscdi><recordtype>conference_proceeding</recordtype></control><display><type>conference_proceeding</type><title>2-D histogram-based segmentation of postal envelopes</title><source>IEEE Electronic Library (IEL) Conference Proceedings</source><creator>Yonekura, E.A. ; Facon, J.</creator><creatorcontrib>Yonekura, E.A. ; Facon, J.</creatorcontrib><description>Mail sorting automation is yet a partially solved challenge. Due to no fixed positions of the semantic information in envelope images, part of this challenge is the automatic location of address blocks. We approach this problem by proposing a new postal envelope segmentation method based on 2D histogram clustering and watershed transform. Segmentation task consists in detecting the 2D histogram modes associated with homogeneous regions in envelope. A new filter used for 2D histogram calculation is proposed. The homogeneous modes in 2D histogram are segmented through the morphological watershed transform. Our approach is applied to complex postal envelopes. Very little a priori knowledge of the envelope images is required. The advantages of this approach are described and illustrated with tests carried out on 300 different images where there are no fixed position for the handwritten address block, postmarks and stamps. A groundtruth strategy is employed to evaluate the accuracy of segmentation.</description><identifier>ISSN: 1530-1834</identifier><identifier>ISBN: 9780769520322</identifier><identifier>ISBN: 0769520324</identifier><identifier>EISSN: 2377-5416</identifier><identifier>DOI: 10.1109/SIBGRA.2003.1241016</identifier><language>eng</language><publisher>IEEE</publisher><subject>Automation ; Envelope detectors ; Filtering ; Gabor filters ; Histograms ; Image databases ; Image segmentation ; Postal services ; Sorting ; Spatial databases</subject><ispartof>16th Brazilian Symposium on Computer Graphics and Image Processing (SIBGRAPI 2003), 2003, p.247-253</ispartof><woscitedreferencessubscribed>false</woscitedreferencessubscribed></display><links><openurl>$$Topenurl_article</openurl><openurlfulltext>$$Topenurlfull_article</openurlfulltext><thumbnail>$$Tsyndetics_thumb_exl</thumbnail><linktohtml>$$Uhttps://ieeexplore.ieee.org/document/1241016$$EHTML$$P50$$Gieee$$H</linktohtml><link.rule.ids>309,310,780,784,789,790,2058,4050,4051,27925,54555,54920,54932</link.rule.ids><linktorsrc>$$Uhttps://ieeexplore.ieee.org/document/1241016$$EView_record_in_IEEE$$FView_record_in_$$GIEEE</linktorsrc></links><search><creatorcontrib>Yonekura, E.A.</creatorcontrib><creatorcontrib>Facon, J.</creatorcontrib><title>2-D histogram-based segmentation of postal envelopes</title><title>16th Brazilian Symposium on Computer Graphics and Image Processing (SIBGRAPI 2003)</title><addtitle>SIBGRA</addtitle><description>Mail sorting automation is yet a partially solved challenge. Due to no fixed positions of the semantic information in envelope images, part of this challenge is the automatic location of address blocks. We approach this problem by proposing a new postal envelope segmentation method based on 2D histogram clustering and watershed transform. Segmentation task consists in detecting the 2D histogram modes associated with homogeneous regions in envelope. A new filter used for 2D histogram calculation is proposed. The homogeneous modes in 2D histogram are segmented through the morphological watershed transform. Our approach is applied to complex postal envelopes. Very little a priori knowledge of the envelope images is required. The advantages of this approach are described and illustrated with tests carried out on 300 different images where there are no fixed position for the handwritten address block, postmarks and stamps. A groundtruth strategy is employed to evaluate the accuracy of segmentation.</description><subject>Automation</subject><subject>Envelope detectors</subject><subject>Filtering</subject><subject>Gabor filters</subject><subject>Histograms</subject><subject>Image databases</subject><subject>Image segmentation</subject><subject>Postal services</subject><subject>Sorting</subject><subject>Spatial databases</subject><issn>1530-1834</issn><issn>2377-5416</issn><isbn>9780769520322</isbn><isbn>0769520324</isbn><fulltext>true</fulltext><rsrctype>conference_proceeding</rsrctype><creationdate>2003</creationdate><recordtype>conference_proceeding</recordtype><sourceid>6IE</sourceid><recordid>eNotj8lKA0EUABsXcIz5glzmBzq-ZaaXY4waAwHB5Ry6zZs4MhvTg-DfK5hT3YoqpRYIS0Twt6_bu83LakkAvEQqENCcqYzYWl0WaM7V3FsH1viSgIkuVIYlg0bHxZW6TukLAL03LlMF6fv8s05TfxxDq2NIcsiTHFvppjDVfZf3VT70aQpNLt23NP0g6UZdVqFJMj9xpt4fH97WT3r3vNmuVztdoy0nTZUpMFQfGKtQYEUewEURb0BiSYYCOybjxEmMxh7Q_PUJmMCRmEPJPFOLf28tIvthrNsw_uxPw_wLP15G9w</recordid><startdate>2003</startdate><enddate>2003</enddate><creator>Yonekura, E.A.</creator><creator>Facon, J.</creator><general>IEEE</general><scope>6IE</scope><scope>6IL</scope><scope>CBEJK</scope><scope>RIE</scope><scope>RIL</scope></search><sort><creationdate>2003</creationdate><title>2-D histogram-based segmentation of postal envelopes</title><author>Yonekura, E.A. ; Facon, J.</author></sort><facets><frbrtype>5</frbrtype><frbrgroupid>cdi_FETCH-LOGICAL-i175t-2f641afc1bfa41f29008bee960eb5262a383268e8ebb67d16183e06a3b233a533</frbrgroupid><rsrctype>conference_proceedings</rsrctype><prefilter>conference_proceedings</prefilter><language>eng</language><creationdate>2003</creationdate><topic>Automation</topic><topic>Envelope detectors</topic><topic>Filtering</topic><topic>Gabor filters</topic><topic>Histograms</topic><topic>Image databases</topic><topic>Image segmentation</topic><topic>Postal services</topic><topic>Sorting</topic><topic>Spatial databases</topic><toplevel>online_resources</toplevel><creatorcontrib>Yonekura, E.A.</creatorcontrib><creatorcontrib>Facon, J.</creatorcontrib><collection>IEEE Electronic Library (IEL) Conference Proceedings</collection><collection>IEEE Proceedings Order Plan All Online (POP All Online) 1998-present by volume</collection><collection>IEEE Xplore All Conference Proceedings</collection><collection>IEEE Electronic Library Online</collection><collection>IEEE Proceedings Order Plans (POP All) 1998-Present</collection></facets><delivery><delcategory>Remote Search Resource</delcategory><fulltext>fulltext_linktorsrc</fulltext></delivery><addata><au>Yonekura, E.A.</au><au>Facon, J.</au><format>book</format><genre>proceeding</genre><ristype>CONF</ristype><atitle>2-D histogram-based segmentation of postal envelopes</atitle><btitle>16th Brazilian Symposium on Computer Graphics and Image Processing (SIBGRAPI 2003)</btitle><stitle>SIBGRA</stitle><date>2003</date><risdate>2003</risdate><spage>247</spage><epage>253</epage><pages>247-253</pages><issn>1530-1834</issn><eissn>2377-5416</eissn><isbn>9780769520322</isbn><isbn>0769520324</isbn><abstract>Mail sorting automation is yet a partially solved challenge. Due to no fixed positions of the semantic information in envelope images, part of this challenge is the automatic location of address blocks. We approach this problem by proposing a new postal envelope segmentation method based on 2D histogram clustering and watershed transform. Segmentation task consists in detecting the 2D histogram modes associated with homogeneous regions in envelope. A new filter used for 2D histogram calculation is proposed. The homogeneous modes in 2D histogram are segmented through the morphological watershed transform. Our approach is applied to complex postal envelopes. Very little a priori knowledge of the envelope images is required. The advantages of this approach are described and illustrated with tests carried out on 300 different images where there are no fixed position for the handwritten address block, postmarks and stamps. A groundtruth strategy is employed to evaluate the accuracy of segmentation.</abstract><pub>IEEE</pub><doi>10.1109/SIBGRA.2003.1241016</doi><tpages>7</tpages></addata></record>
fulltext fulltext_linktorsrc
identifier ISSN: 1530-1834
ispartof 16th Brazilian Symposium on Computer Graphics and Image Processing (SIBGRAPI 2003), 2003, p.247-253
issn 1530-1834
2377-5416
language eng
recordid cdi_ieee_primary_1241016
source IEEE Electronic Library (IEL) Conference Proceedings
subjects Automation
Envelope detectors
Filtering
Gabor filters
Histograms
Image databases
Image segmentation
Postal services
Sorting
Spatial databases
title 2-D histogram-based segmentation of postal envelopes
url http://sfxeu10.hosted.exlibrisgroup.com/loughborough?ctx_ver=Z39.88-2004&ctx_enc=info:ofi/enc:UTF-8&ctx_tim=2024-12-21T08%3A58%3A51IST&url_ver=Z39.88-2004&url_ctx_fmt=infofi/fmt:kev:mtx:ctx&rfr_id=info:sid/primo.exlibrisgroup.com:primo3-Article-ieee_6IE&rft_val_fmt=info:ofi/fmt:kev:mtx:book&rft.genre=proceeding&rft.atitle=2-D%20histogram-based%20segmentation%20of%20postal%20envelopes&rft.btitle=16th%20Brazilian%20Symposium%20on%20Computer%20Graphics%20and%20Image%20Processing%20(SIBGRAPI%202003)&rft.au=Yonekura,%20E.A.&rft.date=2003&rft.spage=247&rft.epage=253&rft.pages=247-253&rft.issn=1530-1834&rft.eissn=2377-5416&rft.isbn=9780769520322&rft.isbn_list=0769520324&rft_id=info:doi/10.1109/SIBGRA.2003.1241016&rft_dat=%3Cieee_6IE%3E1241016%3C/ieee_6IE%3E%3Cgrp_id%3Ecdi_FETCH-LOGICAL-i175t-2f641afc1bfa41f29008bee960eb5262a383268e8ebb67d16183e06a3b233a533%3C/grp_id%3E%3Coa%3E%3C/oa%3E%3Curl%3E%3C/url%3E&rft_id=info:oai/&rft_id=info:pmid/&rft_ieee_id=1241016&rfr_iscdi=true