Log in
Language:

MERAL Myanmar Education Research and Learning Portal

  • Top
  • Universities
  • Ranking
To
lat lon distance
To

Field does not validate



Index Link

Index Tree

Please input email address.

WEKO

One fine body…

WEKO

One fine body…

Item

{"_buckets": {"deposit": "285325e3-7348-4675-9ca1-88328924873e"}, "_deposit": {"id": "4380", "owners": [], "pid": {"revision_id": 0, "type": "recid", "value": "4380"}, "status": "published"}, "_oai": {"id": "oai:meral.edu.mm:recid/4380", "sets": ["1597824304333", "user-ucsy"]}, "communities": ["ucsy"], "item_1583103067471": {"attribute_name": "Title", "attribute_value_mlt": [{"subitem_1551255647225": "A Robust Local Thresholding Method for Segmentation of Non-Uniform Coloured Documents", "subitem_1551255648112": "en_US"}]}, "item_1583103085720": {"attribute_name": "Description", "attribute_value_mlt": [{"interim": "Text document segmentation is one of theessential steps text document recognition andextraction systems. The existing segmenting methodsare not much reliable for text with colour gradientand texture background. Also, long processing timeof existing methods is unfavorable.Thus, aiming to have reliable segmentationand less processing time, a new local thresholdingmethod is proposed in this study. The proposedmethod is based on pixel intensity magnificationconcept. Non-overlapping local window is used. Theperformance of proposed method is compared withthat of Otsu’s method and Niblack’s method. Theresults show that the proposed method give morereliable segmentation compared to Otus’ method, 1.2times longer processing time. Compared to Niblack’smethod, the segmented results are comparable andthe processing time is 5 times faster."}]}, "item_1583103108160": {"attribute_name": "Keywords", "attribute_value_mlt": [{"interim": "segmentation"}, {"interim": "local thresholding"}, {"interim": "pixel magnification"}, {"interim": "text document recognition"}, {"interim": "character recognition"}]}, "item_1583103120197": {"attribute_name": "Files", "attribute_type": "file", "attribute_value_mlt": [{"accessrole": "open_access", "date": [{"dateType": "Available", "dateValue": "2019-10-15"}], "displaytype": "preview", "download_preview_message": "", "file_order": 0, "filename": "NJPSC 2019 Proceedings-pages-193-198.pdf", "filesize": [{"value": "503 Kb"}], "format": "application/pdf", "future_date_message": "", "is_thumbnail": false, "licensetype": "license_free", "mimetype": "application/pdf", "size": 503000.0, "url": {"url": "https://meral.edu.mm/record/4380/files/NJPSC 2019 Proceedings-pages-193-198.pdf"}, "version_id": "3f0ee4f1-7ff0-42b7-9077-0c6e6896d43a"}]}, "item_1583103131163": {"attribute_name": "Journal articles", "attribute_value_mlt": [{"subitem_issue": "", "subitem_journal_title": "National Journal of Parallel and Soft Computing", "subitem_pages": "", "subitem_volume": ""}]}, "item_1583103147082": {"attribute_name": "Conference papers", "attribute_value_mlt": [{"subitem_acronym": "", "subitem_c_date": "", "subitem_conference_title": "", "subitem_part": "", "subitem_place": "", "subitem_session": "", "subitem_website": ""}]}, "item_1583103211336": {"attribute_name": "Books/reports/chapters", "attribute_value_mlt": [{"subitem_book_title": "", "subitem_isbn": "", "subitem_pages": "", "subitem_place": "", "subitem_publisher": ""}]}, "item_1583103233624": {"attribute_name": "Thesis/dissertations", "attribute_value_mlt": [{"subitem_awarding_university": "", "subitem_supervisor(s)": [{"subitem_supervisor": ""}]}]}, "item_1583105942107": {"attribute_name": "Authors", "attribute_value_mlt": [{"subitem_authors": [{"subitem_authors_fullname": "Aung, Thidar"}, {"subitem_authors_fullname": "Thein, Thin Lai Lai"}]}]}, "item_1583108359239": {"attribute_name": "Upload type", "attribute_value_mlt": [{"interim": "Publication"}]}, "item_1583108428133": {"attribute_name": "Publication type", "attribute_value_mlt": [{"interim": "Article"}]}, "item_1583159729339": {"attribute_name": "Publication date", "attribute_value": "2019-03"}, "item_1583159847033": {"attribute_name": "Identifier", "attribute_value": "http://onlineresource.ucsy.edu.mm/handle/123456789/2317"}, "item_title": "A Robust Local Thresholding Method for Segmentation of Non-Uniform Coloured Documents", "item_type_id": "21", "owner": "1", "path": ["1597824304333"], "permalink_uri": "http://hdl.handle.net/20.500.12678/0000004380", "pubdate": {"attribute_name": "Deposited date", "attribute_value": "2019-10-15"}, "publish_date": "2019-10-15", "publish_status": "0", "recid": "4380", "relation": {}, "relation_version_is_last": true, "title": ["A Robust Local Thresholding Method for Segmentation of Non-Uniform Coloured Documents"], "weko_shared_id": -1}
  1. University of Computer Studies, Yangon
  2. Journals

A Robust Local Thresholding Method for Segmentation of Non-Uniform Coloured Documents

http://hdl.handle.net/20.500.12678/0000004380
http://hdl.handle.net/20.500.12678/0000004380
156dbaa2-a563-497b-9c29-9452a5950a7f
285325e3-7348-4675-9ca1-88328924873e
None
Preview
Name / File License Actions
NJPSC NJPSC 2019 Proceedings-pages-193-198.pdf (503 Kb)
Publication type
Article
Upload type
Publication
Title
Title A Robust Local Thresholding Method for Segmentation of Non-Uniform Coloured Documents
Language en_US
Publication date 2019-03
Authors
Aung, Thidar
Thein, Thin Lai Lai
Description
Text document segmentation is one of theessential steps text document recognition andextraction systems. The existing segmenting methodsare not much reliable for text with colour gradientand texture background. Also, long processing timeof existing methods is unfavorable.Thus, aiming to have reliable segmentationand less processing time, a new local thresholdingmethod is proposed in this study. The proposedmethod is based on pixel intensity magnificationconcept. Non-overlapping local window is used. Theperformance of proposed method is compared withthat of Otsu’s method and Niblack’s method. Theresults show that the proposed method give morereliable segmentation compared to Otus’ method, 1.2times longer processing time. Compared to Niblack’smethod, the segmented results are comparable andthe processing time is 5 times faster.
Keywords
segmentation, local thresholding, pixel magnification, text document recognition, character recognition
Identifier http://onlineresource.ucsy.edu.mm/handle/123456789/2317
Journal articles
National Journal of Parallel and Soft Computing
Conference papers
Books/reports/chapters
Thesis/dissertations
Back
0
0
views
downloads
See details
Views Downloads

Versions

Ver.1 2020-09-01 14:38:02.592759
Show All versions

Share

Mendeley Twitter Facebook Print Addthis

Export

OAI-PMH
  • OAI-PMH DublinCore
Other Formats
  • JSON

Confirm


Back to MERAL


Back to MERAL