{"_buckets": {"deposit": "1b620fa2-719b-4748-86c0-02806ee220c4"}, "_deposit": {"id": "3756", "owners": [], "pid": {"revision_id": 0, "type": "recid", "value": "3756"}, "status": "published"}, "_oai": {"id": "oai:meral.edu.mm:recid/3756", "sets": ["user-ucsy"]}, "communities": ["ucsy"], "item_1583103067471": {"attribute_name": "Title", "attribute_value_mlt": [{"subitem_1551255647225": "Automatic Extraction of Data Record from Web Page based on Visual Features", "subitem_1551255648112": "en"}]}, "item_1583103085720": {"attribute_name": "Description", "attribute_value_mlt": [{"interim": "The Web is increasingly becoming a verylarge information source. However, theinformation is visually structured such that it iseasy for humans to recognize data records andpresentation patterns, but not for computers. Asweb sites are getting more complicated, theconstruction of web information extractionsystem becomes more troublesome and timeconsuming.Hence, tools for the mining of dataregions, data records and data items need to bedeveloped in order to provide value addedservices. Large number of techniques has beenproposed to address this problem, but all of themhave inherent limitations. In this paper, wepropose an approach for automatic data recordextraction method from web page, which we callVision based Extraction of data Record (VER).The approach is based on the observation thatvisual similarity of the data record in webdocument. Firstly, we adopt VIPS (Vision-basedPage Segmentation) algorithm to partition a webpage into semantic blocks. Then, blocks areclustered by proposed block clustering methodaccording to the appearance similarity. Amongthese clusters, we identify data region and finallyextract data record from data region."}]}, "item_1583103108160": {"attribute_name": "Keywords", "attribute_value": []}, "item_1583103120197": {"attribute_name": "Files", "attribute_type": "file", "attribute_value_mlt": [{"accessrole": "open_access", "date": [{"dateType": "Available", "dateValue": "2019-07-03"}], "displaytype": "preview", "download_preview_message": "", "file_order": 0, "filename": "9039.pdf", "filesize": [{"value": "118 Kb"}], "format": "application/pdf", "future_date_message": "", "is_thumbnail": false, "licensetype": "license_free", "mimetype": "application/pdf", "size": 118000.0, "url": {"url": "https://meral.edu.mm/record/3756/files/9039.pdf"}, "version_id": "13b76d5d-7be3-4dfe-aed4-cb10527d3616"}]}, "item_1583103131163": {"attribute_name": "Journal articles", "attribute_value_mlt": [{"subitem_issue": "", "subitem_journal_title": "Ninth International Conference On Computer Applications (ICCA 2011)", "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": "Hlaing, Nwe Nwe"}, {"subitem_authors_fullname": "Nyunt, Thi Thi Soe"}]}]}, "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": "2011-05-05"}, "item_1583159847033": {"attribute_name": "Identifier", "attribute_value": "http://onlineresource.ucsy.edu.mm/handle/123456789/149"}, "item_title": "Automatic Extraction of Data Record from Web Page based on Visual Features", "item_type_id": "21", "owner": "1", "path": ["1597824273898"], "permalink_uri": "http://hdl.handle.net/20.500.12678/0000003756", "pubdate": {"attribute_name": "Deposited date", "attribute_value": "2019-07-03"}, "publish_date": "2019-07-03", "publish_status": "0", "recid": "3756", "relation": {}, "relation_version_is_last": true, "title": ["Automatic Extraction of Data Record from Web Page based on Visual Features"], "weko_shared_id": -1}