WEKO3
アイテム
{"_buckets": {"deposit": "941d75bb-22fe-4127-9599-f0138c30fc9b"}, "_deposit": {"created_by": 14, "id": "1075", "owners": [14], "pid": {"revision_id": 0, "type": "depid", "value": "1075"}, "status": "published"}, "_oai": {"id": "oai:ous.repo.nii.ac.jp:00001075", "sets": ["327"]}, "author_link": ["11199", "11200"], "item_1_biblio_info_14": {"attribute_name": "書誌情報", "attribute_value_mlt": [{"bibliographicIssueDates": {"bibliographicIssueDate": "1994-03-31", "bibliographicIssueDateType": "Issued"}, "bibliographicPageEnd": "312", "bibliographicPageStart": "307", "bibliographicVolumeNumber": "29", "bibliographic_titles": [{"bibliographic_title": "岡山理科大学紀要. A, 自然科学", "bibliographic_titleLang": "ja"}, {"bibliographic_title": "Bulletin of Okayama University of Science. A, Natural Sciences", "bibliographic_titleLang": "en"}]}]}, "item_1_creator_6": {"attribute_name": "著者名", "attribute_type": "creator", "attribute_value_mlt": [{"creatorNames": [{"creatorName": "王, 暁文", "creatorNameLang": "ja"}, {"creatorName": "Wang, Xiaowen", "creatorNameLang": "en"}], "nameIdentifiers": [{"nameIdentifier": "11199", "nameIdentifierScheme": "WEKO"}]}, {"creatorNames": [{"creatorName": "橋本, 禮治", "creatorNameLang": "ja"}, {"creatorName": "ハシモト, レイジ", "creatorNameLang": "ja-Kana"}, {"creatorName": "Hashimoto, Reiji", "creatorNameLang": "en"}], "nameIdentifiers": [{"nameIdentifier": "11200", "nameIdentifierScheme": "WEKO"}]}]}, "item_1_description_1": {"attribute_name": "ページ属性", "attribute_value_mlt": [{"subitem_description": "P(論文)", "subitem_description_type": "Other"}]}, "item_1_description_12": {"attribute_name": "抄録(英)", "attribute_value_mlt": [{"subitem_description": "The fuzzy mesh feature (FM-feature) which is proposed in our previous work has been proved that it can absorb some handwriting variation. But the recognition rate got there is still not sufficient, one reason of which may be that this feature includes limited structural information about the character. In this work, we consider a modified fuzzy feature of mesh pattern (FNM-feature) by utilizing the neighbor meshes. And by the experiment about that, we have got the result that FNM-feature improves the recognition rate about 6.6% compared with FM-feature, which shows that FNM-feature with information of neighbor meshes is more effective for recognition.", "subitem_description_language": "ja-Kana", "subitem_description_type": "Other"}]}, "item_1_source_id_13": {"attribute_name": "雑誌書誌ID", "attribute_value_mlt": [{"subitem_source_identifier": "AN00033244", "subitem_source_identifier_type": "NCID"}]}, "item_1_text_10": {"attribute_name": "著者所属(英)", "attribute_value_mlt": [{"subitem_text_language": "en", "subitem_text_value": "Graduate School of Science, Okayama University of Science"}, {"subitem_text_language": "en", "subitem_text_value": "Department of Electronic Engineering, Okayama University of Science"}]}, "item_1_text_9": {"attribute_name": "著者所属(日)", "attribute_value_mlt": [{"subitem_text_language": "ja", "subitem_text_value": "岡山理科大学大学院理学研究科"}, {"subitem_text_language": "ja", "subitem_text_value": "岡山理科大学電子工学科"}]}, "item_files": {"attribute_name": "ファイル情報", "attribute_type": "file", "attribute_value_mlt": [{"accessrole": "open_date", "date": [{"dateType": "Available", "dateValue": "1994-03-31"}], "displaytype": "detail", "download_preview_message": "", "file_order": 0, "filename": "KJ00000063584.pdf", "filesize": [{"value": "300.4 kB"}], "format": "application/pdf", "future_date_message": "", "is_thumbnail": false, "licensetype": "license_note", "mimetype": "application/pdf", "size": 300400.0, "url": {"url": "https://ous.repo.nii.ac.jp/record/1075/files/KJ00000063584.pdf"}, "version_id": "8e3b2622-1dbf-4b44-91ca-fdc8131cd730"}]}, "item_language": {"attribute_name": "言語", "attribute_value_mlt": [{"subitem_language": "eng"}]}, "item_resource_type": {"attribute_name": "資源タイプ", "attribute_value_mlt": [{"resourcetype": "departmental bulletin paper", "resourceuri": "http://purl.org/coar/resource_type/c_6501"}]}, "item_title": "Recognition of Handwritten Character by Fuzzy Neighbor Mesh Feature", "item_titles": {"attribute_name": "タイトル", "attribute_value_mlt": [{"subitem_title": "Recognition of Handwritten Character by Fuzzy Neighbor Mesh Feature", "subitem_title_language": "ja"}, {"subitem_title": "Recognition of Handwritten Character by Fuzzy Neighbor Mesh Feature", "subitem_title_language": "en"}]}, "item_type_id": "1", "owner": "14", "path": ["327"], "permalink_uri": "https://ous.repo.nii.ac.jp/records/1075", "pubdate": {"attribute_name": "PubDate", "attribute_value": "1994-03-31"}, "publish_date": "1994-03-31", "publish_status": "0", "recid": "1075", "relation": {}, "relation_version_is_last": true, "title": ["Recognition of Handwritten Character by Fuzzy Neighbor Mesh Feature"], "weko_shared_id": -1}
Recognition of Handwritten Character by Fuzzy Neighbor Mesh Feature
https://ous.repo.nii.ac.jp/records/1075
https://ous.repo.nii.ac.jp/records/1075b31fc8f1-e201-4c1c-a2fe-c6c29f4072b4
名前 / ファイル | ライセンス | アクション |
---|---|---|
KJ00000063584.pdf (300.4 kB)
|
|
Item type | 紀要論文(ELS) / Departmental Bulletin Paper(1) | |||||
---|---|---|---|---|---|---|
公開日 | 1994-03-31 | |||||
タイトル | ||||||
言語 | ja | |||||
タイトル | Recognition of Handwritten Character by Fuzzy Neighbor Mesh Feature | |||||
タイトル | ||||||
言語 | en | |||||
タイトル | Recognition of Handwritten Character by Fuzzy Neighbor Mesh Feature | |||||
言語 | ||||||
言語 | eng | |||||
資源タイプ | ||||||
資源タイプ識別子 | http://purl.org/coar/resource_type/c_6501 | |||||
資源タイプ | departmental bulletin paper | |||||
ページ属性 | ||||||
内容記述タイプ | Other | |||||
内容記述 | P(論文) | |||||
著者名 |
王, 暁文
× 王, 暁文× 橋本, 禮治 |
|||||
著者所属(日) | ||||||
ja | ||||||
岡山理科大学大学院理学研究科 | ||||||
著者所属(日) | ||||||
ja | ||||||
岡山理科大学電子工学科 | ||||||
著者所属(英) | ||||||
en | ||||||
Graduate School of Science, Okayama University of Science | ||||||
著者所属(英) | ||||||
en | ||||||
Department of Electronic Engineering, Okayama University of Science | ||||||
抄録(英) | ||||||
内容記述タイプ | Other | |||||
内容記述 | The fuzzy mesh feature (FM-feature) which is proposed in our previous work has been proved that it can absorb some handwriting variation. But the recognition rate got there is still not sufficient, one reason of which may be that this feature includes limited structural information about the character. In this work, we consider a modified fuzzy feature of mesh pattern (FNM-feature) by utilizing the neighbor meshes. And by the experiment about that, we have got the result that FNM-feature improves the recognition rate about 6.6% compared with FM-feature, which shows that FNM-feature with information of neighbor meshes is more effective for recognition. | |||||
言語 | ja-Kana | |||||
雑誌書誌ID | ||||||
収録物識別子タイプ | NCID | |||||
収録物識別子 | AN00033244 | |||||
書誌情報 |
ja : 岡山理科大学紀要. A, 自然科学 en : Bulletin of Okayama University of Science. A, Natural Sciences 巻 29, p. 307-312, 発行日 1994-03-31 |