WEKO3
アイテム
{"_buckets": {"deposit": "492b4686-d4b0-423c-81e5-426eb5e89bb7"}, "_deposit": {"created_by": 3, "id": "12859", "owners": [3], "pid": {"revision_id": 0, "type": "depid", "value": "12859"}, "status": "published"}, "_oai": {"id": "oai:sucra.repo.nii.ac.jp:00012859", "sets": ["426"]}, "author_link": ["20268", "20267", "20270", "20269"], "item_119_biblio_info_8": {"attribute_name": "書誌情報", "attribute_value_mlt": [{"bibliographicIssueDates": {"bibliographicIssueDate": "2005", "bibliographicIssueDateType": "Issued"}, "bibliographicIssueNumber": "10", "bibliographicPageEnd": "2295", "bibliographicPageStart": "2286", "bibliographicVolumeNumber": "E88-D", "bibliographic_titles": [{"bibliographic_title": "IEICE transactions on information and systems"}]}]}, "item_119_date_31": {"attribute_name": "作成日", "attribute_value_mlt": [{"subitem_date_issued_datetime": "2007-10-02", "subitem_date_issued_type": "Created"}]}, "item_119_description_17": {"attribute_name": "関連サイト", "attribute_value_mlt": [{"subitem_description": "http://www.ieice.org/jpn/trans_online/index.html | http://www.ieice.org/jpn/trans_online/index.html", "subitem_description_type": "Other"}]}, "item_119_description_19": {"attribute_name": "抄録", "attribute_value_mlt": [{"subitem_description": "This paper presents Dynamic Attention Map by Ising model for face detection. In general, a face detector can not know where faces there are and how many faces there are in advance. Therefore, the face detector must search the whole regions on the image and requires much computational time. To speed up the search, the information obtained at previous search points should be used effectively. In order to use the likelihood of face obtained at previous search points effectively, Ising model is adopted to face detection. Ising model has the two-state spins; \"up\" and \"down\". The state of a spin is updated by depending on the neighboring spins and an external magnetic field. Ising spins are assigned to \"face\" and \"non-face\" states of face detection. In addition, the measured likelihood of face is integrated into the energy function of Ising model as the external magnetic field. It is confirmed that face candidates would be reduced effectively by spin flip dynamics. To improve the search performance further, the single level Ising search method is extended to the multilevel Ising search. The interactions between two layers which are characterized by the renormalization group method is used to reduce the face candidates. The effectiveness of the multilevel Ising search method is also confirmed by the comparison with the single level Ising search method.", "subitem_description_type": "Abstract"}]}, "item_119_description_21": {"attribute_name": "注記", "attribute_value_mlt": [{"subitem_description": "copyright(c)2005 IEICE\n許諾番号:07RB0174", "subitem_description_type": "Other"}]}, "item_119_description_29": {"attribute_name": "資源タイプ", "attribute_value_mlt": [{"subitem_description": "text", "subitem_description_type": "Other"}]}, "item_119_description_30": {"attribute_name": "フォーマット", "attribute_value_mlt": [{"subitem_description": "application/pdf", "subitem_description_type": "Other"}]}, "item_119_publisher_11": {"attribute_name": "出版者名", "attribute_value_mlt": [{"subitem_publisher": "社団法人電子情報通信学会"}]}, "item_119_source_id_14": {"attribute_name": "ISSN", "attribute_value_mlt": [{"subitem_source_identifier": "09168532", "subitem_source_identifier_type": "ISSN"}]}, "item_119_text_3": {"attribute_name": "著者 ローマ字", "attribute_value_mlt": [{"subitem_text_value": "TANAKA, Masaru"}, {"subitem_text_value": "MISHIMA, Taketoshi"}, {"subitem_text_value": "HOTTA, Kazuhiro"}, {"subitem_text_value": "KURITA, Takio"}]}, "item_119_text_32": {"attribute_name": "アイテムID", "attribute_value_mlt": [{"subitem_text_value": "A1003030"}]}, "item_119_text_35": {"attribute_name": "公開日(XooNIps)", "attribute_value_mlt": [{"subitem_text_value": "Oct 2, 2007 09:00:00"}]}, "item_119_text_36": {"attribute_name": "最終更新日(XooNIps)", "attribute_value_mlt": [{"subitem_text_value": "Sep 9, 2011 13:52:03"}]}, "item_119_text_37": {"attribute_name": "更新履歴(XooNIps)", "attribute_value_mlt": [{"subitem_text_value": "Sep 9, 2011 著者 を変更"}, {"subitem_text_value": "Sep 2, 2009 フリーキーワード, 著者 を変更"}, {"subitem_text_value": "Mar 18, 2009 フリーキーワード, キーワード を変更"}, {"subitem_text_value": "Oct 7, 2008 フリーキーワード, インデックス, キーワード を変更"}, {"subitem_text_value": "Aug 7, 2008 コメント, フリーキーワード, キーワード を変更"}, {"subitem_text_value": "Feb 27, 2008 フリーキーワード, インデックス, キーワード を変更"}, {"subitem_text_value": "Feb 12, 2008 フリーキーワード, インデックス, キーワード を変更"}, {"subitem_text_value": "Dec 27, 2007 フリーキーワード, キーワード を変更"}, {"subitem_text_value": "Oct 21, 2007 フリーキーワード, インデックス, キーワード を変更"}, {"subitem_text_value": "Oct 12, 2007 フリーキーワード, キーワード を変更"}, {"subitem_text_value": "Oct 3, 2007 コメント, フリーキーワード, キーワード を変更"}, {"subitem_text_value": "Oct 2, 2007 フリーキーワード, 巻, キーワード を変更"}, {"subitem_text_value": "Oct 2, 2007 ID, フリーキーワード, インデックス, キーワード を変更"}]}, "item_119_text_38": {"attribute_name": "登録者(XooNIps)", "attribute_value_mlt": [{"subitem_text_value": "sucra_jim4"}]}, "item_119_text_39": {"attribute_name": "閲覧数(XooNIps)", "attribute_value_mlt": [{"subitem_text_value": "1329"}]}, "item_119_text_4": {"attribute_name": "著者 所属", "attribute_value_mlt": [{"subitem_text_value": "埼玉大学工学部"}, {"subitem_text_value": "埼玉大学工学部電気電子システム工学科"}, {"subitem_text_value": "埼玉大学大学院理工学研究科"}, {"subitem_text_value": "産業技術総合研究所脳神経情報研究部門"}]}, "item_119_text_40": {"attribute_name": "ダウンロード数(XooNIps)", "attribute_value_mlt": [{"subitem_text_value": "678"}]}, "item_119_text_41": {"attribute_name": "XooNIps_インデックス", "attribute_value_mlt": [{"subitem_text_value": "sucra_jim4|Public/埼玉大学/理工学研究科|Public/埼玉大学/理工学研究科/数理電子情報部門|Public/主題別/総合領域/情報学/知覚情報処理・知能ロボティクス|Public/ジャンル別/学術雑誌論文(国内)/電子情報通信学会"}]}, "item_119_text_42": {"attribute_name": "XooNIps_ITEM_KEY", "attribute_value_mlt": [{"subitem_text_value": "811"}]}, "item_119_text_5": {"attribute_name": "著者 所属(別言語)", "attribute_value_mlt": [{"subitem_text_value": "Faculty of Engineering, Saitama UniversityDepartment of Electrical and Electronic Systems, Faculty of Engineering, Saitama University"}, {"subitem_text_value": "Department of Electrical and Electronic Systems, Faculty of Engineering, Saitama University"}, {"subitem_text_value": "Department of Electrical and Electronic Systems, Faculty of Engineering, Saitama University"}, {"subitem_text_value": "Neuroscience Research Institute, the National Institute of Advanced Industrial Science and Technology"}]}, "item_119_text_9": {"attribute_name": "年月次", "attribute_value_mlt": [{"subitem_text_value": "2005-10"}]}, "item_creator": {"attribute_name": "著者", "attribute_type": "creator", "attribute_value_mlt": [{"creatorNames": [{"creatorName": "田中, 勝"}, {"creatorName": "タナカ, マサル", "creatorNameLang": "ja-Kana"}], "nameIdentifiers": [{"nameIdentifier": "20267", "nameIdentifierScheme": "WEKO"}]}, {"creatorNames": [{"creatorName": "三島, 健稔"}, {"creatorName": "ミシマ, タケトシ", "creatorNameLang": "ja-Kana"}], "nameIdentifiers": [{"nameIdentifier": "20268", "nameIdentifierScheme": "WEKO"}]}, {"creatorNames": [{"creatorName": "堀田, 一弘"}, {"creatorName": "ホッタ, カズヒロ", "creatorNameLang": "ja-Kana"}], "nameIdentifiers": [{"nameIdentifier": "20269", "nameIdentifierScheme": "WEKO"}]}, {"creatorNames": [{"creatorName": "栗田, 多喜夫"}, {"creatorName": "クリタ, タキオ", "creatorNameLang": "ja-Kana"}], "nameIdentifiers": [{"nameIdentifier": "20270", "nameIdentifierScheme": "WEKO"}]}]}, "item_files": {"attribute_name": "ファイル情報", "attribute_type": "file", "attribute_value_mlt": [{"accessrole": "open_date", "date": [{"dateType": "Available", "dateValue": "2018-01-24"}], "displaytype": "detail", "download_preview_message": "", "file_order": 0, "filename": "A1003030.pdf", "filesize": [{"value": "1.5 MB"}], "format": "application/pdf", "future_date_message": "", "is_thumbnail": false, "licensetype": "license_free", "mimetype": "application/pdf", "size": 1500000.0, "url": {"label": "A1003030.pdf", "url": "https://sucra.repo.nii.ac.jp/record/12859/files/A1003030.pdf"}, "version_id": "754875a2-b61c-45e6-a21c-9da00d0807be"}]}, "item_keyword": {"attribute_name": "キーワード", "attribute_value_mlt": [{"subitem_subject": "Ising model", "subitem_subject_scheme": "Other"}, {"subitem_subject": "dynamic attention map", "subitem_subject_scheme": "Other"}, {"subitem_subject": "renormalization group", "subitem_subject_scheme": "Other"}, {"subitem_subject": "efficient search", "subitem_subject_scheme": "Other"}, {"subitem_subject": "face detection", "subitem_subject_scheme": "Other"}]}, "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": "journal article", "resourceuri": "http://purl.org/coar/resource_type/c_6501"}]}, "item_title": "An Efficient Search Method Based on Dynamic Attention Map by Ising Model(\u003cSpecial Section\u003eImage Recognition and Understanding)", "item_titles": {"attribute_name": "タイトル", "attribute_value_mlt": [{"subitem_title": "An Efficient Search Method Based on Dynamic Attention Map by Ising Model(\u003cSpecial Section\u003eImage Recognition and Understanding)"}]}, "item_type_id": "119", "owner": "3", "path": ["426"], "permalink_uri": "https://sucra.repo.nii.ac.jp/records/12859", "pubdate": {"attribute_name": "公開日", "attribute_value": "2007-10-02"}, "publish_date": "2007-10-02", "publish_status": "0", "recid": "12859", "relation": {}, "relation_version_is_last": true, "title": ["An Efficient Search Method Based on Dynamic Attention Map by Ising Model(\u003cSpecial Section\u003eImage Recognition and Understanding)"], "weko_shared_id": -1}
An Efficient Search Method Based on Dynamic Attention Map by Ising Model(<Special Section>Image Recognition and Understanding)
https://sucra.repo.nii.ac.jp/records/12859
https://sucra.repo.nii.ac.jp/records/12859624f8e07-addc-4636-9c3e-f5d2d140e4f5
名前 / ファイル | ライセンス | アクション |
---|---|---|
A1003030.pdf (1.5 MB)
|
|
Item type | 学術雑誌論文 / Journal Article(1) | |||||
---|---|---|---|---|---|---|
公開日 | 2007-10-02 | |||||
タイトル | ||||||
タイトル | An Efficient Search Method Based on Dynamic Attention Map by Ising Model(<Special Section>Image Recognition and Understanding) | |||||
言語 | ||||||
言語 | eng | |||||
キーワード | ||||||
主題Scheme | Other | |||||
主題 | Ising model | |||||
キーワード | ||||||
主題Scheme | Other | |||||
主題 | dynamic attention map | |||||
キーワード | ||||||
主題Scheme | Other | |||||
主題 | renormalization group | |||||
キーワード | ||||||
主題Scheme | Other | |||||
主題 | efficient search | |||||
キーワード | ||||||
主題Scheme | Other | |||||
主題 | face detection | |||||
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 | journal article | |||||
著者 |
田中, 勝
× 田中, 勝× 三島, 健稔× 堀田, 一弘× 栗田, 多喜夫 |
|||||
著者 ローマ字 | ||||||
TANAKA, Masaru | ||||||
著者 ローマ字 | ||||||
MISHIMA, Taketoshi | ||||||
著者 ローマ字 | ||||||
HOTTA, Kazuhiro | ||||||
著者 ローマ字 | ||||||
KURITA, Takio | ||||||
著者 所属 | ||||||
埼玉大学工学部 | ||||||
著者 所属 | ||||||
埼玉大学工学部電気電子システム工学科 | ||||||
著者 所属 | ||||||
埼玉大学大学院理工学研究科 | ||||||
著者 所属 | ||||||
産業技術総合研究所脳神経情報研究部門 | ||||||
著者 所属(別言語) | ||||||
Faculty of Engineering, Saitama UniversityDepartment of Electrical and Electronic Systems, Faculty of Engineering, Saitama University | ||||||
著者 所属(別言語) | ||||||
Department of Electrical and Electronic Systems, Faculty of Engineering, Saitama University | ||||||
著者 所属(別言語) | ||||||
Department of Electrical and Electronic Systems, Faculty of Engineering, Saitama University | ||||||
著者 所属(別言語) | ||||||
Neuroscience Research Institute, the National Institute of Advanced Industrial Science and Technology | ||||||
書誌情報 |
IEICE transactions on information and systems 巻 E88-D, 号 10, p. 2286-2295, 発行日 2005 |
|||||
年月次 | ||||||
2005-10 | ||||||
出版者名 | ||||||
出版者 | 社団法人電子情報通信学会 | |||||
ISSN | ||||||
収録物識別子タイプ | ISSN | |||||
収録物識別子 | 09168532 | |||||
関連サイト | ||||||
内容記述タイプ | Other | |||||
内容記述 | http://www.ieice.org/jpn/trans_online/index.html | http://www.ieice.org/jpn/trans_online/index.html | |||||
抄録 | ||||||
内容記述タイプ | Abstract | |||||
内容記述 | This paper presents Dynamic Attention Map by Ising model for face detection. In general, a face detector can not know where faces there are and how many faces there are in advance. Therefore, the face detector must search the whole regions on the image and requires much computational time. To speed up the search, the information obtained at previous search points should be used effectively. In order to use the likelihood of face obtained at previous search points effectively, Ising model is adopted to face detection. Ising model has the two-state spins; "up" and "down". The state of a spin is updated by depending on the neighboring spins and an external magnetic field. Ising spins are assigned to "face" and "non-face" states of face detection. In addition, the measured likelihood of face is integrated into the energy function of Ising model as the external magnetic field. It is confirmed that face candidates would be reduced effectively by spin flip dynamics. To improve the search performance further, the single level Ising search method is extended to the multilevel Ising search. The interactions between two layers which are characterized by the renormalization group method is used to reduce the face candidates. The effectiveness of the multilevel Ising search method is also confirmed by the comparison with the single level Ising search method. | |||||
注記 | ||||||
内容記述タイプ | Other | |||||
内容記述 | copyright(c)2005 IEICE 許諾番号:07RB0174 |
|||||
資源タイプ | ||||||
内容記述タイプ | Other | |||||
内容記述 | text | |||||
フォーマット | ||||||
内容記述タイプ | Other | |||||
内容記述 | application/pdf | |||||
作成日 | ||||||
日付 | 2007-10-02 | |||||
日付タイプ | Created | |||||
アイテムID | ||||||
A1003030 |