基于L1范数的分块二维局部保持投影算法
针对高维输入数据维数较大时可能存在奇异值问题,同时为提高算法的运算效率以及算法的鲁棒性,提出了一种基于L1范数的分块二维局部保持投影算法B2DLPP-L1。传统的局部保持投影算法为避免出现奇异值问题,首先运用主成分分析算法将高维数据投影到子空间中,然而这种方式将会造成高维数据中部分有效信息的流失,B2DLPP-L1算法选择将二维数据直接作为输入数据,避免运用向量形式的输入数据时可能造成的数据流失;同时该算法对二维输入数据进行分块处理,将分块后的数据块作为新的输入数据,之后运用基于L1范数的二维局部保持投影算法对其进行降维。理论上,B2DLPP-L1算法能够较好地对数据进行降维,不仅能够保持高维...
Saved in:
| Published in | 计算机工程与科学 Vol. 39; no. 3; pp. 519 - 523 |
|---|---|
| Main Author | |
| Format | Journal Article |
| Language | Chinese |
| Published |
第二炮兵工程大学初级指挥学院,陕西西安,710025
2017
|
| Subjects | |
| Online Access | Get full text |
| ISSN | 1007-130X |
| DOI | 10.3969/j.issn.1007-130X.2017.03.017 |
Cover
| Abstract | 针对高维输入数据维数较大时可能存在奇异值问题,同时为提高算法的运算效率以及算法的鲁棒性,提出了一种基于L1范数的分块二维局部保持投影算法B2DLPP-L1。传统的局部保持投影算法为避免出现奇异值问题,首先运用主成分分析算法将高维数据投影到子空间中,然而这种方式将会造成高维数据中部分有效信息的流失,B2DLPP-L1算法选择将二维数据直接作为输入数据,避免运用向量形式的输入数据时可能造成的数据流失;同时该算法对二维输入数据进行分块处理,将分块后的数据块作为新的输入数据,之后运用基于L1范数的二维局部保持投影算法对其进行降维。理论上,B2DLPP-L1算法能够较好地对数据进行降维,不仅能够保持高维数据中的有效信息,降低计算复杂程度,提高算法的运行效率,同时还能够克服存在外点情况下分类准确率较低问题,提高算法的鲁棒性。通过选择不同的人脸数据库进行实验,实验结果表明,在存在外点的情况下,运用最近邻分类器时能够取得更高的分类准确率,同时所需的分类时间有所减少。 |
|---|---|
| AbstractList | TP391.4; 针对高维输入数据维数较大时可能存在奇异值问题,同时为提高算法的运算效率以及算法的鲁棒性,提出了一种基于L1范数的分块二维局部保持投影算法B2DLPP-L1.传统的局部保持投影算法为避免出现奇异值问题,首先运用主成分分析算法将高维数据投影到子空间中,然而这种方式将会造成高维数据中部分有效信息的流失,B2DLPP-L1算法选择将二维数据直接作为输入数据,避免运用向量形式的输入数据时可能造成的数据流失;同时该算法对二维输入数据进行分块处理,将分块后的数据块作为新的输入数据,之后运用基于L1范数的二维局部保持投影算法对其进行降维.理论上,B2DLPP-L1算法能够较好地对数据进行降维,不仅能够保持高维数据中的有效信息,降低计算复杂程度,提高算法的运行效率,同时还能够克服存在外点情况下分类准确率较低问题,提高算法的鲁棒性.通过选择不同的人脸数据库进行实验,实验结果表明,在存在外点的情况下,运用最近邻分类器时能够取得更高的分类准确率,同时所需的分类时间有所减少. 针对高维输入数据维数较大时可能存在奇异值问题,同时为提高算法的运算效率以及算法的鲁棒性,提出了一种基于L1范数的分块二维局部保持投影算法B2DLPP-L1。传统的局部保持投影算法为避免出现奇异值问题,首先运用主成分分析算法将高维数据投影到子空间中,然而这种方式将会造成高维数据中部分有效信息的流失,B2DLPP-L1算法选择将二维数据直接作为输入数据,避免运用向量形式的输入数据时可能造成的数据流失;同时该算法对二维输入数据进行分块处理,将分块后的数据块作为新的输入数据,之后运用基于L1范数的二维局部保持投影算法对其进行降维。理论上,B2DLPP-L1算法能够较好地对数据进行降维,不仅能够保持高维数据中的有效信息,降低计算复杂程度,提高算法的运行效率,同时还能够克服存在外点情况下分类准确率较低问题,提高算法的鲁棒性。通过选择不同的人脸数据库进行实验,实验结果表明,在存在外点的情况下,运用最近邻分类器时能够取得更高的分类准确率,同时所需的分类时间有所减少。 |
| Abstract_FL | In order to solve the problem that high-dimensional input data may have singular value,as well as to improve the operation efficiency and robustness of the algorithm,we propose a new algorithm named block two dimensional locality preserving projections based on L1-norm (B2DLPP-L1).Traditional locality preserving projection (LPP) uses the principal component analysis (PCA) to project input data to PCA subspace to avoid singular value problem,however,input data can lose some effective information in this way.The B2DLPP-L1 algorithm chooses two dimensional data as input data,and it divides original input images into modular images and use the images which are divided into two types as the new input data afterwards.Then we apply the proposed algorithm to the sub-images to reduce the dimensionality.In theory,the B2DLPP-L1 algorithm can better reduce dimensionality,preserve effective information of input data,reduce computation,improve operation efficiency of the algorithm,and overcome the problem of low classification accuracy and improve algorithm robustness.Experimental results on face databases reveal that the B2DLPP-L1 algorithm utilizes less time to accomplish the nearestneighbor classification and obtain more accurate classification rate. |
| Author | 丁铭 贾维敏 |
| AuthorAffiliation | 第二炮兵工程大学初级指挥学院,陕西西安710025 |
| AuthorAffiliation_xml | – name: 第二炮兵工程大学初级指挥学院,陕西西安,710025 |
| Author_FL | JIA Wei-min DING Ming |
| Author_FL_xml | – sequence: 1 fullname: DING Ming – sequence: 2 fullname: JIA Wei-min |
| Author_xml | – sequence: 1 fullname: 丁铭 贾维敏 |
| BookMark | eNo9jztLA0EcxLeIYIz5EmJjced_s9lXKcEXHNiksAt7y915p240h2g6JSIiwS4EhGBrJQatIuKXuYd-C1ciNjMw_JhhllDFdE2A0CoGl0gm1xM3TlPjYgDuYAL7bgMwd4G41iqo-p8vonqaxj4Ao0xQjquI5o-zbHbv4a_hoBi9lA_X-e1NPhlns2H5_pZPL78HT9nnpBheFXej_GNaPo-L19EyWgjVURrU_7yG2lub7daO4-1t77Y2PEczzJ2QSi6BBkJSThi2g0EIQlDVZABKBbzhg6ZCcgJUC-JrIRgL_KbGIICHnNTQ2rz2XJlQmaiTdM96xg52kjSJdP_w4vcnECuWXZmz-qBrotPY0ie9-Fj1-h3GLdTEDUl-ABQeaDo |
| ClassificationCodes | TP391.4 |
| ContentType | Journal Article |
| Copyright | Copyright © Wanfang Data Co. Ltd. All Rights Reserved. |
| Copyright_xml | – notice: Copyright © Wanfang Data Co. Ltd. All Rights Reserved. |
| DBID | 2RA 92L CQIGP W92 ~WA 2B. 4A8 92I 93N PSX TCJ |
| DOI | 10.3969/j.issn.1007-130X.2017.03.017 |
| DatabaseName | 维普期刊资源整合服务平台 中文科技期刊数据库-CALIS站点 维普中文期刊数据库 中文科技期刊数据库-工程技术 中文科技期刊数据库- 镜像站点 Wanfang Data Journals - Hong Kong WANFANG Data Centre Wanfang Data Journals 万方数据期刊 - 香港版 China Online Journals (COJ) China Online Journals (COJ) |
| DatabaseTitleList | |
| DeliveryMethod | fulltext_linktorsrc |
| DocumentTitleAlternate | An algorithm for block two dimensional locality preserving projection based on L1 norm |
| DocumentTitle_FL | An algorithm for block two dimensional locality preserving projection based on L1 norm |
| EndPage | 523 |
| ExternalDocumentID | jsjgcykx201703017 671704129 |
| GrantInformation_xml | – fundername: 国家自然科学基金青年科学基金 funderid: (61401471) |
| GroupedDBID | 2RA 92L ALMA_UNASSIGNED_HOLDINGS CDYEO CQIGP W92 ~WA 2B. 4A8 92I 93N PSX TCJ |
| ID | FETCH-LOGICAL-c617-f597905e8957361857ef0885a4600aae72b0c5897305c83bc8866eb4c10807f73 |
| ISSN | 1007-130X |
| IngestDate | Thu May 29 04:04:00 EDT 2025 Wed Feb 14 10:02:59 EST 2024 |
| IsPeerReviewed | true |
| IsScholarly | true |
| Issue | 3 |
| Keywords | 流行学习 局部保持投影 dimensionality reduction 降维 locality preserving projections face recognition 人脸识别 manifold learning |
| Language | Chinese |
| LinkModel | OpenURL |
| MergedId | FETCHMERGED-LOGICAL-c617-f597905e8957361857ef0885a4600aae72b0c5897305c83bc8866eb4c10807f73 |
| Notes | locality preserving projections ~ dimensionality reduction ; manifold learning ; face recognition 43-1258/TP In order to solve the problem that high-dimensional input data may have singular value, as well as to improve the operation efficiency and robustness of the algorithm, we propose a new algorithm named block two dimensional locality preserving projections based on Ll-norm （B2DLPP-L1）. Tradi- tional locality preserving projection （LPP） uses the principal component analysis （PCA） to project input data to PCA subspace to avoid singular value problem, however, input data can lose some effective in- formation in this way. The B2DLPP-L1 algorithm chooses two dimensional data as input data, and it di- vides original input images into modular images and use the images which are divided into two types as the new input data afterwards. Then we apply the proposed algorithm to the sub-images to reduce the dimensionality. In theory, the B2DLPP-L1 algorithm can better reduce dimensionality, preserve effec- tive informa |
| PageCount | 5 |
| ParticipantIDs | wanfang_journals_jsjgcykx201703017 chongqing_primary_671704129 |
| PublicationCentury | 2000 |
| PublicationDate | 2017 |
| PublicationDateYYYYMMDD | 2017-01-01 |
| PublicationDate_xml | – year: 2017 text: 2017 |
| PublicationDecade | 2010 |
| PublicationTitle | 计算机工程与科学 |
| PublicationTitleAlternate | Computer Engineering ＆ Science |
| PublicationTitle_FL | Computer Engineering and Science |
| PublicationYear | 2017 |
| Publisher | 第二炮兵工程大学初级指挥学院,陕西西安,710025 |
| Publisher_xml | – name: 第二炮兵工程大学初级指挥学院,陕西西安,710025 |
| SSID | ssib006568571 ssib017479296 ssib001050383 ssib015938883 ssib001102936 ssib051375740 ssib023646326 ssib036438059 ssib000459496 |
| Score | 2.0860906 |
| Snippet | 针对高维输入数据维数较大时可能存在奇异值问题,同时为提高算法的运算效率以及算法的鲁棒性,提出了一种基于L1范数的分块二维局部保持投影算法B2DLPP-L1。传统的局部保持投... TP391.4; 针对高维输入数据维数较大时可能存在奇异值问题,同时为提高算法的运算效率以及算法的鲁棒性,提出了一种基于L1范数的分块二维局部保持投影算法B2DLPP-L1.传统的局... |
| SourceID | wanfang chongqing |
| SourceType | Aggregation Database Publisher |
| StartPage | 519 |
| SubjectTerms | 人脸识别 局部保持投影 流行学习 降维 |
| Title | 基于L1范数的分块二维局部保持投影算法 |
| URI | http://lib.cqvip.com/qk/94293X/201703/671704129.html https://d.wanfangdata.com.cn/periodical/jsjgcykx201703017 |
| Volume | 39 |
| hasFullText | 1 |
| inHoldings | 1 |
| isFullTextHit | |
| isPrint | |
| journalDatabaseRights | – providerCode: PRVEBS databaseName: Inspec with Full Text issn: 1007-130X databaseCode: ADMLS dateStart: 20130501 customDbUrl: isFulltext: true dateEnd: 99991231 titleUrlDefault: https://www.ebsco.com/products/research-databases/inspec-full-text omitProxy: false ssIdentifier: ssib015938883 providerName: EBSCOhost |
| link | http://utb.summon.serialssolutions.com/2.0.0/link/0/eLvHCXMwnV3NaxNBFB9iCuJFFBVrVYp0TrI1m53P426yoUj0YoTcwn4lpUKqNgXtSamISPAWCkL16kkseoqI_0w-9L_wvdlNshUp6mWZzPz2zZt9m5nfPOa9JWQNk8AxO44srbiymAhiK7BDYcUqtBOlY2kHJtvnXbFxn91u8mah8C53amm3F65He3-MK_kfq0Id2BWjZP_BsnOhUAFlsC9cwcJw_SsbU59TXaOeS32GV-XXbeorqipUOdQXVHPqlagvqYZGhnAFrcLcV6Vazu6rIMbzqGcwno3nH3yNQlxlMDXEg0CUbJuCi8IRXEU83O76RqCgnkPTL1rOSC-qBK3ucZiuGMVBAlRy0wS6eaY7KPimBjS3EeNWqTv3Ic4gNuqoQcfqTewClPf83EDM8FUt79dIAzizSRjdp7C2NvOzdJryKHsbndyUy7MpN129eRq9_PvC4GihzcKAHazPO8CjfdIkuc36P556W8BeF_OR6VNkqYz-niJZcqt36vfyhFizXMJC26TXyUcql4BPLdqBPSu-IODAJR2lFnjYHkrgq3M8ZvcXOYINPx2VI8TcdiSXadTvbEynyVo24FsnDRdziWxudzuPgCGZgLVuO-h2ctyqcY6czTZFq276hp8nhb3NC4SP3w9Hwzd1-0d_fzL4NH37Yvzq5fjwYDTsT79-GR89-7n_YfT9cNJ_Pnk9GH87mn48mHweXCSNmt-obFjZRz6sCMiz1YYNrS5xmBa4dAQmJkvasPDxgAETD4JElsNSxJWGhYhHygkjpYRIQhbh2VjZls4lUuxud5PLZLVsvKpxDM8_YWEkdKIiHSdxyBwRMdZeJivzEbceprlcWnMTL5Mb2TNoZf_wndbWzlYnevrgCT42dB3IKyeKWCFnEJk66K6SYu_xbnINKGsvvJ69N78A_g9wRg |
| linkProvider | EBSCOhost |
| openUrl | ctx_ver=Z39.88-2004&ctx_enc=info%3Aofi%2Fenc%3AUTF-8&rfr_id=info%3Asid%2Fsummon.serialssolutions.com&rft_val_fmt=info%3Aofi%2Ffmt%3Akev%3Amtx%3Ajournal&rft.genre=article&rft.atitle=%E5%9F%BA%E4%BA%8EL1%E8%8C%83%E6%95%B0%E7%9A%84%E5%88%86%E5%9D%97%E4%BA%8C%E7%BB%B4%E5%B1%80%E9%83%A8%E4%BF%9D%E6%8C%81%E6%8A%95%E5%BD%B1%E7%AE%97%E6%B3%95&rft.jtitle=%E8%AE%A1%E7%AE%97%E6%9C%BA%E5%B7%A5%E7%A8%8B%E4%B8%8E%E7%A7%91%E5%AD%A6&rft.au=%E4%B8%81%E9%93%AD+%E8%B4%BE%E7%BB%B4%E6%95%8F&rft.date=2017&rft.issn=1007-130X&rft.volume=39&rft.issue=3&rft.spage=519&rft.epage=523&rft_id=info:doi/10.3969%2Fj.issn.1007-130X.2017.03.017&rft.externalDocID=671704129 |
| thumbnail_s | http://utb.summon.serialssolutions.com/2.0.0/image/custom?url=http%3A%2F%2Fimage.cqvip.com%2Fvip1000%2Fqk%2F94293X%2F94293X.jpg http://utb.summon.serialssolutions.com/2.0.0/image/custom?url=http%3A%2F%2Fwww.wanfangdata.com.cn%2Fimages%2FPeriodicalImages%2Fjsjgcykx%2Fjsjgcykx.jpg |