Skip navigation

DSpace

機構典藏 DSpace 系統致力於保存各式數位資料(如:文字、圖片、PDF)並使其易於取用。

點此認識 DSpace
DSpace logo
English
中文
  • 瀏覽論文
    • 校院系所
    • 出版年
    • 作者
    • 標題
    • 關鍵字
    • 指導教授
  • 搜尋 TDR
  • 授權 Q&A
    • 我的頁面
    • 接受 E-mail 通知
    • 編輯個人資料
  1. NTU Theses and Dissertations Repository
  2. 電機資訊學院
  3. 資訊工程學系
請用此 Handle URI 來引用此文件: http://tdr.lib.ntu.edu.tw/jspui/handle/123456789/55986
完整後設資料紀錄
DC 欄位值語言
dc.contributor.advisor徐宏民(Winston H. Hsu)
dc.contributor.authorChia-Hung Linen
dc.contributor.author林家宏zh_TW
dc.date.accessioned2021-06-16T05:12:20Z-
dc.date.available2019-09-02
dc.date.copyright2014-09-02
dc.date.issued2014
dc.date.submitted2014-08-18
dc.identifier.citation[1] T. Ahonen, A. Hadid, and M. Pietikainen. Face recognition with local binary patterns. In ECCV, 2004.
[2] S. Baluja and H. A. Rowley. Boosting sex identification performance. International Journal of Computer Vision, 71:111–119, 2007.
[3] A. Bosch, A. Zisserman, and X. Munoz. Representing shape with a spatial pyramid kernel. In CIVR, 2007.
[4] B.-C. Chen, Y.-Y. Chen, Y.-H. Kuo, and W. H. Hsu. Scalable face image retrieval using attribute-enhanced sparse codewords. IEEE Transactions on Multimedia, 15:1163–1173, 2013.
[5] B. Datta. Numerical Linear Algebra and Applications. Brooks/Cole Pub., 1995.
[6] R.-E. Fan, K.-W. Chang, C.-J. Hsieh, X.-R. Wang, and C.-J. Lin. Liblinear: A library for large linear classification. J. Mach. Learn. Res., 9:1871–1874, 2008.
[7] M. R. Gary B. Huang et al. Labeled faces in the wild: A database for studying face recognition in unconstrained environments. Technical Report 07-49, University of Massachusetts, Amherst, 2007.
[8] G. B. Huang and V. Jain. Unsupervised joint alignment of complex images. In ICCV, 2007.
[9] N. Kumar, P. N. Belhumeur, and S. K. Nayar. FaceTracer: A Search Engine for Large Collections of Images with Faces. In ECCV, 2008.
[10] N. Kumar, A. C. Berg, P. N. Belhumeur, and S. K. Nayar. Attribute and Simile Classifiers for Face Verification. In ICCV, 2009.
[11] J. Langford, T. Zhang, D. J. Hsu, and S. M. Kakade. Multi-label prediction via compressed sensing. In NIPS. 2009.
[12] J. Li, T. Wang, and Y. Zhang. Face recognition using feature of integral gabor-haar transformation. In ICIP, 2007.
[13] B. Moghaddam and M.-H. Yang. Learning gender with support faces. IEEE Trans. Pattern Anal. Mach. Intell., 24:707–711, 2002.
[14] T. Ojala, M. Pietikainen, and D. Harwood. A comparative study of texture measures with classification based on featured distributions. Pattern Recognition, 29(1):51–59, 1996.
[15] F. Pedregosa, G. Varoquaux, A. Gramfort, and others. Scikit-learn: Machine learning in Python. Journal of Machine Learning Research, 12:2825–2830, 2011.
[16] W. Scheirer, N. Kumar, P. N. Belhumeur, and T. E. Boult. Multi-attribute spaces: Calibration for attribute fusion and similarity search. In CVPR, 2012.
[17] B. Siddiquie, R. S. Feris, and L. S. Davis. Image ranking and retrieval based on multi-attribute queries. In CVPR, 2011.
[18] F. Tai and H.-T. Lin. Multilabel classification with principal label space transformation. Neural Computation, 24(9):2508–2542, 2012.
[19] M. Uřičař, V. Franc, and V. Hlavač. Detector of facial landmarks learned by the structured output SVM. In G. Csurka and J. Braz, editors, VISAPP. SciTePress — Science and Technology Publications, 2012.
dc.identifier.urihttp://tdr.lib.ntu.edu.tw/jspui/handle/123456789/55986-
dc.description.abstract近年來,人臉屬性在電腦視覺及影像處理研究內是很重要的資訊,可被利用於分類、辨識、檢索等研究方向。隨著多媒體相關研究的蓬勃發展,對人臉屬性類別的需求也逐漸增加,不僅僅侷限在簡單的性別、年紀、種族等資訊, 但越多的人臉屬性類別,也會導致在處理龐大資訊時的計算量及空間需求量大增。因此,我們提出了潛在人類型別(Latent Human Topic-LHT) 的概念來取代人臉屬性類別,減少其數量,以達到有效率的壓縮。LHT 代表的是一個多種人臉屬性關係之間的組合,藉由奇異值分解 (Singular Value Decomposition-SVD) 來尋找各人臉屬性之間的關係組合,因此可以將原本數量眾多的人臉屬性類別替換成數量較少的 LHT 類別來達到壓縮的目的。同時藉由 LHT 也可以簡單的做到人臉屬性偵測,在我們提出的方法中,利用 LHT 來取代原有的人臉屬性並利用機器學習的方法學習 LHT 模型以做到 LHT 偵測,最後僅需要將偵測出來的 LHT 數值經過快速的重建運算,即可還原為原始的各項人臉屬性。由於 LHT 的概念是從資料中去學習人臉屬性之間的關係,所以仍然可以保留各項人臉屬性的資訊,因此在人臉屬性偵測的實驗中,利用數量較少的 LHT 來偵測人臉屬性仍可以達到與傳統方法近乎相同的準確率,但由於 LHT 的數量遠少於初始的人臉屬性類別數量,所以在偵測時的運算量及所需要的儲存空間都可以大為減少。尤其是在有限硬體資源的裝置上,如:手機或其他行動無線裝置,會有更大的需求希望可以在達到相同準確率下,節省更多計算資源及儲存空間,因此,我們提出的 LHT 將可以滿足這項需求。zh_TW
dc.description.abstractFacial attribute is important information for a variety of machine vision tasks including recognition, classification, and retrieval. There arises a strong need for detecting various facial attributes such as gender, age and more which consume more computation and storage resources. Therefore, we propose a compression framework to find fewer significant Latent Human Topics (LHT) to approximate more facial attributes. LHT is a combination of attribute correlation by transferring facial attribute space to compressional space with Singular Value Decomposition (SVD). Using the proposed scheme, we can easily detect the facial attributes from a face image via fast reconstructing the compressed labels automatically detected by a few LHT classifiers. Experimental results show that our system can achieve similar performance with substantially fewer dimensions compared to the original number of facial attributes, and it even shows slight improvements because LHT carry informative at tribute correlations learned from data.en
dc.description.provenanceMade available in DSpace on 2021-06-16T05:12:20Z (GMT). No. of bitstreams: 1
ntu-103-R01922051-1.pdf: 1402932 bytes, checksum: 3a83bf0d0e194c6d3d07a54d4c97b98d (MD5)
Previous issue date: 2014
en
dc.description.tableofcontents口試委員會審定書 i
誌謝 ii
摘要 iii
Abstract iv
1 Introduction 1
2 Related Work 4
2.1 Related works for facial attributes . . . . . . . . . . . . . . . . . . . . . 4
2.2 Related works for facial attribute correlation and label space compression 5
2.2.1 Facial attribute correlation . . . . . . . . . . . . . . . . . . . . . 5
2.2.2 Label space compression . . . . . . . . . . . . . . . . . . . . . . 6
3 Facial Attribute Space Compression by Latent Human Topic Discovery 7
3.1 System Framework . . . . . . . . . . . . . . . . . . . . . . . . . . . . . 7
3.2 Facial Attribute Space Compression . . . . . . . . . . . . . . . . . . . . 8
3.3 Latent Human Topic Detection . . . . . . . . . . . . . . . . . . . . . . . 9
3.3.1 Feature Extraction . . . . . . . . . . . . . . . . . . . . . . . . . 10
3.3.2 Ensemble learning . . . . . . . . . . . . . . . . . . . . . . . . . 10
3.4 Facial Attribute Reconstruction . . . . . . . . . . . . . . . . . . . . . . . 10
4 Dataset - LFW-attribute Dataset 12
5 Experiments 14
5.1 Attribute Correlation Matrix . . . . . . . . . . . . . . . . . . . . . . . . 14
5.2 Latent Human Topic Detection in Different Compression Level . . . . . . 15
6 Conclusions and future works 18
Bibliography 19
dc.language.isoen
dc.subject屬性關係zh_TW
dc.subject人臉屬性偵測zh_TW
dc.subject壓縮zh_TW
dc.subjectFacial attribute detectionen
dc.subjectCompressionen
dc.subjectAttribute correlationen
dc.title藉由探索潛在的人類型別壓縮人臉的屬性空間zh_TW
dc.titleFacial Attribute Space Compression by Latent Human Topic Discoveryen
dc.typeThesis
dc.date.schoolyear102-2
dc.description.degree碩士
dc.contributor.oralexamcommittee陳文進(Wen-Chin Chen),陳祝嵩(Chu-Song Chen)
dc.subject.keyword人臉屬性偵測,壓縮,屬性關係,zh_TW
dc.subject.keywordFacial attribute detection,Compression,Attribute correlation,en
dc.relation.page20
dc.rights.note有償授權
dc.date.accepted2014-08-19
dc.contributor.author-college電機資訊學院zh_TW
dc.contributor.author-dept資訊工程學研究所zh_TW
顯示於系所單位:資訊工程學系

文件中的檔案:
檔案 大小格式 
ntu-103-1.pdf
  未授權公開取用
1.37 MBAdobe PDF
顯示文件簡單紀錄


系統中的文件,除了特別指名其著作權條款之外,均受到著作權保護,並且保留所有的權利。

社群連結
聯絡資訊
10617臺北市大安區羅斯福路四段1號
No.1 Sec.4, Roosevelt Rd., Taipei, Taiwan, R.O.C. 106
Tel: (02)33662353
Email: ntuetds@ntu.edu.tw
意見箱
相關連結
館藏目錄
國內圖書館整合查詢 MetaCat
臺大學術典藏 NTU Scholars
臺大圖書館數位典藏館
本站聲明
© NTU Library All Rights Reserved