摘要
近年來因為人臉驗證的廣泛應用及實際需求, 許多研究都致力於真實情境下的人臉驗證。我們可以從網路上蒐集大量的圖像資料, 並從而建立相關的資料庫, LFW 資料庫就是利用這方式建立, 作為評估不同演算法在現實中人臉驗證的表現的資料庫。 在這篇論文裡, 我們提出利用局部區塊的稀疏表示法來描述人臉影像的結構和特徵並把這個稀疏表示法的描述方式應用在人臉驗證上。稀疏編碼在過去的研究中顯示對抗雜訊是很穩健的, 我們從蒐集的人臉影像學習出具代表性的「字典」, 並且透過稀疏編碼利用這個字典來表示影像中的局部區塊。利用學習的字典和稀疏編碼, 我們在幾個資料庫上進行人臉驗證的實驗, 並提升了準確率。
關鍵字
人臉驗證參考文獻
[2] Nicolas Pinto, James J. DiCarlo, and David D. Cox. How far can you get with a modern face recognition test set using only simple features? Computer Vision and Pattern Recognition (CVPR), 2009.
[3] Neeraj Kumar, Alexander C. Berg, Peter N. Belhumeur, and Shree K. Nayar. Attribute and Simile Classifiers for Face Verification. International Conference on Computer Vision (ICCV), 2009.
[4] Eric Nowak and Frederic Jurie. Learning visual similarity measures for comparing never seen objects. Computer Vision and Pattern Recognition (CVPR), 2007.
[5] Matthieu Guillaumin, Jakob Verbeek, and Cordelia Schmid. Is that you? Metric Learning Approaches for Face Identification.International Conference on Computer Vision (ICCV), 2009.
[6] Hieu V. Nguyen and Li Bai. Cosine Similarity Metric Learning for Face Verification. Asian Conference on Computer Vision (ACCV), 2010.
延伸閱讀
- Lin, Y. Y. (2015). 利用稀疏表示法之人臉識別 [master's thesis, National Tsing Hua University]. Airiti Library. https://www.airitilibrary.com/Article/Detail?DocID=U0016-1908201515574962
- Chou, L. Y. (2007). 在個人相簿中以非臉部資訊輔助之人臉辨識 [master's thesis, National Taiwan University]. Airiti Library. https://doi.org/10.6342/NTU.2007.02279
- Yu, C. Y., & Ko, C. H. (2015). The Application of Facial Expression Recognition to the Evaluation of Stylized Images. 設計學研究, 18(1), 99-122. https://doi.org/10.30105/JDS.201507_18(1).0005
- 蕭士勛（2017）。Learning-based approach for occluded face verification〔碩士論文，淡江大學〕。華藝線上圖書館。https://www.airitilibrary.com/Article/Detail?DocID=U0002-3009201700405100
- Chang, H. M. (2010). Face Recognition Based on Local Image Descriptor [master's thesis, National Taiwan University]. Airiti Library. https://doi.org/10.6342/NTU.2010.00845