Loading...
|
Please use this identifier to cite or link to this item:
https://nccur.lib.nccu.edu.tw/handle/140.119/118961
|
| Title: | 臉部辨識多變量統計方法之比較及在行動裝置上的應用
A comparison of face recognition multivariate methods and an application to mobile devices |
| Authors: | 張群
Chang, Chun |
| Contributors: | 姜志銘
宋傳欽
張群
Chang, Chun |
| Keywords: | 臉部辨識
主成分分析
線性判別分析
二維主成分分析
二維線性判別分析
圖像前處理
行動裝置
Face recognition
Principal components analysis
Linear discriminant analysis
Two-dimensional principal components analysis
Two-dimensional linear discriminant analysis
Mobile device |
| Date: | 2018 |
| Issue Date: | 2018-07-27 12:16:28 (UTC+8) |
| Abstract: | 近幾年來，由於資訊安全上的需求，有越來越多臉部辨識的相關研究論文被提出來，並廣泛的被運用到各種不同的領域，包括智慧車(或自駕車)、金融科技、智慧零售、機器人、無人機、商業分析及預防犯罪威脅等，但是對於所擷取的影像，如頭部姿態、光線照明、背景複雜、年齡的增長等變化較大時，會造成辨識上的困難，所以影響辨識的因素以及如何提升系統的辨識率，也就成為值得研究的課題。
本論文首先比較幾個文獻上常被用來降維、分類的多變量特徵擷取技術，包含主成分分析、線性判別分析、二維主成分分析及二維線性判別分析等。我們將四種人臉資料庫(三種來自於文獻，一種為自建)中的每個資料庫分成兩半，其中一半做為訓練用，另一半做為測試用。實證結果顯示，當資料庫影像之頭部姿態變化幅度較小時，二維線性判別分析法在辨識上有不錯的績效，其平均辨識正確率達94%，次高者為線性判別分析法，其平均辨識正確率達92%。若將原始圖像先經過去除雜訊、增強影像等前處理後，主成分分析法與二維主成分分析法的辨識正確率可明顯增加。
最後，我們利用上述多變量分析的技術，開發一套臉部辨識的應用程式並將其解鎖功能應用於行動裝置上。我們也提出共變異數矩陣的更新迭代公式，將之應用於這一套應用程式，此公式可簡單地將已完成解鎖對象的臉部影像資料併入原有的共變異數矩陣中，以使臉部資訊保持在最新、最完整的狀態，而不需一再重新計算龐大且繁雜的共變異數矩陣。
Since the need of better security, more and more face recognition related research papers have been given in recent years. Their results are widely used in various fields, such as smart car (or self-driving car), FinTech, smart retail, robot, drone, business analysis, and crime prevention. However, when the content of images, such as head posture, lighting, complex background, and aging, has a big change, it is harder to recognize the right person. Therefore, the question of factors that influence the recognition result and how to improve the system recognition rate becomes an important research topic.
This paper first compares several common dimension reduction and classification techniques of multivariate analysis methods, including principal components analysis, linear discriminant analysis, two-dimensional principal components analysis and two-dimensional linear discriminant analysis, for feature extraction. We divide the data in each of our four databases into two halves. The first half is for training, while the second one is for testing. The empirical results show that when the changes of head postures are small, the two-dimensional linear discriminant analysis has a very good correct classification rate, which is 94% on average. The linear discriminant analysis has the second highest correct classification rate, which is 92% on average. In addition, if we pre-process the images, the correct classification rate increases a lot on each of principal components analysis and two-dimensional principal components analysis.
Finally, we give a new updating formula for computing covariance matrix. Using this new updating formula and our face recognition technique of principal components analysis. We develop a Graphical User Interface, which can unlock any personal computer. When new face image information is given, we update the covariance matrix through our proposed iteration method, which can easily keep the data for the face recognition in the latest and the most complete state without recalculating the huge and complicated covariance matrix. |
| Reference: | Belhumeur, P. N., Hespanha, J. P. and Kriegman, D.J. (1997). Eigenfaces vs. Fisherfaces: Recognition using class specific linear projection. IEEE Transactions on Pattern Analysis and Machine Intelligence, 19 (7), 711-720.
Doukas, C. and Maglogiannis, I. (2010). A fast mobile face recognition system for android OS based on Eigenfaces decomposition. Proc. of Artificial Intelligence Applications and Innovations, vol. 339 AICT, pp. 295-302.
Johnston, R. and Wichern, D. (2007). Applied multivariate statistical analysis. Prentice Hall, Upper Saddle River, NJ, 6th edition.
Kazemi, V. and Sullivan, J. (2014). One millisecond face alignment with an ensemble of regression trees. 2014 IEEE Conference on Computer Vision and Pattern Recognition.
Krzanowski, W., Jonathan, P., McCarthy, W., & Thomas, M. (1995). Discriminant Analysis with Singular Covariance Matrices: Methods and Applications to Spectroscopic Data. Journal of the Royal Statistical Society. Series C (Applied Statistics), 44(1), 101-115. doi: 10.2307/2986198
Li, M. and Yuan, B. (2005). 2D-LDA: a statistical linear discriminant analysis for image matrix. Pattern Recognition Letter, 26(5): 527-532.
Swets, D. L. and Weng, J. J. (1996). Using discriminant eigenfeatures for image retrieval. IEEE Transactions on Pattern Analysis and Machine Intelligence, 18(8): 831–836,
Turk, M. and Pentland, A. (1991a). Eigenfaces for Recognition. J. Cognitive Neuroscience, vol. 3, no. 1, pp.71-86.
Turk, M. and Pentland, A. (1991b). Face Recognition Using Eigenfaces. Proceedings of IEEE Conferecnce on Computer Vision and Pattern Recognition, pp. 586-591.
Viola, P. and Jones, M. J. (2004). Robust Real-Time Face Detection. International Journal of Computer Vision, Vol. 57, No. 2, pp. 137-154.
Yang, J., Zhang, D., Frangi, A. F. and Yang, J. Y. (2004). Two-Dimensional PCA：A New Approach to Appearance-•Based Face Representation and Recognition. IEEE Transactions on Pattern Analysis and Machine Intelligence, 26(1): 131-137. |
| Description: | 碩士
國立政治大學
應用數學系
104751001 |
| Source URI: | http://thesis.lib.nccu.edu.tw/record/#G1047510011 |
| Data Type: | thesis |
| DOI: | 10.6814/THE.NCCU.MATH.004.2018.B01 |
| Appears in Collections: | [應用數學系] 學位論文
|
Files in This Item:
| File |
Size | Format | |
|---|
| 01.pdf | 2911Kb | Adobe PDF2 | 189 | View/Open |
|
All items in 政大典藏 are protected by copyright, with all rights reserved.
|
