近年來由於個人安全問題日益受到重視，於是許多身份辨認的機制迅速應運而生。相較於指紋辨識系統，由於人臉辨識系統不需與人們作身體上的碰觸，使用上較為方便因而成為重要的辨識機制。然而單獨使用可見光影像的人臉辨識系統具有因其辨識率深受環境照明度影響，同時亦較容易因他人試圖拿本人之照片矇騙而使得辨識系統產生錯誤判斷。因此利用同時拍攝之可見光影像與熱影像進行融合之後產生之融合影像進行人臉辨識可降低上述單獨使用可見光影像之人臉辨識系統之缺點。
本論文根據利用離散小波係數作可見光影像與熱影像融合之方法，提出了一個動態可見光影像與熱影像係數融合比例之方法，此方法可隨著可見光影像照明度的不同而動態調整可見光影像與熱影像的融合比例，然後再利用每一人連續多張融合影像進行線性鑑別式分析(Linear Discriminant Analysis，LDA)將融合後影像之特徵參數加以轉換，最後利用歐氏距離來進行人臉歸屬之辨識。由於利用每人連續多張影像再加上本論文所提出之動態調整融合比例之融合方法，因此可以降低環境照明度的影響，以提升安全性與辨識率。
由實驗結果顯示出，在環境照明度不均勻的情況下，利用本論文所提出動態調整可見光影像與熱影像融合比例之融合方法，在一人連續多張融合影像進行辨識所得到的辨識率能比以往所提出之可見光影像與熱像之融合方法所得到的辨識率來得高。證明利用本論文所提出之融合方法可進一步降低環境照明度的影響、提升安全性與辨識率。

Because people have paid more and more attention on the issue of personal safety in recent years, as a result, there are many identification mechanisms produced rapidly. Compared to the fingerprint recognition system, as a result of face recognition system for people without physical touch, it is more convenient to use and thus become an important identification mechanism. However, for the face recognition systems which only use visible images, it’s recognition rate greatly affected by environmental illumination, and vulnerable to other people trying to fool the system by the photographs and made an error recognition. Use the fusion images fused of visible images and thermal images taken at the same time to perform face recognition can reduce the above-mentioned drawbacks of the face recognition system which only use visible images.
In this paper, we use DWT coefficients to fuse visible and thermal images, and propose a fusion method which dynamically adjust the fusion proportion of visible and thermal images. This method can dynamically adjust the fusion proportion of visible and thermal images depends on the difference of illumination of visible images. Then we use multiple fusion images of every person to perform LDA to transform character parameters of fusion images. Finally, the use of Euclidean distance to the vesting of face recognition. The use of multiple images of every person and the fusion method proposed in this paper, thus can reduce the influence of environmental illumination to enhance the security and recognition rate.
The experimental results show that non-uniform illumination in the environment, the recognition rate by using the fusion method proposed in this paper to adjust dynamically the fusion proportion of visible and thermal images can be better than that by using the fusion method proposed previously to fuse visible and thermal images when both using multiple fusion images of every person. Prove that the use of the fusion method proposed in this paper can further reduce the influence of environmental illumination to enhance the security and recognition rate.

Oh-Kyu Kwon, and Seong G. Kong, “Multiscale Fusion of Visual and Thermal Images for Robust Face Recognition” , IEEE International Conference on Computer Intelligence for Homeland Security and Personal Safetys, pp. 112-116, Mar 2005.
Peter N. Belhumeur, Joao P. Hespanha, and David J. Kriegman, “Eigenfaces vs. Fisherfaces: Recognition Using Class Specific Linear Projection” , IEEE Transactions on Pattern Analysis and Machine Intelligence, Vol. 19, No. 7, pp.711-720, Jul 1997.
Xuan Zou, Josef Kittler, and Kieron Messer, “Illumination Invariant Face Recognition: A Survey” , IEEE International Conference on Digital Object Identifier, pp.1-8, Sept 2007.
Seong G. Kong , Jingu Heo, Besma R. Abidi, Joonki Paik, and Mongi A. Abidi, “Recent advances in visual and infrared face recognition – a review”,Computer Vision Image Understanding, Vol. 97, No. 1, Jan 2004.
W.S. Lee, H.J. Lee, and J.H. Chung, “Wavelet-Based FLD for Face Recognition”, Proc. IEEE Midwest Symp. on Circuits and Systems,Lansing MI, pp.734-737, Aug 2000.
C. Liu, and H. Wechsler, “Gabor Feature Based Classification Using the Enhanced Fisher Linear Discriminant Model for Face Recognition”,Proc. of IEEE Trans. on Image Processing, Vol.11, pp.467- 476, 2002.
http://www.equinoxsensors.com/products/HID.html
Thomas Little Heath, “The Thirteen Books of Euclid’s Elements”, Dover Pubns, June 1956.
http://www.cl.cam.ac.uk/research/dtg/attarchive/facedatabase.html
賴明志, “基於小波與LDA演算法之人臉辨識研究”,大葉大學電機工程學系碩士班碩士論文,2006.
R. Brunelli, and T. Poggio, “Face recognition: Features versus templates”, IEEE Trans. Pattern Analysis and Machine Intelligence, Vol. 15, pp.1042-1052, 1993.
T. Kanade, “Picture Processing by Computer Complex and Recognitionof Human Faces,” PhD thesis, Kyoto University, 1973.
Xiaoming Liu, Tsuhan Chen, and B.V.K. Vijaya Kumar, “Face Authentication for Multiple Subjects Using Eigenflow”, Pattern Recognition, special issue on Biometric, Vol. 36, Issue 2, pp. 313-328, Feb. 2003.
M. Turk ,and A. Pentland, “Eigenfaces for Recognition”, Jour. Of Cognitive Neuroscience,Vol. 3, pp.71-86, 1991.
Lawrence, S. , Giles, C.L. , Ah Chung Tsoi; Back, A.D. , “ Face recognition: a convolutional neural-network approach”, IEEE Transactions on Neural Networks ,Vol. 8 Issue: 1 , pp.98-113, Jan. 1997.
Xiaoguang Jia, Mark S. Nixon, “Extending the Feature Vector for Automatic Face Recognition”, IEEE Transactions on Pattern Analysis and Machine Intelligence, Vol. 17, No. 12, pp.1167-1176, Dec. 1995.
Shang-Hung, L., K. Sun-Yuan, and L. Long-Ji, “Face recognition/ detection by probabilistic decision-based neural network”, IEEE Transactions on Neural Networks, Vol. 1, Issue 8, pp.114-132, Jan. 1997.
R. A. Fisher, Sc. D., and F. R.S., “The Use of Multiple Measurements in Taxonomic Problems.”, Annals of Eugenics, Vol. 7, pp.179-188, 1936.
J.D. Woodward., “Biometrics:Privacy’s Foe or Privacy’s friend?.”, Proceeding of the IEEE, Vol 85, Issue 9, pp.1479-1492, 1997.
B. Miller., “Everything you need toknow about automated biometric identification.”, Security Technol., April 1997.
Y. Yoshitomi, T. Miyaura, Tomita, S. Kimura, “Face identification using thermal image processing.”, IEEE International Workshop on Robot and Human Communication, pp.374-379, 1997.
F. Prokoski, “History, current status, and future of infrared identification.”, IEEE Workshop on Computer Vision Beyond the Visible Spectrum : Methods and Applications, pp.5-14, 2000.
F. Prokoski, R.Riedel, J. Coffin, “Identification of individuals by means of facial thermography.”, Security Technology, pp.120-125,1992.
Kamran Etemad, Rama Chellappa, “Discriminant Analysis for Recognition of Human Face Images”, Journal of the Optical Society of America A, Vol. 14, No. 8, pp. 1724-1733, Aug. 1997.
J. Wilder, P. J. Phillips, C. Jiang, and S. Wiener, “Comparison of visible and infrared imagery for face recognition.”, In Proc. IEEE AFGR , 1996.