不均勻的照明條件是影響臉型識別系統效能的關鍵之一。不均勻的照明條件對影像明暗變化的影響是平滑而緩慢的，HOG Feature從局部的角度切入，因此在不同的照明條件下有不錯的辨識能力；然而在明暗變化的交界處由於灰階值變化劇烈，因此HOG Feature會產生不穩定的現象。

本論文針對此特性，提出基於光照條件之動態加權HOG臉型辨識方法，抽取局部特徵周遭的Illumination Feature，並藉由Illumination Feature的差異判定HOG Feature是否穩定;我們依照特徵穩定性提出兩種改善辨識率方法：（1）針對不穩定的HOG Feature本身進行修正。（2）根據整體照明條件改善比對方法。第一個方法利用HOG本身的特性，HOG以統計定位點周遭的梯度大小、方向來描述臉部細節，此特性與不均勻的照明具有方向性的性質類似，因此偵測不均勻照明發生的位置、方向進行HOG Feature補償。而第二個方法我們加入五官、輪廓定位點資訊（Shape Feature），然後根據照明條件的差異，分配HOG Feature與Shape Feature在比對中的權重。

本論文採用CMU PIE臉型資料庫。實驗結果顯示Illumination Feature可以成功的描述局部特徵周遭的照明條件，並依此判定定位點之HOG Feature是否受到不均勻的照明影響。在這樣的基礎上，我們更進一步的以受到不均勻影響照明的定位點數目及受影響的方向量化出影像的整體照明條件，然後根據照明條件差異分配HOG Feature與Shape Feature在的權重，達到基於光照條件之動態加權HOG臉型辨識，並成功的使FAR 1%時的FRR從2.8%降至1.5%。

Varying lighting conditions affects the performance of a facial recognition system. HOG is robust feature to use under lighting variations as image brightness changes smoothly and slowly. However, under severe changes in brightness, for example boundaries of light and shade, the HOG feature becomes unstable.

This thesis proposes Face Recognition Using Dynamically Weighted HOG Based on Illumination Conditions. This method extracts Illumination Feature around the landmarks of local features, and evaluates the stability of HOG feature by Illumination Feature differences. Two methods are proposed to improve the recognition rate: (1) Amend unstable HOG feature itself. (2) Improve matching algorithm according to the overall lighting condition. The first method uses the characteristics of the HOG feature. HOG uses the gradient orient and intensity to describe facial details around landmarks, which is similar to the characteristics of directional lighting variations. Therefore, detecting the location (and direction) of lighting variation will allow amendments to HOG feature. The second method involves adding facial landmarks coordinate as Shape feature to determine the weighting of both HOG and Shape feature according to the overall lighting conditions.

Experimental results on CMU PIE database show that Illumination feature can describe the lighting conditions around landmarks successfully. On this basis, we further quantify the overall lighting conditions by the numbers and directions of landmarks under varying lighting conditions. The weighting of both HOG and Shape feature can be determined based on overall lighting conditions, and reduce the FRR from 2.8% to 1.5%. This achieves Face Recognition Using Dynamically Weighted HOG Based on Illumination Conditions.

[1] A. K. Jain, "Biometric recognition: Q&A", Nature, vol. 449, pp. 38-40, September 2007.
[2] A. K. Jain, A. Ross, and S. Prabhakar, "An Introduction to Biometric Recognition", IEEE Transactions on Circuits and Systems for Video Technology, Special Issue on Image- and Video-Based Biometrics, vol. 14, no. 1, pp. 4-20, January 2004.
[3] Stan Z. Li and Anil K. Jain, "Handbook of Face Recognition",2nd ed,2011 .
[4] T. Kanade, "Picture Processing System by Computer Complex and Recognition of Human Faces", doctoral dissertation Kyoto University, November 1973.
[5] M. A. Turk and A. P. Pentland, "Eigenfaces for recognition", Journal of Cognitive Neuroscience, vol. 3, MIT Press, January 1991.
[6] M. A. Turk and A. P. Pentland, "Face recognition using eigenfaces", IEEE Computer Society Conference on Computer Vision and Pattern Recognition, pp. 586 -591, January 1991
[7] L. Sirovich and M. Kirby, "Low-dimensional procedure for the characterization of human faces", Journal of the Optical Society of America vol. 4, pp. 519-524, March 1987.
[8] M. Kirby and L. Sirovich, "Application of the Karhunen-Lokve Procedure for the Characterization of Human Faces", IEEE Transactions on Pattern Analysis and Machine Intelligence. vol. 12, pp. 103-108, January 1990.
[9] R. Brunelli and T. Poggio, "Face recognition: Features versus templates". IEEE Transactions on Pattern Analysis and Machine Intelligence, vol. 15, pp. 1042-- 1052, October 1993.
[10] P. N. Belhumeur, J. P. Hespanha, and D. J. Kriegman, "Eigenfaces vs. Fisherfaces Recognition using class specific linear projection", IEEE Transactions on Pattern Analysis and Machine Intelligence. Vol. 19, pp. 711-720, July 1997.
[11] M.-H. Yang, N. Ahuja, and D. Kriegman, " Face recognition using kernel eigenfaces ", In Proceedings of the IEEE International Conference on Image Processing, vol. 1, pp. 37-40, September 2000.
[12] S. Mika, G. Ratsch, J. Weston, B. Scholkopf, and K.-R. Mller, " Fisher discriminant analysis with kernels ", Neural Networks for Signal Processing IX, August 1999.
[13] B. Schölkopf, A. Smola, and K. R. Müller, "Nonlinear component analysis as a kernel eigenvalue problem", Neural Computation, vol. 10, No. 5, Pages 1299-1319, July 1999.
[14] John C. Lee and E. Milios, "Matching Range Images of Human Faces", International Conference on Computer Vision, pp. 722-726, December 1990.
[15] H. Tanaka and M.Ikeda and H. Chiaki, "Curvature-based Face Surface Recognition Using Spherical Correlation", Third International Conference on Automated Face and Gesture Recognition, pp. 372-377, April 1998.
[16] B. Achermann, H. Bunke , "Classifying range images of human faces with Hausdorff distance", 15th International Conference on Pattern Recognition, pp. 809-813, September 2000.
[17] G. Pan, Z. Wu, Y. Pan , "Automatic 3D face verification from range data", International Conference on Multimedia and Expo, vol. 3, pp. 133-136, July 2003.
[18] Y. Lee, J. Shim , "Curvature-based human face recognition using depth-weighted Hausdorff distance", International Conference on Image Processing, vol. 3, pp. 1429-1432, August 2004.
[19] T.D. Russ, M.W. Koch, C.Q , "A 2D range Hausdorff approach for 3D face recognition", IEEE Computer Society Conference on Computer Vision and Pattern Recognition, pp. 169, June 2005.
[20] C. Hesher, A. Srivastava, G. Erlebacher, "A novel technique for face recognition using range imaging", 7th International Symposium on Signal Processing and Its Applications, vol. 2, pp. 201-204, July 2003.
[21] G. Pan, Z. Wu, Y. Pan, "Automatic 3D face verification from range data", International Conference on Multimedia and Expo, vol. 3, July 2003.
[22] P. and N. McKay , "A Method for Registration of 3-D Shapes", IEEE Transactions on Pattern Analysis and Machine Intelligence, vol. 14, pp. 239-256, February 1992.
[23] Z. Zhang, "Iterative point matching for registration of free-form curves and surfaces", International Journal of Computer Vision, vol. 13, pp. 119-152, October 1994.
[24] F. Tsalakanidou a, D. Tzovaras b, "Use of depth and colour eigenfaces for face recognition", Pattern Recognition Letters, vol. 24, pp. 1427-1435, June 2003.
[25] X. Lu and A. K. Jain, "Integrating Range and Texture Information for 3D Face Recognition", 7th IEEE Workshops on Application of Computer Vision, vol. 1, pp. 156-163, January 2005.
[26] W.-S. Chu, J.-C. Chen, J.-J. James Lien, "Kernel discriminant transformation for image set-based face recognition", Pattern Recognition Volume 44, Issue 8, pp. 1567–1580 , August 2011.
[27] L. Shen and J. He, "Face Recognition with Directional Local Binary Patterns ", 6th Chinese conference on Biometric recognition, vol. 7098, pp. 6-10, 2011.
[28] Y. Li, J. Feng, "Adaptive Patch Alignment Based Local Binary Patterns For Face Recognition", First Asian Conference on Pattern Recognition, pp. 269-272, November 2011.
[29] O. Déniz, G. Buenoa, J. Salidoa, F. De la Torre,” Face recognition using Histograms of Oriented Gradients.”, Pattern Recognition Letters, vol. 32, pp. 1598–1603, September 2011.
[30] C.-N. Fan, F.-Y. Zhang, "Homomorphic Filtering Based Illumination Normalization Method For Face Recognition", Pattern Recognition Letters, vol. 32, pp. 1468-1479, July 2011.
[31] John Wright, Allen Y. Yang,Arvind Ganesh, S. Shankar Sastry, and Yi Ma, "Robust Face Recognition via Sparse Representation", IEEE Transactions on Pattern Analysis and Machine Intelligence, vol. 31, no. 2, pp. 210-227, February 2009.
[32] R. Rammamorthi and P. Hanrahan. “A Signal-Processing Framework for Inverse Rendering.” 28th annual conference on Computer graphics and interactive techniques, pp. 117-128, 2001.
[33] R. Basri and D. W. Jacobs. “Lambertian Reflectance and Linear Subspaces”. IEEE Transactions on Pattern Analysis and Machine Intelligence, vol. 25, no. 2, pp. 218-223, February 2003.
[34] R. Ramamoorthi. “Analytic PCA Construction for Theoretical Analysis of Lighting Variability in Images of a Lambertian Object”. IEEE Transactions on Pattern Analysis and Machine Intelligenc, vol. 24, no.10, pp. 1322-1333, October 2002.
[35] H. Han, S. Shan, X. Chen, W. Gao.” Illumination Transfer Using Homomorphic Wavelet Filtering and Its Application to Light-Insensitive Face Recognition”, 8th IEEE International Conference on Automatic Face & Gesture Recognition, pp. 1-6, September 2008.
[36] S. G. Mallat. “A Theory for Multiresolution Signal Decomposition: The Wavelet Representation”. IEEE Transactions on Pattern Analysis and Machine Intelligence, vol. 11, pp. 674-693, July 1989.
[37] R. C. Gonzalez, R. E. Woods. “Digital Image Processing”. Prentice Hall, 2002.
[38] W. L. Chen, E. M. Joo and S. Wu. “Illumination Compensation and Normalization for Robust Face Recognition using Discrete Cosine Transform in Logarithm domain.” IEEE Transactions on Systems, Man and Cybernetics, Part B, vol. 36, pp. 458-466, April 2006.
[39] R. Basri and D. Jacobs. “Photometric Stereo with General Unknown Lighting.”
IEEE Computer Society Conference on Computer Vision and Pattern Recognition, vol. 2, pp. 374-381, 2001.
[40] S. Amnon and R. R. Tammy. “The Quotient Image: Class-Based Re-rendering and Recognition with Varying Illuminations.” IEEE Transactions on Pattern Analysis and Machine Intelligence, vol. 23, pp. 29-39, February 2001.
[41] P. Yang, S. Shan, W. Gao, Stan Z. Li, D. Zhang. “Face Recognition Using Ada-Boosted Gabor Features.”, 6th IEEE International Conference on Automatic Face and Gesture Recognition, pp. 356-361, May 2004.
[42] T. Ahonen, A. Hadid, and M. Pietik¨ainen,” Face Recognition with Local Binary Patterns.” 8th European Conference on Computer Vision, pp. 469-481, May 2004.
[43] N. Dalal, B. Triggs,” Histograms of Oriented Gradients for Human Detection”, International Conference on Computer Vision & Pattern Recognition , vol. 1, pp. 886-893, June 2005.
[44] T.F. Cootes, G.J. Edwards, C.J. Taylor,” Active Appearance Models”, IEEE Transactions on Pattern Analysis and Machine Intelligence, vol. 23, pp.681-685, June 2001.
[45] T.F. Cootes, C.J. Taylor, D.H.Cooper, J. Graham,” Active Shape Models-Their Training and Application”, Computer Vision and Image Understanding, Volume 61, Issue 1, pp. 38-59, January 1995.
[46] X. Yang, G. Su, J. Chen, N. Su, X. Ren, "Large scale identity deduplication using face recognition based on facial feature points", 6th Chinese conference on Biometric recognition, pp. 25-32, 2011.
[47] T. Sim, S. Baker, and M. Bsat ,“The CMU Pose, Illumination, and Expression (PIE) Database”, IEEE Transactions on Pattern Analysis and Machine Intelligence, vol. 25, pp. 1615-1618, December 2002.