小波域下基於四元數相關濾波器之人臉辨識

Face Recognition based on Quaternion Correlation Filters in Wavelet Domain

劉書瑋(Shu-Wei Liu)

指導教授 ： 陳文雄

國立暨南國際大學/科技學院/電機工程學系/碩士(2012年)

摘要

近年來相關濾波器常被用於目標物偵測、人臉辨識系統等圖型識別的問題上。當選擇適當的影像進行訓練，即可獲得不錯的辨識率。然而實際上環境照明、旋轉、表情等因素均會使得相關能量濾波器效能有所影響，尤其，環境照明造成的影響最為顯著。本篇論文首先介紹先進相關濾波器基本原理與四元數小波轉換的特性，隨後提出一種結合四元數小波轉換與最佳權衡最大平均相關高度濾波器（四元數＋OT-MACH）的新方法。可改善原先最小平均相關能量濾波器（MACE）不足的地方。實驗結果顯示選擇適當的權衡參數能減少環境照明對辨識系統的影響，提升辨識率與減少分類錯誤情況的產生。

關鍵字

相關濾波器 ； 人臉辨識 ； 照明影響 ； 小波轉換 ； 四元數 ； 四元數最大平均相關高度濾波器

並列摘要

Recently, correlation filter often been used to Object Detection, face recognition for pattern recognition problems. The recognition rates will be getting a good while choosing training images properly. But in fact, illumination, rotation, and expression and so on factor can mask it affect efficacy. Especially, the most obvious caused of illumination influence. This paper first introduces advanced correlation filters and quaternion wavelet transform characteristic, Then proposed new method a combination of the quaternion wavelet transform and the optimal trade-off the maximum average correlation height filter （quaternion + OT-MACH）. Can improve the deficiencies in the original minimum average correlation energy filter （MACE）. Experimental results show that the appropriate to choose trade-off parameter can decrease the environmental impact of lighting on the recognition system to enhance the recognition rate and reduce the generation of misclassification.

並列關鍵字

correlation filters ； face recognition ； illumination effect ； wavelet transform ； quaternion ； quaternion OT-MACH filter

參考文獻

[1] I. T. Jolliffe, Principal component analysis, Springer,2002.

[2] R. C. Gonzalez and R. E. Woods, Digital Image Processing, 3rd Edition, Prentice-Hall,2008.

[3] 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, 1997.

[4] B. V. K. V. Kumar, M. Savvides, and X. Chunyan, “Correlation Pattern Recognition for Face Recognition,” Proceedings of the IEEE, vol. 94, pp. 1963-1976, 2006.

[5] W. Zhao, R. Chellappa, P. J. Phillips, and A. Rosenfeld, “Face recognition: A literature survey,” ACM Comput. Surv., vol. 35, pp. 399-458, 2003.