基於縮放自商影像的低複雜度之 抗光影變化人臉辨識系統

Low Cost Illumination Invariant Face Recognition by Down-Up Sampling Self Quotient Image

林立(Lin, li)

指導教授 ： 邱瀞德

國立清華大學/電機資訊學院/資訊工程學系/碩士(2013年)

https://doi.org/10.6843/NTHU.2013.00709

摘要

流明改變在一般的環境中常常會造成人臉辨識的效率降低．自商影像(SQI)是一種移除光影變化的方法，但是也需要較多的運算時間．因此，我們提出了一種快速的人臉辨識方法，利用影像縮放來產生自商影像(DUSSQI)的方式來移除光影的影響．而DUSSQI有下列的優點(1)有效的移除光影影響 (2)提取不同的臉部細節，像是材質以及邊緣　(3)由於全域的運算方式降低了計算的花費．我們也使用主成分分析來降低相似度比較過程的運算時間．實驗結果顯示我們的方法在extended YaleB database達到98.3%的辨識率，在FERET database中達到93.8%的辨識率，並且比原本的SQI方法降低了97.1%的計算時間．相似度比較的處理時間與原本沒有使用PCA的DUSSQI相比，降低了70.4%．

關鍵字

人臉辨識 ； 光影移除

並列摘要

Illumination variation generally causes performance degradation of face recognition systems under real-life environments. The Self Quotient Image (SQI) method cite{SQI} is proposed to remove extrinsic lighting effects but requires high computation complexity. Therefore, we propose a low cost face recognition scheme that uses multi-scale down-up sampling to generate self quotient image (DUSSQI) to remove the lighting effects. The DUSSQI has the following advantages: (1) Remove the lighting influence effectively. (2) Extract different face details including texture and edges. (3) Only global operation on pixels is required to reduce computational cost. We also use principal component analysis (PCA) to reduce the process time in feature similarity comparison stage. Experimental results demonstrate that our proposed approach achieves 98.3\% recognition rate for extended YaleB database and 93.8\% for FERET database under various lighting conditions and reduces 97.1\% computational time compared to that of SQI. The processing time in the similarity comparison stage also reduces 70.4\% compared to that of the original DUSSQI without PCA.

並列關鍵字

face recognition ； illumination invariance ； image scaling ； quotient image

參考文獻

[2] N. McLaughlin, J. Ming, and D. Crookes, "Illumination invariant facial recognition using a piecewise-constant lighting model,“ in Acoustics, Speech and Signal Processing (ICASSP), 2012 IEEE International Conference on, march 2012, pp. 1537 -1540.

[3] X. Tan and B. Triggs, "Enhanced local texture feature sets for face recognition under dicult lighting conditions,“ Image Processing, IEEE Transactions on, vol. 19, no. 6, pp. 1635-1650, 2010.

[4] W. Chen, M.-J. Er, and S. Wu, "Illumination compensation and normalization for robust face recognition using discrete cosine transform in logarithm domain," Systems, Man, and Cybernetics, Part B: Cybernetics, IEEE Transactions on, vol. 36, no. 2, pp. 458-466, 2006.

[5] T. Zhang, Y.-Y. Tang, B. Fang, Z. Shang, and X. Liu, "Face recognition under varying illumination using gradientfaces," Image Processing, IEEE Transactions on, vol. 18, no. 11, pp. 2599-2606, 2009.

[6] D. Jobson, Z.-u. Rahman, and G. Woodell, "Properties and performance of a center/surround retinex,“ Image Processing, IEEE Transactions on, vol. 6, no. 3, pp. 451-462, 1997.