近年來因應監視系統的人臉辨識需求大增，相對應的，獲得快速或即時的臉部識別演算法也獲得大量的投入研究，特別是在安全性相關的應用方面上。儘管今日人臉偵測及辨識系統在成效上已取得相當成熟的水準，但由於攝影系統日漸要求高解析度的硬體配備之下，從影片中直接辨識人臉仍存在演算法不夠迅速且有降低畫框數處理的現象，原因在於現行的應用環境不管在室內或戶外多採用壓縮格式的串流。在本文中，我們提出了可在離散餘弦轉換領域 (DCT domain) 上進行低複雜度的計算，即可透過人臉辨識出畫面裡的人之名字，充分展現了能在壓縮領域上使用軟硬體加速演算法並能一氣呵成地實現人臉辨識的可能性。實驗結果展現了所提出的方法於各種解析度下的壓縮影片內容上執行基本的人臉辨識率平均值達85%以上，且可在提出的改善方式上，輕易取得93.5%以上的人臉辨識率，並能同時識別出多張人臉的名字。本研究的主要貢獻是提供用於在DCT域中進行實時臉部識別一個可能的解決方案，實驗中不僅顯示提出的方法運用在壓縮領域中能提高人臉特徵提取效能，而且還可以提高監控系統的人臉識別率。

Since face detection (FD) and recognition (FR) in video have received significant attention among both academics and practitioners, there is a growing demand for the corresponding real time FD and FR algorithms especially for security applications. Although current face detection and recognition systems have reached a certain level of efficiency and/or maturity, recognition from video remains less efficient, and also has problems since the related images and video are usually handled in compressed form, which is especially true in indoor or outdoor unconstrained application environments. In this work we propose an efficient method of FD and FR in the DCT domain with low complexity computation, which has the potential of perming well in the compressed domain. The experimental results show that our proposed method has a face recognition rate of 93%. The main contribution of this study is providing a possible solution for real-time face recognition performed in the DCT domain. This can, not only improve the performance of DCT facial feature extraction, but can also enhance the face recognition rate in surveillance systems.

[1] Jeremiah R. Barr, Kevin W. Bowyer, Patrick J. Flynn, Soma Biswas, “Face Recognition From Video : A Review”, International Journal of Pattern Recognition and Artificial Intelligence, April, Vol. 26, No. 5, 2012, DOI: http://dx.doi.org/10.1142/S0218001412660024
[2] Qiu Chen, Koji Kotani, “An Improved Face Recognition Algorithm Using Quantized DCT Coefficients”, Seventh International Conference on Signal Image Technology & Internet-Based Systems, Dijon, France, 2011, pages 329-333.
[3] Daidi Zhong, Irek. Defee, “Pattern Recognition in Compressed DCT Domain”, International Conference on Image Processing (ICIP) International conference on IEEE , 24-27 Oct. 2004, DOI: 10.1109/ICIP.2004.1421482
[4] Koji Kotani, Qiu Chen, Feifei Lee, and Tadahiro Ohmi, “Region-Division Vector Quantization Histogram Method for Human Face Recognition”, Intelligent Automation and Soft Computing, March, Vol. 12, No. 3, 2013, pages 257-268. DOI: http://dx.doi.org/10.1080/10798587.2006.10642929
[5] Li-JieXue, Zheng-Ming Li, “Using Skin Color and HAD-AdaBoost Algorithm for Face Detection in Color Images”, WKDD '08 Proceedings of the First International Workshop on Knowledge Discovery and Data Mining, January 23 - 24, IEEE Computer Society Washington, DC, USA, 2008, pages 339-342.
[6] Kai-Biao Ge, Jing Wen, Bin Fang, “AdaBoost Algorithm based on MB-LBP Features with Skin Color Segmentation for Face Detection”, Proceedings of the 2011 International Conference on Wavelet Analysis and Pattern Recognition, Guilin, 10-13 July, 2011, DOI: 10.1109/ICWAPR.2011.6014477
[7] Chunmei Qing and Jianming Jiang, “Recognition of JPEG Compressed Face Images based on AdaBoost”, Journal of Semantic Multimedia – Second International Conference on Semantic and Digital Media Technologies, SAMT2007, B. Falcidieno et al. (Eds.), LNCS 4816, 2007, pages 272-275.
[8] Ying-Hao Yu, Tsu-Tian Lee, Ngai-Ming Kwok and Pei-Yin Chen, “Chip-based Adaptive Skin Color Detection Using Trajectory Constraints on Hue”, Visualization in Engineering Journal, December, 2014, DOI: 10.1186/s40327-014-0011-1
[9] Rein-Lien Hsu, Mohamed Abdel-Mottaleb, and Anil K. Jain, “Face Detection in Color Images”, Pattern Analysis and Machine Intelligence, IEEE, August 07, Vol. 24, No. 5, 2002, pages 696-706.
[10] Jian-qing ZHU, Can-hui CAI, “Region Growing based High Brightness Skin Detection”, Signals, Circuits and Systems (ISSCS), 2011 10th International Symposium, 30 June-1 July, 2011, DOI: 10.1109/ISSCS.2011.5978652
[11] Farhad Dadgostar, Abdolhossein Sarrafzadeh, “An Adaptive Real-time Skin Detector based on Hue Thresholding: A Comparison on Two Motion Tracking Methods”, Science Direct Journal Pattern Recognition Letters, March 20 Auckland, New Zealand, Vol. 27, No. 12, September, 2006, DOI: http://dx.doi.org/10.1016/j.patrec.2006.01.007
[12] Paul Viola, Michael J. Jones, “Robust Real-Time Face Detection”, International Journal of Computer Vision, May, Vol. 57, No, 2, 2004, pages 137-154. DOI: 10.1023/B:VISI.0000013087.49260.fb
[13] Qiu Chen, Koji Kotani, Feifei Lee, Tadahiro Ohmi, “A Codebook Design Method for Robust VQ-based Face Recognition Algorithm”, Journal of Software Engineering & Applications, Japan, February, Vol. 3, No. 2, 2010, pages 119-124. DOI: 10.4236/jsea.2010.32015
[14] Raghavender R. Jillela and Arun Ross, “Adaptive Frame Selection for Improved Face Recognition in Low-Resolution Videos”, Proceedings of International Joint Conference on Neural Networks, Atlanta, Georgia, USA, 14-19 June, 2009. DOI: 10.1109/IJCNN.2009.5178989
[15] Detlev Marpe, Heiko Schwarz and Thomas Wiegand, “Context-based Adaptive Binary Arithmetic Coding in the H.264/AVC Video Compression Standard”, Circuits and Systems for Video Technology, July 2003, Vol. 13, No. 7, pages 620-636, 2003. DOI: 10.1109/TCSVT.2003.815173
[16] Roberto R. Osorio and Javier D. Bruguera, “High-Speed FPGA Architecture for CABAC Coding Acceleration in H.264/AVC Standard”, Journal of Signal Process System, Hingham, MA, USA, August 2013, Vol. 72, No. 2, 2013, pages 119-132.
[17] Taheni Damak, Hassen Louki, Ahmed Ben Atitallah, Nouri Masmoudi, “Software and Hardware Architecture of H.264/AVC Decoder”, International Journal of Computer Applications, IJCA Journal, Vol. 59, No.19, December 2012.
[18] M. Mahdi Ghandi and Mohammad Ghanbari, “The H.264/AVC Video Coding Standard for the Next Generation Multimedia Communication”, in IAEEE journal, 2004. http://citeseerx.ist.psu.edu/viewdoc/versions?doi=10.1.1.103.9107
[19] Yao-Chang Yang, Chien-Chang Lin, Hsui-Cheng Chang, Ching-Lung Su and JiuninGuo, “A High Throughput VLSI Architecture Design for H.264 Context-based Adaptive Binary Arithmetic Decoding with Look Ahead Parsing”, Multimedia and Expo, 2006 IEEE International Conference, 9-12 July 2006, 2006, pages 357-360.
[20] IAN H. WITTEN, RADFORD M. NEAL, and JOHN G. CLEARY, “Arithmetic Coding for Data Compression”, Magazine Communication of the ACM, New York, NY, USA, June 1987. Vol. 30, No. 6, 1987, pages 520-540.
[21] Hieu V. Nguyen and Li Bai, “Cosine Similarity Metric Learning for Face Verification”, Computer Vision-ACCV 2010. Springer (2011) Vol. 6493, 2010, pages 709-720.
[22] K. Weinberger, J. Blitzer, and L. Saul, “Distance Metric Learning for Large Margin Nearest Neighbor Classification”, Journal of Machine Learning Research, Vol. 10 February, 2009, pages. 207-244.
[23] Huafeng Wang, Yunhong Wang, and Yuan Cao, “Video-based Face Recognition: A Survey”, International Journal of Computer, Electrical, Automation, Control and Information Engineering Vol:3, No:12, 2009. http://www.waset.org/Publications/video-based-face-recognition-a-survey/15131
[24] Ruiping Wang, Shiguang Shan, Xilin Chen, and Wen Gao, “Manifold-Manifold Distance with Application to Face Recognition based on Image Set”, Computer Vision and Pattern Recognition, 2008. CVPR 2008. IEEE Conference, 23-28 June, 2008. DOI: 10.1109/CVPR.2008.4587719
[25] Zhang Weiguo, and Wang Liqing, “Target Recognition Algorithm based on Block and SIFT Features ”, Signal Processing, Communication and Computing (ICSPCC), 2013 IEEE Conference, 5-8 Aug. 2013. DOI: 10.1109/ICSPCC.2013.6663966
[26] Wu Zhen, Xu Zhe, Zhang Rui-nian, and Li Shao-Mei, “SIFT Feature Extraction Algorithm for Image in DCT Domain”, Proceedings of the 2nd international Symposium on Computer, Communication, Control and Automation (ISCCCA-13), August, 2013, pages 0261-0264.
[27] Radovan Fusek, and Eduard Sojka, “Gradient-DCT (G-DCT) Descriptors”, Image Processing Theory, Tool and Application (IPTA), 2014 4th International Conference, 14-17 Oct, 2014. DOI: 10.1109/IPTA.2014.7001946
[28] Anton Akusok, Yoan Miche, Jozsef Hegedus, Rui Nian, and Amaury Lendasse, “A Two-Stage Methodology Using K-NN and False-Positive Minimizing ELM for Nominal Data Classification”, Cognitive Computation, September 2014, Vol 6, No. 3, 2014, pages 432-445. DOI: 10.1007/s12559-014-9253-4
[29] Nasser M. Nasrabadi, member, IEEE and Robert A. King, “Image Coding Using Vector Quantization: A Review”, IEEE Transactions on Communications, August 1988, VOL. 36, NO. 8, 1988, pages 957-971. DOI: 10.1109/26.3776
[30] P. Jonathon Philips, J. Ross Beveridge, Bruce A. Draper, Geof Givens, Alice J. O’Toole, David S. Bolme, Joseph Dunlop, Yui Man Lui, Hassan Sahibzada, and Samuel Weimer, “A Introduction to the Good, the Bad, & the Ugly Face Recognition Challenge Problem”, Automatic Face & Gesture Recognition and Workshops (FG 2011), IEEE International Conference, 21-25 March, 2011. DOI: 10.1109/FG.2011.5771424.
[31] T. Wieg, Ed., Pattay , “Draft ITU-T Recommendation H.264 and Draft ISO/IEC 14 496-10 AVC”, Joint Video Team of ISO/IEC JTC1/SC29/WG11 & ITU-T SG16/Q.6 Doc. JVT-G050, Thailand, March. 2003.
[32] Yongkang Wong, Shaokang Chen, Sandra Mau, Conrad Sanderson, Brian C. Lovell, “Patch-based Probabilistic Image Quality Assessment for Face Selection and Improved Video-based Face Recognition”, Computer Vision and Pattern Recognition Workshops (CVPRW), 2011 IEEE Computer Society Conference 20-25 June, 2011, Pages 74-81. DOI: 10.1109/CVPRW.2011.5981881
[33] Virendra P. Vishwakarma, Sujata Pandey and M. N. Gupta, “Adaptive Histogram Equalization and Logarithm Transform with Rescaled Low Frequency DCT Coefficients for Illumination Normalization”, International Journal of Recent Trends in Engineering (IJRTE), May, Vol 1, No. 1, 2009, Pages 318-322..
[34] Amnon Shashua and Tammy Riklin-Raviv, “The Quotient Image: Class based Re-rendering and Recognition With Varying Illuminations”, Pattern Analysis and Machine Intelligence, IEEE Transactions, August, 2002, Pages 129-239. DOI: 10.1109/34.908964
[35] Weilong Chen, Meng Joo Er, and Shiqian Wu, “Illumination Compensation and Normalization for Robust Face Recognition Using Discrete Cosine Transform in Logarithm Domain”, EEE Transactions on Systems, Man, and Cybernetics—PART B, 13 March, 2006, pages 458-466.
[36] Tripti Goel, Vijay Nehra, Virendra P. Vishwakarma, “Rescaling of Low Frequency DCT Coefficients with Kernel PCA for Illumination Invariant Face Recognition”, Advance Computing Conference (IACC), 2013 IEEE 3rd International, February, 2013, page 1177-1182. DOI: 10.1109/IAdCC.2013.6514394
[37] Michele A. Saad, Alan C. Bovik, “Blind Image Quality Assessment: A Natural Scene Statistics Approach in the DCT Domain”, IEEE Transactions on Image Processing, Vol. 21, No. 8, August, 2012, pages 3339-3352. DOI: 10.1109/TIP.2012.2191563
[38] Anish Mittal, Anush Krishna Moorthy, and Alan Conrad Bovik, “No-Reference Image Quality Assessment in the Spatial Domain”, IEEE Transactions on Image Processing, 17 August, Vol. 27, No. 12, December 2012. DOI: 10.1109/TIP.2012.2214050
[39] Damon M. Chandler, “Seven Challenges in Image Quality Assessment: Past, Present, and Future Research”, Journal ISRN Signal Processing Volume 2013, November, 2012, pages 53. http://dx.doi.org/10.1155/2013/905685
[40] Eickerler, S., Müller, S., Rigoll, G, “Recognition of Jpeg Compressed Face Images based on Statistical Methods”, Image Vision Computation. March, Vol 18, No. 4, 2000, pages 279-287. DOI: http://dx.doi.org/10.1016/S0262-8856(99)00055-4
[41] Hafed, Z. M., Levine, M.D., “Face Recognition Using the Discrete Cosine Transform”, International Journal Computation. Vol. 43, No. 3, July, 2001, page 167-188. DOI: 10.1023/A:1011183429707
[42] Schwerin, B., Paliwal, K., “Local-DCT features for Facial Recognition”, Signal Processing and Communication Systems, 2008. 2nd International Conference, 15-17 December, 2008. DOI: 10.1109/ICSPCS.2008.4813751
[43] Shaoqing Ren, Xudong Cao, Yichen Wei, Jian Sun, “Face Alignment at 3000 FPS via Regressing Local Binary Features”, Computer Vision and Pattern Recognition, IEEE Conferencce, 23-28 June, 2014. DOI: 10.1109/CVPR.2014.218
[44] Xiang Wu, Ran He, Zhenan Sun, “A Lightened CNN for Deep Face Representation”, Cornell University Library Computer Vision and Pattern Recognition Cite as arXiv:1511.02683, 14 November, 2015.
[45] Wang Jun, “Detecting and Tracking Human Faces in Compressed Domain for Content based Video Indexing”, Master Thesis, School of Computing, National University of Singapore, 2002. https://www.semanticscholar.org/paper/Detecting-and-Tracking-Human-Faces-in-Compressed-Jun-Qiuying/83f81b2a08330b27fe199d8a55d2d3a921721294
[46] Huala Wang and Shih-Fu Chang, “A Highly Efficient System for Automatic Face Region Detection in MPEG Video”, IEEE Transactions on Circuits and Systems for Video Technology, 06 August, Vol. 7, No. 5, 2002, pages 615-628. DOI: 10.1109/76.611173
[47] T.F. Cootes, G.J. Edwards and C.J Taylor, “Active Appearance Model”, IEEE Transactions on Pattern Analysis and Machine Intelligence, June, Vol:23, No. 6, 2001, pages 681-685. DOI: 10.1109/34.927467
[48] Johannes Stallkamp, Hazım K. Ekenel and Rainer Stiefelhagen, “Video-based Face Recognition on Real-World Data”, Computer Vision, 2007. ICCV 2007. IEEE 11th International Conference, 14-21 October, 2007. DOI: 10.1109/ICCV.2007.4408868
[49] Waqas Haider, Hadia Bashir, Abida Sharif, Irfan Sharif and Abdul Wahab, “A Survey on Face Detection and Recognition Approach”, Research Journal of Recent Sciences, ISSN 2277-2502, April, Vol. 3, No. 4, 2014, pages 56-62. http://www.isca.in/rjrs/archive/v3/i4/10.ISCA-RJRS-2013-216.php
[50] Qiu Chen, Koji Kotani, Feife Lee, Tadahiro Ohmi, “An Improved Face Recognition Algorithm Using Histogram-based Features in Spatial and Frequency Domains”, International Journal of Computer, Electrical, Automation, Control and Information Engineering, World Academy of Science, Vol. 10, No. 2, 2016.
[51] Z.-M. Lu and H. Burkhardt, “Colour Image Retrieval based on DCT-domain Vector Quantisation Index Histograms”, Browse Journals & Magazines, Electronics Letters, 29 August, Vol. 41, No. 17, 2005, pages 956-957. DOI: 10.1049/el:20052176
[52] Messaoud Bengherabi, Lamia Mezai, Farid Harizi, Mohamed. Cheriet, Abderrazak Guessoum, “Face Recognition based on 2DPCA, DICPCA, and DIA2DPCA in DCT domain”, System, Signal and Devices, 2008. IEEE SSD 2008, 5th International Multi-Conference, 20-22 July, 2008. DOI: 10.1109/SSD.2008.4632873
[53] R. Jenkins, A. M. Burton, “100% Accuracy in Automatic Face Recognition”, Science 25 January 2008: Vol. 319, No. 5862, 2008, page 435. DOI: 10.1126/science.1149656
[54] Lacey Best-Rowden, Brendan Klare, Joshua Klontz, Anil K, Jain, “Video-to-Video Face Matching: Establishing a Baseline for Unconstrained Face Recognition”, Biometrics: Theory, Applications and Systems (BTAS), 2013 IEEE Sixth International Conference, 29 Sept.-2 Oct. 2013, January, 2014. DOI: 10.1109/BTAS.2013.6712699
[55] L. Wolf, T. Hassner, and I. Maoz, “Face Recognition in Unconstrained Videos with Matched Background Similarity”, Computer Vision and Pattern Recognition (CVPR), 2011 IEEE Conference on , 20-25 June, 2011, pages 529-534. DOI: 10.1109/CVPR.2011.5995566
[56] H. Li, G. Hua, Z. Lin, J. Brandt, and J. Yang, “Probabilistic Elastic Matching for Pose Variant Face Verification”, Computer Vision and Pattern Recognition (CVPR), 2013 IEEE Conference, 23-28 June, 2013. DOI: 10.1109/CVPR.2013.449
[57] Z. Cui, W. Li, D. Xu, S. Shan, and X. Chen, “Fusion Robust Face Region Descriptors via Multiple Metric Learning for Face Recognition in the Wild”, Computer Vision and Pattern Recognition (CVPR), 2013 IEEE Conference on, 23-28 June, 2013. DOI: 10.1109/CVPR.2013.456
[58] H. Bhatt, R. Singh, and M. Vatsu, “On Rank Aggregation for Face Recognition from Videos”, Image Processing (ICIP), 2013 20th IEEE International Conference, 15-18 September, 2013. DOI: 10.1109/ICIP.2013.6738616