本篇論文主要探討以嬰兒表情為基礎的監控系統。由於嬰兒無法保護自己，若照顧者有疏忽可能讓嬰兒處於危險中。本系統可協助照顧者監控嬰兒，即使照顧者離開嬰兒身邊，也可防止意外的發生。
本研究將攝影機架設在嬰兒床上方以擷取嬰兒影像。此系統首先針對影像去除雜訊及減少受到光源的影響。藉由膚色的資訊來做嬰兒臉部區塊的擷取。接著利用Hu動差、R動差和Z動差去計算臉部區塊。由於每種動差包含許多不同動差，例如Hu動差有七個動差，因此給十五張影像去計算相同類別下臉部表情的特徵，並且藉此了解動差間的關係。本研究將嬰兒表情分成十五個類別，分別是哭、笑、發呆…等，接著再利用決策樹做分類。利用動差所計算出的相關係數所建構的三個決策樹來進行分類分別是用來。實驗的結果顯示本研究所提出的方法可行，而且也針對不同種類的動差進行分析及討論。
最後本研究目前僅針對部份的嬰兒表情進行分類，希望未來能收集到更多嬰兒不同年紀的資料，以建構更完整資料庫。

This paper presents a vision-based infant surveillance system based on infant facial expression recognition. Since infants are too little to protect themselves, they are easy hurt in accidents by the negligence of the baby-sitters. An infant surveillance system can assist the baby-sitters to monitor the infants to avoid the occurrence of the infant injuries even the infants are left alone in a short period.
In this study the video camera is set above the crib to capture the infant sequences. The system first preprocesses the input image to remove the noises and reduce the influence of lights and shadows. The region of infant face is then segmented based on the skin color information. Three moment types, including Hu moment, R moment, and Zernike moment, are calculated based on the infant face region. Since each moment type contains several different moments (e.g. seven in Hu moment), given one 15-frame sequence the correlations between each two moments in the same class can be calculated as the features of facial expressions. Fifteen classes of infant facial expressions, including different poses of crying, smiling, dazing, and so on, are defined in this study and classified by the decision tree technique. Three decision trees are constructed to classify their corresponding types of the moments respectively. The experimental results show that the proposed method is robust and efficient, and the properties of different types of the moments are also analyzed and discussed.
Finaly, the study mainly classify parts of facial expressions of infants. in the future year, i hope that more information of infants at different stages will be discovered in order to make the research more complete.

[Ada00] Y. Adachi, A. Imai, M. Ozaki, and N. Ishii, “Extraction of Face Region by Using Characteristics of Color Space and Detection of Face Direction through an Eigenspace,” Proceeding of 4th Int’l Conference on Knowledge-Based Intelligent Engineering Systems and Allied Technologies, Brighton, UK, Volume 1, pp. 393-396, 2000.

[Aha08] M. A. R. Ahad, T. Ogata, J. K. Tan, H. S. Kim, and S. Ishikawa, “Template-based human motion recognition for complex activities,” SMC 2008. IEEE International Conference on Systems, Man and Cybernetics, pp.673 – 678, 2008.

[Cha99] D. Chai and K. N. Ngan, “Face Segmentation Using Skin-Color Map in Videophone Applications,”IEEE Trans on Circuits and Systems for Video Technology, volume 9, no. 4, pp. 551-564, 1999.

[Dav94] David R. Shaffer (1994) “Social and Personality Development,” Brooks/Cole, pp.185-188.

[Fan03] J. Fang and G. Qiu, “Human Face Detection Using Angular Radial Transform and Support Vector Machines,” Processing. 2003 International Conference on Image Processing, Nottingham Univ, UK, Volume 1, pp. I - 669-72, 2003.

[Gil07] L. Goldmann, U. J. Monich, and T. Sikora, “Components and Their Topology for Robust Face Detection in the Presence of Partial Occlusions,” IEEE Transactions on Information Forensics and Security, Volume 2, pp. 559-569, 2007.

[Hje01] E. Hjelmas and B. K. Low, “Face Detection: A Survey,” Computer Vision and Image Understanding, Volume 83, pp. 236-274, 2001.

[Kik05] K. Kikuchi and K. Arakawa, “Estimation of babies' emotion by frequency analyses of their cries,” IEEE-Eurasip Nonlinear Signal and Image Processing, pp. 18-22, 2005.

[Lie04] M. Lievin and F. Luthon, “Nonlinear Color Space and Spatiotemporal MRF for Hierarchical Segmentation of Face Features in Video,” IEEE Trans. on Image Processing, Volume 13, no. 1, pp. 63 -71, 2004.

[Liu08] J. Liu, and C. Yan, ”Feature Extraction Technique Based on the Perceptive Invariability,” FSKD '08. Fifth International Conference on Fuzzy Systems and Knowledge Discovery, Volume 3, pp. 551-554, 2008.

[Mar03] B. Martinkauppi, M. Soriano, and M. Pietikainen, “Detection of Skin Color under Changing Illumination: A Comparative Study,” Proceeding of 12th Int’l Conference on Image Analysis and Processing, Finland, pp. 652-657, 2003.

[Mes08] D. S. Messinger, M. H. Mahoor, S. Cadavid, Chow Sy-Miin, and J. F. Cohn, “Early interactive emotional development” IEEE International Conference on Development and Learning, pp. 232-237, 2008.

[Mit03] Y. Mitsukura, H. Takimoto, M. Fukumi, and N. Akamatsu, “Face Detection and Emotional Extraction System Using Double Structure Neural Network,” Proc. of the International Joint Conference on Neural Networks, Volume 2, pp. 1253 -1257, 2003.

[Ｍuk95] R. Mukundan, and K. R. Ramakrishnan, “Fast computation of Legendre and Zernike moments”, Control Systems Group, ISRO Satellite Centre, Volume 28, pp. 1433-1442,1995.

[Mut09] E. M. Mutsvangwa, J. Smit, E. Hoyme, W. Kalberg, L. Viljoen, M. Meintjes, and S. Douglas, “Design, Construction and Testing of a Stereo- Photogrammetric Tool for the Diagnosis of Fetal Alcohol Syndrome in Infants,” appear to IEEE Transactions on Medical Imaging : Accepted for future publication, Volume. PP, pp. 1-1, 2009.

[Ngu04] H. T. Nguyen and A. W. M. Smeulders, “Fast Occluded Object Tracking by A Robust Appearance Filter,” IEEE Trans. on Pattern Analysis and Machine Intelligence, Volume 26, pp. 1099 -1104, 2004.

[Nor06] A. J. Nor'aini, P. Raveendran, and N. Selvanathan, ”Human Face Recognition using Zernike moments and Nearest Neighbor classifier,” SCOReD 2006. 4th Student Conference on Research and Development, pp.120-123, 2006.

[Fae06]K. Faez, and N. Farajzadeh, ”A Performance Comparison of the ZM, PZM and LM in the Face Recognition System in Presence of Salt-pepper Noise,” SMC '06. IEEE International Conference on Systems, Man and Cybernetics,Volume 5, pp.4197 - 4201, 2006.

[Pa06] P. Pa, A. N. Iyer, and R. E. Yantorno, ” Emotion Detection From Infant Facial Expressions And Cries,” IEEE International Conference on Acoustics, Speech and Signal Processing, Volume 2, pp. 14-19, 2006.

[Rey08] O. F. Reyes-Galaviz, S. D. Cano-Ortiz, and C. A. Reyes-Garcia, “Evolutionary-Neural System to Classify Infant Cry Units for Pathologies Identification in Recently Born Babies,” Seventh Mexican International Conference on Artificial Intelligence, pp. 330-335, 2008.

[Zhi08] R. Zhi, and Q. Ruan, “A Comparative Study on Region-Based Moments for Facial Expression Recognition,” CISP '08. Congress on Image and Signal Processing,Volume 2, pp. 600 – 604, 2008.

[姚08] 姚國鵬, “車載型視覺式駕駛者疲倦昏睡偵測系統,” 碩士論文, 國立臺灣師範大學資訊工程研究所, 2008.

[1] 內政統計資訊服務網，http://sowf.moi.gov.tw/stat/national/j025.xls，各國嬰兒死亡率.xls，2006年。

[2] 行政院衛生署，http://www.health.gov.tw/Default.aspx?tabid=419/96，臺北 市生命統計.pdf，2007年。

[3] 行政院衛生署，http://www.health.gov.tw/Default.aspx?tabid=306&mid=101 2&itemid=7409，嬰兒死亡主要原因.xls，2007年。

[4] http://www.books.com.tw/exep/prod/newprod_file.php?item=N010005725，守 護天使嬰兒看護墊。

[5] Angelcare, http://www.angelcare-monitor.com, Baby monintors and Diaperdisposal system, 2001.