Please use this identifier to cite or link to this item:
標題: 應用於嬰幼兒監護系統之臉部追蹤與異物偵測演算法設計與實作
Design and Implement of Facial Tracking and Foreign Object Detecting algorithm for Baby Watch and Care System
作者: 呂冠賢
Lu, Hsien-Kuan
關鍵字: 人臉偵測;facial detection
出版社: 電機工程學系所
引用: [1] Lee, Y. B., You, B. J., and Lee, S. W.,“A Real-Time Color-Based Object Tracking Robust to Irregular Illumination Variations” IEEE ICRA. Vol.2, pp1659-1664,2001. [2] Lerdsudwichai, C., and Abdel-Mottaleb ,M., “Algorithm for Multiple Faces Tracking”. Multimedia and Expo, ICME ''03, International Conference Vol2, pp777-780 July ,2003. [3] Y-L.Tian, T.Kanade and J. F. Cohn. “ Multi-State Based Facial Feature Tracking and Detection “ ,Technical report CMU-RI- TR-99-18.Robotics Institute , Carnegie Mellon University, August, 1999. [4] Ching-Chih Weng ,Homer Chen1,and Chiou-Shann Fuh, “A Novel Automatic White Balance Method For Digital Still Cameras”, [5] Comaniciu D, Ramesh V. “Robust Detection and Tracking of Human Faces with an Active Camera” IEEE Int. Workshop on Visual Surveillance, Dublin, Ireland, 11~18, 2000. [6] Hsu, R. L., A. M. Mohamed and A. K. Jain “ Face detection in color image.” IEEE Transactions on Pattern Analysis and Machine Intelligence, 24(5), 696-704,2002 [7] Zhao, L. H., X. L. Sun, J. H. Liu and X. H. Xu “Face detection based on skin color. Proceedings of the Third International Conference on Machine Learning and Cybemetics”, Shanghai, China.,2004 [8] Horn, B.K.P., and Schunck,Jr.E.J.,“Determining Optical Flow” Artificial Intelligence, Vol 17, pp185-203, 1981. [9]H.A.Rowley, S.Baluja, and T.Kanade.,”Rotation invariant neural network based face detection”,Computer Vission and Pattern Recognition,1998 IEEE Computer Society Conference on, 1998, pp.38-44 [10] Baker,S., and Matthews,I.,“Lucas-Kanade 20 Years On: A Unifying Framework ”. International Journal of ComputerVision, 53(3), pp221–255, 2004. [11] Sun,Y.B. Kim, J.T., and Lee,W.H.,“Extraction of Face bjects Using Skin Color Information”,Communications, ircuits and Systems and West Sino Expositions , ol2,pp1136-1140,2002. [12] Xiao zheng Zhang and Russ M. Mersereau, ” Lip Feature Extraction Towards an Automatic Speech reading System “ , In Proc. International Conference on Image Processing, Vancouver, Sept. 2000. [13] Arsenioa, A., and Santos-Victor, J.,“ Robust Visual Tracking by an Active Observer”,IEEE IROS 97,Vol3,pp1342-1347,1997. [14]Sobotta, K.; Pitas, I. “Face localization and facial feature extraction based on shape and Color information”, Image Processing, 1996. Proceedings., International Conference on Volume: 3 , 1996 , Page(s): 483 -486 vol.3 [15] Yao, Hongxun and Wen Gao, “Face Detection and Location Based on Skin Chrominance and Lip Chrominance Transformation From Color Images “ , Pattern Recognition , Volume:34 , number 8 , pp.1555-1564 , 2001 [16] X. Xie, R. Sudhakar, H.Zhuang, "A cascaded Scheme for Tracking and Head Movement Compensation", IEEE TRANSCATIONS ON SYSTEMS, MAN, AND CYBERNETICS-PART A: SYSTEMS AND HUMANS, VOL. 28, NO. 4, JULY 1998 [17]Wu, H.; Yokoyama, T.; Pramadihanto, D.; Yachida, M. “Face and facial feature extraction from color image”, Automatic Face and Gesture Recognition, 1996., Proceedings of the Second International Conference on , 1996 , Page(s): 345 –350 [18] Jian Huang Lai, Yuen P.C, Wen Sheng Chen, Lao. S.,and Kawade, M.“ Robust Facial Feature Point Detection Under Nonlinear Illuminations “ . IEEE ICCV Workshop on Recognition, Analysis, and Tracking of Faces and Gestures in Real -Time Systems . pp .168-174,2001. [19]Baumberg, A.M.; Hogg, D.C." An efficient method for contour tracking using active shape models",Motion of Non-Rigid and Articulated Objects, 1994., Proceedings of the 1994 IEEE Workshop on , 1994 ,Page(s): 194 –199 [20] CC. Han, H.Y. Liao, G.J. Yu, and L.H. Chen, “Fast face detection via morphology-based pre-processing ”, Pattern Recognition, Vol.33, pp.1707-1712,2000. [21] R.L. Hsu, ”Face detection in color images,” IEEE Transaction on Pattern Analysis and Machine Intelligence, Vol.24, pp.696-706, 2002. [22] L. Jordao, M. Perrone, J.P. Costeira, and J. Santos-Victor, “Active face and feature tracking,” Proceedings of International Conference on Image Analysis and Processing, pp.572-576, 1999. [23] G.J. Jang and I.S. Kweon, “Robust real- time face tracking using adaptive color model,” Technical Report, Korea Advanced Institute of Science and Technology, 2000. [24] C.H. Lin and K.C. Fan, “Triangle -based approach to the detection of human face,” Pattern Recognition, Vol.34, pp.1271-1284, 2001. [25] Gonzalez Woods,“Digital Image Processing” ,繆紹綱編譯,Book ,2003 ,培生教育出版集團. [26] Zhong Jian, Yao Suying, Xu Jiangtao” Development and Implementation of Automatic White Balance Based on Luminance Compensation”. In IEEE Conf. Digital Object Identifier : 10.1109/IITA.2008.395 ,2008. [27] Tzan-sheng chiou , ”Automatic White Balance for Digital Still Camera”, MSc thesis , National Taiwan University , Department of Computer Science and Information Engineering,2006. [28] Funt B , F.Ciurea, J.McCann ,“ Retinex in Matlab ”, Proceedings of IS&T/SID Eighth Color Imaging Conference Scottsdale , Arizona (USA) , pp.112-121,November 7-10,2000. [29] Soriano, M. Martinkauppi, B. Huovinen,S. Laaksonen, M. Machine Vision & Media Process. Unit, Oulu Univ,” Skin detection in video under changing illumination conditions”. In Proc . 15th International Conference on Pattern Recognition, vol. 1, 839 – 842. [30] S.Birchfield."Elliptical Head Tracking Using Intensity Gradients and Color Histograms",In IEEE Conf. on computer Vision and Pattern Recognitions, Santa Barara, California, June 1998 [31] S.Birchfield."An elliptical head tracker",In Proc. Of the 31st Asilomar Conf. On Signal, Systems and Computers, 1997 [32]Cheng-Chin-Chiang,Wen-Kai-Tai,Mau-Tsuen-Yang,Yi-Ting-Huang,Chi-Jaung-Huang ,“A novel method for detecting lips, eyes and faces in real time”, [33] Zhang Baizhen; Ruan Qiuqi,“Facial feature extraction using improved deformable templates”, Signal Processing, The 8th International Conference on Volume 4, 16-20 2006 [34] K. Sobottka,and I. Pitas, “Face localization and facial feature extraction based on shape and Color information”, Image Processing, 1996. Proceedings, International Conference on Volume: 3, 1996, pp.483-486 [35] Viola, P.;Jones, M,“ Rapid Object Detection using a Boosted Cascade of Simple Features ”,Computer Vision and Pattern Recognition, 2001. CVPR 2001. Proceedings of the 2001 IEEE Computer Society Conference on Volume 1, 2001 Page(s):I-511 - I-518 vol.1 Digital Object Identifier 10.1109/CVPR.2001.990517 [36] X. Fu, and B. Guo, “An efficient video objects segmentation algorithm”,Intelligent Control and Automation, Vol. 2., pp. 10026-10030,June 2006.
本系統可分成三個子系統:人臉定位偵測,人臉追蹤以及異物偵測。在人臉偵測方面:利用膚色範圍找出可能的人臉區域,以達到人臉初步定位的目的。初步定位後,再利用橢圓遮罩定位出人臉輪廓。在人臉追蹤方面:由於第一張影像為了求其準確性處理時間較多,所以會把一些重要的座標資訊儲存起來,接下來會利用這些既有資訊再小範圍區域的搜尋,每收尋一次就更新一次座標資訊,以達到即時的效果。在異物偵測方面:在人臉候選區塊做 Sobel 運算子得到邊緣資訊,並利用五官之間的特性以及嘴唇顏色有別於皮膚顏色的特性,同時擷取五官,而非逐一偵測,得以提高正確性。
實驗結果顯示,在人臉定位偵測部分,使用我們所建立的嬰兒圖像資料庫,正確率可以達到 93%; 在五官偵測部分,正確率可以達到 85%; 使用 Pentium 4的電腦執行程式碼,第一張輸入影像處理需要 0.612杪,接下來每1/6秒偵測一次,執行所需時間約為 0.2秒; 每隔兩秒加入異物偵測功能,加入此一步驟執行時間會增加 0.006杪。

In this study, we will discuss a digital wisdom Baby Watch and Care system that could trace baby's face and detection object. The system will alert user when detecting something around mouth and nose. The way can replace the manpower security in nowadays and reduce user's burden.
There are three subsystems, human face position detecting, human face tracing and object detecting. Human face detecting uses skin color to search out the face area and gain initial human face position. After the initial position, using elliptical mask to position the contour of human face. Human face tracing, it takes more time to work first image for accuracy, so some important coordinates information will be stored. Then, using the information to do small range searching, every searching will renew coordinates information to achieve immediate. Object detecting, getting edge information by Sobel operation on chosen human face area and using facial features to compare lips color with skin color, choosing facial features at the same time instead of detecting step by step, by doing this to promote accuracy.
The experiment shows, in human face position detecting part, the baby images data we built could achieve 93% accuracy. In facial features part, the accuracy is 85%. First input image processing needs 0.612 second by using Pentium 4 computer program code, then the detecting happens every one sixth second, working time needs 0.2 second. Object detecting will be started every two seconds, it needs more 0.006 second if object detecting works.
其他識別: U0005-1208200911172000
Appears in Collections:電機工程學系所

Show full item record
TAIR Related Article

Google ScholarTM


Items in DSpace are protected by copyright, with all rights reserved, unless otherwise indicated.