CAD-Final-CAS-PEAL.doc

Size: px

Start display at page:

Download "CAD-Final-CAS-PEAL.doc"

沾史
7 years ago
Views:

1 CAS-PEAL : {xhzhang, sgshan, bcao, wgao, dlzhou, dbzhao}@jdl.ac.cn CAS-PEAL 1,040 99,450 CAS-PEAL CAS-PEAL Eigenface Correlation [1] [1, 2, 3] [2,3] FERET 14, , , ,368

2 AT&T % 103 1, ,288 BANCA ,000 52,000 1,400 CAS-PEAL , ,450 CAS-PEAL 7 7 Pose Expression Accessory Lighting 4 PEAL CAS-PEAL CAS-PEAL 2. CAS-PEAL CAS-PEAL CAS-PEAL

3 1 C4 9 USB PC C0 C8 C1 C7 C2 C6 C3 C4 C U-45 U-90 M-45 M-90 U+00 D-45 D-90 M+00 U+45 U+90 D+00 M+45 M+90 D+45 D

4 CAS-PEAL CAS-PEAL 1,040 99,

5 图 6 光照子库中的 15 种方向光背景子库 5 种不同的背景颜色包括蓝色红色黑色白色和黄色环境光照模式下由于摄像头的白平衡功能面部图像的色彩分布在每种背景颜色条件下均有不同如图 7 所示 5. 图 7 背景子库中的蓝红黑白黄 5 种背景距离子库环境光照模式下改变志愿者与摄像头的相对距离获取到距离子库中每个志愿者的 3 种不同距离的面部图像如图 8 所示 6. 图 8 距离子库中三种不同的距离下的图片时间跨度子库随着时间的改变人的面部特征会有一定的变化在我们的人脸数据库中我们引入了时间跨度子库子库中的志愿者图片距离他们第一次采集的图片有 6 个月的时间跨度如图 9 所示 7. 图 9 时间子库第二行的图像为第一次采集 6 个月后再次拍摄的图像

6 4. CAS-PEAL-R1 CAS-PEAL CAS-PEAL CAS-PEAL-R1[15] CAS-PEAL-R1 1,040 30,900 1,040 9,060 C ,040 21, CAS-PEAL-R1 1 1,040 1,040 5 * 377 1, , , * : 9, (3 7) 1,040 21,840 : 21,840 * CAS-PEAL RGB BMP CAS-PEAL-R BMP, CAS-PEAL-R1 5G CAS-PEAL-R CAS-PEAL-R1 11 CAS-PEAL-R1

7 5. CAS-PEAL-R1 Three bears problem [2] CAS-PEAL-R CAS-PEAL-R1 CAS-PEAL-R1 Training Set Gallery Probe Sets Training Set ,200 Gallery 1,040 1 Probe Set 6,992 6 ± 30 21,840 3 FERET

8 FERET FRVT [2,3] CMC ROC 6. CAS-PEAL-R Eigenface Correlation Eigenface Correlation CAS-PEAL mask Eigenface Correlation 16 Training set Gallery 32 32

9 18 Probe set Probe set Correlation Eigenface PCA CAS-PEAL-R CAS-PEAL-R1 A B CAS-PEAL A B CAS-PEAL-R I i I i I i 6.3. Eigenface Correlation A B Eigenface Correlation Eigenface Correlation 80% 60% 50% 40% 10% 40% 10% Eigenface Correlation Eigenface Correlation

10 20 CAS-PEAL-R1 21 CAS-PEAL-R1 6 B 100% 80% A B B 40% A 10% 60% 40% CAS-PEAL 7. CAS-PEAL CAS-PEAL 1,040 99,450 Eigenface Correlation CAS-PEAL-R1

11 1. Eigenface Correlation CAS-PEAL-R % [1] R.Chellappa, C.L.Wilson, S.Sirohey. Human and Machine Recognition of faces: A survey. In: Proceedings of the IEEE, 1995, 83 (5): [2] P. Johnathon Phillips, H. Moon, Syed A. Rizvi et al. The FERET Evaluation Methodology for Face-Recognition Algorithms. IEEE Trans. on Pattern Analysis and Machine Intelligence, 2000, 22 (10): [3] P.J.Philips, P.J.Grother, R.J.Micheals et al. Face Recognition Vendor Test 2002: Evaluation Report [R]. National Institute of Standards and Technology, NISTIR 6965, [4] Matthew Turk, and Alex Pentland. Eigenfaces for Recognition. Journal of Cognitive Neuroscience. 1991, 3 (1): [5] Peter N. Belhumeur, Joao P. Hespanha, and David J. Kriegman. Eigenfaces vs. Fisherfaces: Recognition Using Class Specific Linear Projection. IEEE Transactions on Pattern Analysis and Machine Intelligence, 1997, 19 (7): [6] A. Georghiades, D. Kriegman, and P. Belhumeur. From few to many: Generative models for recognition under variable pose and illumination. IEEE Transactions on Pattern Analysis and Machine Intelligence, 2001, 23(6): [7] Terence Sim, Simon Baker, and Maan Bsat. The CMU Pose, Illumination and Expression Database. IEEE Transactions on Pattern Analysis and Machine Intelligence, 2003, 25 (12): [8] F. S. Samaria, and A. C. Harter. Parameterization of a Stochastic Model for Human Face Identification. In: Proceedings of the 2 nd IEEE Workshop on Applications of Computer Vision, Sarasoto, FL, [9] Hyoja-Dong, and Nam-Gu. Asian Face Image Database PF01. Pohang University of Science and Technology. [10] A. R. Martinez and R. Benavente. The AR Face Database [R]. Computer Vision Center (CVC), Barcelona, Spain, Technical Report 24, [11] E. Bailly-Bailliere, S. Bengio, F. Bimbot et al. The BANCA Database and Evaluation Protocol. In: Fourth International Conference on Audio- and Video-based Biometric Person Authentication (AVBPA), Guildford, UK, 2003: [12] B.-W. Hwang, H. Byun, M.-C. Roh and S.-W. Lee. Performance Evaluation of Face Recognition Algorithms on the Asian Face Database, KFDB. In: Fourth International Conference on Audio- and Video-based Biometric Person Authentication (AVBPA), Guildford, UK, 2003: [13] V. Blanz and T. Vetter. A Morphable Model for the Synthesis of 3D Faces. In: Computer Graphics Proceedings, Annual Conference Series (SIGGRAPH), Los Angeles, USA, 1999: [14] K. Messer, J. Matas, J. Kittler et al. XM2VTSDB: The Extended M2VTS Database. In: Second International Conference on Audio and Video-based Biometric Person Authentication, Washington DC, USA, 1999:

12 [15] Wen Gao, Bo Cao, Shiguang Shan et al. The CAS-PEAL Large-Scale Chinese Face Database and Evaluation Protocols [R], Joint Research & Development Laboratory, CAS, No. JDL_TR_04_FR_001, CAS-PEAL: A Large-scale Chinese Face Database and Some Primary Evaluations Xiaohua Zhang, Shiguang Shan, Bo Cao, Wen Gao, Delong Zhou, Debin Zhao Digital Lab, Institute of Computing Technology, Chinese Academy of Sciences, Beijing, China, {xhzhang, sgshan, bcao, wgao, dlzhou, dbzhao}@jdl.ac.cn Abstract: As the basis of research, development and evaluation of face recognition algorithms, face image database is of great importance. In this paper, we introduce the construction and basic content of the CAS-PEAL large-scale Chinese face database and some primary evaluation results based on it. The CAS-PEAL face database consists of 99,450 facial images of 1,040 Chinese individuals. All the images in the database were collected in specially designed environment with four principal variations of Pose, Expression, Accessory and Lighting, as well as three other variations of Background, Distance and Aging. Currently, the standard training set and probe set of CAS-PEAL face database have been made publicly available for research purpose only on a case-by-case basis. Compared with other public face databases, CAS-PEAL face database excels in its large-scale and variation modes and is expected to have positive impact on the development and evaluation of face recognition algorithms. In addition, as an oriental face image database, CAS-PEAL makes possible the compare of algorithms performance between different ethnic groups and will benefit the application of face recognition technology in China. This paper also gives the evaluation results of two basic face recognition algorithms (Eigenface and Correlation) and two business systems, explains the difficulty of the database to the face recognition algorithms and analyses the current development status of face recognition technology. Keywords: Face Recognition; Face Database; Performance Evaluation

2 3. 1,,,.,., CAD,,,. : 1) :, 1,,. ; 2) :,, ; 3) :,; 4) : Fig. 1 Flowchart of generation and application of 3D2digital2building 2 :.. 3 : 1) :,

2 3. 1,,,.,., CAD,,,. : 1) :, 1,,. ; 2) :,, ; 3) :,; 4) : Fig. 1 Flowchart of generation and application of 3D2digital2building 2 :.. 3 : 1) :, 3 1 Vol. 3. 1 2008 2 CAA I Transactions on Intelligent Systems Feb. 2008, (,210093) :.,; 3., 3. :; ; ; ; : TP391 :A :167324785 (2008) 0120001208 A system f or automatic generation of 3D building models