人脸识别英文.ppt

Topic 5. Human Faces Face Image Databases Face Image Databases References. Outline Face Detection Methods [5] Face vs non face Clsutering Distance Measure Deformable Face Template Local Deformation and Global Transform Deformable Model of Facial Features Upper Face Action Units Lower Face Action Units Templates for Various States Templates for Various States Features for Action Unit Recognition Classification from Feature Vector Recognition Rate Apparence Model: Landmarks on a face Eigen vectors for Geometry and Photometry Apparence Model Face Localization and Recognition A Linear HMM Model for Face Face Detection Sample of the 4D space Multi scale Detection Edge Features Decision Tree Examples of Decision Trees Bounds Analysis Some Examples Face Prior Learning: Experimental Details 83 key points defined on face 720 individuals with all kinds of types Dimension reduced to 33 by PCA 40000 samples drawn by the inhomogeneous Gibbs sampler in each Monte Carlo integration 50 features pursuit Total runtime: about 5 days on a PIII 667, 256MB PC Obs Syn Samples 1 Synthesis Samples Synthesis Samples 50 Observed Histograms 50 Synthesized Histograms Observed faces Synthesized faces without any features Synthesized faces with 20 features Synthesized faces with 10 features Human face is extensively studied in vision. Depending on the applications, there are a long list of tasks [5]: Detection and Recognition: Face detection finding all faces in a picture, facial feature detection eyes, lips, …, Face localization detecting a single face in image, Face recognition or identification from a database, classification Face authentication verifying claim, bank id, Age/gender recognition, Face tracking location and pose over time Facical expression recognition affective states, aesthetic study. Modeling and Photorealistic Synthesis: Appearance models, deformable templates, lighting models, facial action units, face hallucination high resolution from low resolution, pose adjustment, image editing removing wrinkles, eye glass, red eye etc. 3. Artistic rendering Sketch, portrait, caricature, cartoon, painting, … The CMU Rowley dataset The CMU Schneidrman and Kanade Dataset 1. P. Hallinan, G. Gordon, A. Yuille, P. Giblin, and D. Mumford, 2D and 3D Patterns of the Face, A.K. Peters, Ltd. Book chapters 2 4. handouts. 2. D.H. Ballard, "Generaling the Hough transform to detect arbitrary shapes", in handbook. 3. P. Viola and M. Jones, "Robust Real Time Object Detection", 4. F. Fleuret and D. Geman, " Coarse to fine face detection", IJCV 411/2,2001. 5. M.H. Yang, D. Kriegman, N. Ahuja, “Detecting faces in images, a survey”, PAMI vol.24,no.1, January, 2002. 6 T.F.Cootes, G.J. Edwards and C.J.Taylor. "Active Appearance Models", ECCV 1998 7. C. Liu, S. C. Zhu, and H. Y. Shum, "Learning inhomogeneous Gibbs models of faces by minimax entropy", ICCV 2001. 8. Y. Tian, T. Kanade, and J. Cohn, "Recognizing action units for facial expression analysis" PAMI, Feb, 2001. 9. H. Chen, Y. Q. Xu, H. Y. Shum, S. C. Zhu, and N. N. Zhen, "Example based facial sketch generation with non parametric sampling", ICCV 2001. We proceed in three steps: A survey on face detection and recognition techniques Mathematical models of face images 3. Face synthesis: photorealistic and non photorealistic. 6 clusters in a 19 x19 space Sung and Poggio D1 D2 For each input image, it measures two distances for each cluster center: D1 is the Mahalanobis distance and D2 is the Euclidean distance. Thus Sung and poggio have 2 x 6 x 2 = 24 features for classification in a multiple layer perceptron. Deformable face template by Fishler and Elschlager 1973. M. Fishler and R. Elschlager, “The representation and matching of pictorial structures”, IEEE Trans. on Computer. Vol.C 22, 67 92, 1973. Geometric variations of faces: Hallinan, Yuille, Mumford et al Eye template using parabolic curves by Yuille et al 1989 92. A.L.Yuille, D. Cohen, and P.Hallinan, “Feature extraction from faces using deformable templates”, CVPR 89, IJCV 92. We can derive meaningful diffusion equations from the energy functionals. 400 images each labeled with 122 points.