ECE738 Advanced Image Processing Face Recognition by Elastic Bunch Graph Matching IEEE Trans. PAMI, July 1997.

Slides:



Advertisements
Similar presentations
Golden face grade By Yael Gabay & adi sherf. What is the Golden ratio?
Advertisements

Active Shape Models Suppose we have a statistical shape model –Trained from sets of examples How do we use it to interpret new images? Use an “Active Shape.
November 12, 2013Computer Vision Lecture 12: Texture 1Signature Another popular method of representing shape is called the signature. In order to compute.
Face Recognition and Biometric Systems Elastic Bunch Graph Matching.
Face Recognition By Sunny Tang.
Face Alignment with Part-Based Modeling
Computer Vision Lecture 16: Texture
Image Enhancement by Modifying Gray Scale of Individual Pixels
Lecture 07 Segmentation Lecture 07 Segmentation Mata kuliah: T Computer Vision Tahun: 2010.
Amir Hosein Omidvarnia Spring 2007 Principles of 3D Face Recognition.
Complex Feature Recognition: A Bayesian Approach for Learning to Recognize Objects by Paul A. Viola Presented By: Emrah Ceyhan Divin Proothi Sherwin Shaidee.
Face Recognition & Biometric Systems Support Vector Machines (part 2)
Adviser : Ming-Yuan Shieh Student ID : M Student : Chung-Chieh Lien VIDEO OBJECT SEGMENTATION AND ITS SALIENT MOTION DETECTION USING ADAPTIVE BACKGROUND.
Face Recognition & Biometric Systems, 2005/2006 Face recognition process.
Face Recognition Committee Machine Presented by Sunny Tang.
Real-time Embedded Face Recognition for Smart Home Fei Zuo, Student Member, IEEE, Peter H. N. de With, Senior Member, IEEE.
Image Filtering CS485/685 Computer Vision Prof. George Bebis.
1Ellen L. Walker Recognizing Objects in Computer Images Ellen L. Walker Mathematical Sciences Dept Hiram College Hiram, OH 44234
7. Neighbourhood operations A single pixel considered in isolation conveys information on the intensity and colour at a single location in an image, but.
Face Detection: a Survey Speaker: Mine-Quan Jing National Chiao Tung University.
Spacecraft Stereo Imaging Systems Group S3. Variables Separation of the cameras Height of the cameras – relative to the bench Angle – The direction cameras.
12009/12/16 Hierarchical Ensemble of Global and Local Classifiers for Face Recognition Yu Su, Shiguang Shan, Member, IEEE, Xilin Chen, Member, IEEE, and.
Hui Kong, Member, IEEE, Jean- Yves Audibert, and Jean Ponce, Fellow, IEEE.
2D Fourier Theory for Image Analysis Mani Thomas CISC 489/689.
Recognition – PCA and Templates. Recognition Suppose you want to find a face in an imageSuppose you want to find a face in an image One possibility: look.
Smart Traveller with Visual Translator for OCR and Face Recognition LYU0203 FYP.
Image Databases for Face Recognition System Yumiko Shironouchi.
Robust estimation Problem: we want to determine the displacement (u,v) between pairs of images. We are given 100 points with a correlation score computed.
Oral Defense by Sunny Tang 15 Aug 2003
Image Processing David Kauchak cs458 Fall 2012 Empirical Evaluation of Dissimilarity Measures for Color and Texture Jan Puzicha, Joachim M. Buhmann, Yossi.
Face Recognition Using Neural Networks Presented By: Hadis Mohseni Leila Taghavi Atefeh Mirsafian.
Multiclass object recognition
CS Spring 2012 CS 414 – Multimedia Systems Design Lecture 8 – JPEG Compression (Part 3) Klara Nahrstedt Spring 2012.
Following the work of John Daugman University of Cambridge
Klara Nahrstedt Spring 2011
1 ECE 738 Paper presentation Paper: Active Appearance Models Author: T.F.Cootes, G.J. Edwards and C.J.Taylor Student: Zhaozheng Yin Instructor: Dr. Yuhen.
Access Control Via Face Recognition Progress Review.
Texture. Texture is an innate property of all surfaces (clouds, trees, bricks, hair etc…). It refers to visual patterns of homogeneity and does not result.
AUTOMATIZATION OF COMPUTED TOMOGRAPHY PATHOLOGY DETECTION Semyon Medvedik Elena Kozakevich.
© by Yu Hen Hu 1 ECE533 Digital Image Processing Image Segmentation.
Multimodal Information Analysis for Emotion Recognition
HP-PURDUE-CONFIDENTIAL Final Exam May 16th 2008 Slide No.1 Outline Motivations Analytical Model of Skew Effect and its Compensation in Banding and MTF.
ECE738 Advanced Image Processing Face Detection IEEE Trans. PAMI, July 1997.
A Two-level Pose Estimation Framework Using Majority Voting of Gabor Wavelets and Bunch Graph Analysis J. Wu, J. M. Pedersen, D. Putthividhya, D. Norgaard,
Why is computer vision difficult?
Variation of aspect ratio Voice section Correct voice section Voice Activity Detection by Lip Shape Tracking Using EBGM Purpose What is EBGM ? Experimental.
Computer Vision Lecture #10 Hossam Abdelmunim 1 & Aly A. Farag 2 1 Computer & Systems Engineering Department, Ain Shams University, Cairo, Egypt 2 Electerical.
Levels of Image Data Representation 4.2. Traditional Image Data Structures 4.3. Hierarchical Data Structures Chapter 4 – Data structures for.
1 Iris Recognition Ying Sun AICIP Group Meeting November 3, 2006.
Categorization by Learning and Combing Object Parts B. Heisele, T. Serre, M. Pontil, T. Vetter, T. Poggio. Presented by Manish Jethwa.
Face Detection Using Skin Color and Gabor Wavelet Representation Information and Communication Theory Group Faculty of Information Technology and System.
By: David Gelbendorf, Hila Ben-Moshe Supervisor : Alon Zvirin
Course14 Dynamic Vision. Biological vision can cope with changing world Moving and changing objects Change illumination Change View-point.
Introduction Performance of metric learning is heavily dependent on features extracted Sensitive to Performance of Filters used Need to be robust to changes.
Image Quality Measures Omar Javed, Sohaib Khan Dr. Mubarak Shah.
1 A Multimodal Approach for Face Modeling and Recognition 指導老師 : 萬書言 老師 學生 : 何炳杰.
Evaluation of Gender Classification Methods with Automatically Detected and Aligned Faces Speaker: Po-Kai Shen Advisor: Tsai-Rong Chang Date: 2010/6/14.
Face Detection & Recognition
A Neurodynamical Cortical Model of Visual Attention and Invariant Object Recognition Gustavo Deco Edmund T. Rolls Vision Research, 2004.
EE368 Final Project Spring 2003
Image Pre-Processing in the Spatial and Frequent Domain
PRESENTED BY Yang Jiao Timo Ahonen, Matti Pietikainen
Object Recognition in the Dynamic Link Architecture
Following the work of John Daugman University of Cambridge
Image Segmentation Techniques
Binocular Stereo Vision
Statistical Deconvolution for Superresolution Fluorescence Microscopy
Digital Image Processing Week IV
Instructor: Professor Yu Hen Hu
--- Range Image Registration
Presentation transcript:

ECE738 Advanced Image Processing Face Recognition by Elastic Bunch Graph Matching IEEE Trans. PAMI, July 1997

ECE738 Advanced Image Processing (C) 2005 by Yu Hen Hu 2

ECE738 Advanced Image Processing (C) 2005 by Yu Hen Hu 3

ECE738 Advanced Image Processing (C) 2005 by Yu Hen Hu 4 Gabor Transform Gabor Function Daugman, IEEE Trans. ASSP July 1988

ECE738 Advanced Image Processing (C) 2005 by Yu Hen Hu 5 Gabor Wavelet Transform An implementation of Gabor transform Gaussian envelop width  = 2  Last term in complex sinusoids removes DC in the kernel 5 level spatial frequency from 4 to 16 pixels in an 128 x 128 image, 8 orientations Daugman, IEEE Trans. ASSP July 1988

ECE738 Advanced Image Processing (C) 2005 by Yu Hen Hu 6 Jet a set of 40 (5 spatial frequency, 8 orientations) complex Gabor wavelet coefficients for one image point. J = [a 1, a 2, …, a 40 ] Similarity between jets: d is the displacement of pixels: needs to be estimated. k j : spatial wave vector Fig. 1. Similarities S a (J,J’) (dashed line) and S  (J,J’) (solid line) with J’ taken from the left eye of a face, and J taken from pixel positions of the same horizontal line. The dotted line shows the estimated displacement d (divided by eight to fit the ordinate range). The right eye is 24 pixels away from the left eye, generating a local maximum for both similarity functions and zero displacement close to d x = -24.

ECE738 Advanced Image Processing (C) 2005 by Yu Hen Hu 7 Face Graph Facial fiducial points –Pupil, tip of mouth, etc. Face graph –Nodes at fiducial pts. –Un-directed graph –Object-adaptive –The structure of graph is the same for each face –Fitting a face image to a face graph is done automatically –Some nodes may be undefined due to occlusion. Hence, association of nodes of different face graphs may need to be done manually. Bunch –A set of Jets all asso with the same fiducial pt. –e.g. an eye Jet may consists of different types of eyes: open, closed, male, female, etc. Face bunch graph (FBG): –Same as a face graph, except each node consists of a jet bunch rather than a jet

ECE738 Advanced Image Processing (C) 2005 by Yu Hen Hu 8 Face Bunch Graph Has the same structure as individual face graph –Each node labeled with a bunch of jets –Each edge labeled with average distance between corresponding nodes in face samples Given a new face, an elastic bunch graph matching (EBGM) method selects the best fitting jets (local experts) from the bunch dedicated to each node in the face bunch graph.

ECE738 Advanced Image Processing (C) 2005 by Yu Hen Hu 9 Elastic Bunch Graph Matching Graph similarity measure : weighting factor Initially, manually generate a few FGs to create a FBG Heuristic algorithm to find the image graph that maximizes the similarity: –Coarse scan of image using jets to detect face –Varying sizes and aspect ratio of FBG to adapt to right format of face. –Finally, all nodes are moved locally to maximize S B.

ECE738 Advanced Image Processing (C) 2005 by Yu Hen Hu 10 Results