Paper Reading Dalong Du April.08, 2011.

Slides:



Advertisements
Similar presentations
Active Appearance Models
Advertisements

Image Registration  Mapping of Evolution. Registration Goals Assume the correspondences are known Find such f() and g() such that the images are best.
BRIEF: Binary Robust Independent Elementary Features
Aggregating local image descriptors into compact codes
Principal Component Analysis Based on L1-Norm Maximization Nojun Kwak IEEE Transactions on Pattern Analysis and Machine Intelligence, 2008.
Presented by Xinyu Chang
Human Identity Recognition in Aerial Images Omar Oreifej Ramin Mehran Mubarak Shah CVPR 2010, June Computer Vision Lab of UCF.
Computer Vision for Human-Computer InteractionResearch Group, Universität Karlsruhe (TH) cv:hci Dr. Edgar Seemann 1 Computer Vision: Histograms of Oriented.
Object Recognition using Invariant Local Features Applications l Mobile robots, driver assistance l Cell phone location or object recognition l Panoramas,
Activity Recognition Aneeq Zia. Agenda What is activity recognition Typical methods used for action recognition “Evaluation of local spatio-temporal features.
Foreground Modeling The Shape of Things that Came Nathan Jacobs Advisor: Robert Pless Computer Science Washington University in St. Louis.
Wangfei Ningbo University A Brief Introduction to Active Appearance Models.
AAM based Face Tracking with Temporal Matching and Face Segmentation Dalong Du.
Image alignment Image from
1 Minimum Ratio Contours For Meshes Andrew Clements Hao Zhang gruvi graphics + usability + visualization.
Instructor: Mircea Nicolescu Lecture 13 CS 485 / 685 Computer Vision.
Object Recognition with Invariant Features n Definition: Identify objects or scenes and determine their pose and model parameters n Applications l Industrial.
ICIP 2000, Vancouver, Canada IVML, ECE, NTUA Face Detection: Is it only for Face Recognition?  A few years earlier  Face Detection Face Recognition 
Real-time Embedded Face Recognition for Smart Home Fei Zuo, Student Member, IEEE, Peter H. N. de With, Senior Member, IEEE.
A Study of Approaches for Object Recognition
Object Recognition with Invariant Features n Definition: Identify objects or scenes and determine their pose and model parameters n Applications l Industrial.
Rodent Behavior Analysis Tom Henderson Vision Based Behavior Analysis Universitaet Karlsruhe (TH) 12 November /9.
Scale Invariant Feature Transform (SIFT)
Presented by Zeehasham Rasheed
1 Invariant Local Feature for Object Recognition Presented by Wyman 2/05/2006.
Smart Traveller with Visual Translator for OCR and Face Recognition LYU0203 FYP.
Multiple Object Class Detection with a Generative Model K. Mikolajczyk, B. Leibe and B. Schiele Carolina Galleguillos.
A String Matching Approach for Visual Retrieval and Classification Mei-Chen Yeh* and Kwang-Ting Cheng Learning-Based Multimedia Lab Department of Electrical.
PhD Thesis. Biometrics Science studying measurements and statistics of biological data Most relevant application: id. recognition 2.
Face Alignment Using Cascaded Boosted Regression Active Shape Models
Distinctive Image Features from Scale-Invariant Keypoints By David G. Lowe, University of British Columbia Presented by: Tim Havinga, Joël van Neerbos.
Computer vision.
Internet-scale Imagery for Graphics and Vision James Hays cs195g Computational Photography Brown University, Spring 2010.
Multimodal Interaction Dr. Mike Spann
Prakash Chockalingam Clemson University Non-Rigid Multi-Modal Object Tracking Using Gaussian Mixture Models Committee Members Dr Stan Birchfield (chair)
1 Interest Operators Harris Corner Detector: the first and most basic interest operator Kadir Entropy Detector and its use in object recognition SIFT interest.
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.
IEEE TRANSSACTIONS ON PATTERN ANALYSIS AND MACHINE INTELLIGENCE
Scientific Writing Abstract Writing. Why ? Most important part of the paper Number of Readers ! Make people read your work. Sell your work. Make your.
80 million tiny images: a large dataset for non-parametric object and scene recognition CS 4763 Multimedia Systems Spring 2008.
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,
Histograms of Oriented Gradients for Human Detection(HOG)
Paper Reading Dalong Du Nov.27, Papers Leon Gu and Takeo Kanade. A Generative Shape Regularization Model for Robust Face Alignment. ECCV08. Yan.
A Multiresolution Symbolic Representation of Time Series Vasileios Megalooikonomou Qiang Wang Guo Li Christos Faloutsos Presented by Rui Li.
AAM based Face Tracking with Temporal Matching and Face Segmentation Mingcai Zhou 1 、 Lin Liang 2 、 Jian Sun 2 、 Yangsheng Wang 1 1 Institute of Automation.
GENDER AND AGE RECOGNITION FOR VIDEO ANALYTICS SOLUTION PRESENTED BY: SUBHASH REDDY JOLAPURAM.
CSE 185 Introduction to Computer Vision Feature Matching.
776 Computer Vision Jan-Michael Frahm Spring 2012.
Finding Clusters within a Class to Improve Classification Accuracy Literature Survey Yong Jae Lee 3/6/08.
CSCI 631 – Foundations of Computer Vision March 15, 2016 Ashwini Imran Image Stitching.
CSCI 631 – Foundations of Computer Vision March 15, 2016 Ashwini Imran Image Stitching Link: singhashwini.mesinghashwini.me.
776 Computer Vision Jan-Michael Frahm Spring 2012.
Face recognition using Histograms of Oriented Gradients
Another Example: Circle Detection
Visual homing using PCA-SIFT
Deeply learned face representations are sparse, selective, and robust
Bag-of-Visual-Words Based Feature Extraction
Scale Invariant Feature Transform (SIFT)
Nonparametric Semantic Segmentation
Paper Presentation: Shape and Matching
Dynamical Statistical Shape Priors for Level Set Based Tracking
Cheng-Ming Huang, Wen-Hung Liao Department of Computer Science
Image Segmentation Techniques
CAP 5415 Computer Vision Fall 2012 Dr. Mubarak Shah Lecture-5
Geometric Hashing: An Overview
The SIFT (Scale Invariant Feature Transform) Detector and Descriptor
SIFT.
CSE 185 Introduction to Computer Vision
Presented by Xu Miao April 20, 2005
Learning Incoherent Sparse and Low-Rank Patterns from Multiple Tasks
Presentation transcript:

Paper Reading Dalong Du April.08, 2011

Paper Jilin Tu, Brandon Laften, Xiaoming Liu, Musodiq Bello, Jens Rittscher, Peter Tu. LPSM: Fitting Shape Model by Linear Programming

Outline Author Introduction. Problem Introduction. How to do? Discussion.

Outline Author Introduction. Abstract. Why to do? How to do? Discussion.

Author Introduction (1/2) Jilin Tu Xiaoming Liu

Author Introduction (2/2) Xiaoming Liu A Researcher in the Visualization and Computer Vision lab at GE Global Research.  His current research focuses on facial image processing in the context of surveillance videos. More specifically, He works on facial image alignment, face super-resolution from video sequences, face recognition, etc. Previously, He has also worked on multimedia information retrieval, video-based human animation, etc. In a broader sense, His interests include computer vision, pattern recognition, information retrieval, and machine learning. Education Background B.S. degree from Beijing Information Technology Institute, Beijing, China in 1997 M.S. degrees from Zhejiang University, Hangzhou, China in 2000 Ph.D. degree in Electrical and Computer Engineering from Carnegie Mellon University, in 2004.

Outline Author Introduction. Abstract. Why to do? How to do? Discussion.

Abstract Introduction (1/2) Abstract—We propose a shape model fitting algorithm tha uses linear programming optimization. Most shape model fitting approaches (such as ASM, AAM) are based on gradient-descent-like local search optimization and usually suffer from local minima. In contrast, linear programming (LP) techniques achieve globally optimal solution for linear problems. In [1], a linear programming scheme based on successive convexification was proposed for matching static object shape in images among cluttered background and achieved very good performance. In this paper, we rigorously derive the linear formulation of the shape model fitting problem in the LP scheme and propose a LP shape model fitting algorithm (LPSM). In the experiments, we compared the performance of our LPSM with the LP graph matching algorithm(LPGM), ASM, and a CONDENSATION based ASM algorithm on a test set of PUT database. The experiments show that LPSM can achieve higher shape fitting accuracy. We also evaluated its performance on the fitting of some real world face images collected from internet . The results show that LPSM can handle various appearance outliers and can avoid local minima problem very well, as the fitting is carried out by LP optimization with l1 norm robust cost function.

Abstract Introduction (2/2) 摘要——我们提出了一种利用线性规划优化策略的形状模型匹配算法。大多数形状模型匹配算法(例如ASM,AAM)是基于类梯度下降局部搜索优化策略的,于是通常会陷入局部极小。与之相反的是,线性规划技术给出了针对线性问题的全局优化解决方案。[1]中提出了基于连续凸化的线性规划(LP)方案来匹配复杂背景下的静态对象形状,并取得了很好的效果。本文中,我们严格推导出了在LP方案下的形状模型匹配问题的线性形式,并提出了LP形状模型匹配算法(LPSM)。实验中,在PUT数据库的测试集上,我们对比了LPSM与LP图匹配算法(LPGM),ASM以及基于CONDENSATION的ASM算法的性能。实验表明,LPSM能够达到更高的形状匹配精度。我们也评价了算法在真实环境下人脸图像的性能,这些人脸图像从互联网上收集而来。结果显示LPSM能够处理各种各样的异常表观图像并且能非常好的避免局部极小问题,这是因为匹配是通过带有L1范式的鲁棒代价函数线性规划优化来完成的。

Outline Author Introduction. Abstract. Why to do? How to do? Discussion.

Why to do? (1/2) Brief summary Shape model Appearance model PCA->Kernel PCA, hierarchical Bayesian model Appearance model Gaussian distribution->mixture of Gaussians with discriminative features Fitting algorithm Coarse-to-fine iterative optimization process by PCA subspace->EM optimization, sampling based approach in a Bayesian framework Heavily depend on good initialization Gradient descent optimization in essence

Why to do? (2/2) Linear Programming Be able to achieve globally optimal solution to linear objective functions subject to linear constraint Solution Incorporate a shape subspace model into a LP framework

Outline Author Introduction. Abstract. Why to do? How to do? Discussion.

How to do?---pre-knowledge (1/4) Model Training A intrinsic shape S Shape alignment Procrustes Analysis PCA A extrinsic transformation θ similarity Transformation s, R, t Aligned Shapes c θ

How to do?---pre-knowledge (2/4) Intrinsic shape space to extrinsic image space Rearrange

How to do?---pre-knowledge (3/4) Intrinsic shape space to extrinsic image space, continue The training shape data is normalized by removing scale, rotation and translation Be Complementary Space for each other Rearrange We have

How to do?---pre-knowledge (4/4) Model fitting Fitting model to the object involves minimizing the following cost function with the constraint ,

How to do? (1/12) Graph matching by linear programming Given a point set , , pre-define a set of pair-wise neighboring model points is a target point in a query image matching to the point p The object function for minimizing the matching cost

How to do? (2/12) Graph matching by linear programming, continue

How to do? (3/12) Graph matching by linear programming, continue Remove L1 norm Use line segment to approximate unit circle 即 substitute with

How to do? (4/12) Shape model fitting by linear programming Formulate shape model in a LP framework

How to do? (5/12) Shape model fitting by linear programming, continue Linearization Scale factor object orientation Four line segment introduces inaccuracy Use polygon to approximate cycle

How to do? (6/12) Shape model fitting by linear programming, continue Object function algorithm

How to do? (7/12) Improvement Convex hull constraint in the intrinsic shape The PCA(hypercube) is not compact enough Add additional constraints by quantizing the shape space and modeling the allowable intrinsic shape parameter distributions by histograms in the top k most correlated dimensions in the parameter space Take k = 3

How to do? (8/12) Improvement Model appearance likelihood in maximal rejection classifier(MRC) subspace Carry out canny edge detection---blue point Evaluate the normalized correlation between the image patch on the landmark and the image patches centering on the canny edge points that are 4-10 pixels away from the landmark. Acquire eight image patches centering on the edges that have the maximal normalized correlation

How to do? (9/12) Implementation Obtain the Two method to compute the fitted landmarks

How to do? (10/12) Experiment PCA, FDA, MRC MRC more discriminative than PCA and more smoother than FDA

How to do? (11/12) Experiment

How to do? (12/12) Experiment

Outline Author Introduction. Abstract. Why to do? How to do? Discussion.

Discussion More powerful feature extraction method SIFT HOG Utilize more advantage learning techniques AdaBoost Make LPSM real-time Parallel computing Coarse-to-fine image pyramid analysis techniques

Thank you!