How to tell the differences between a Cat and a Dog Masoud Alipour Ali Farhadi IPM – Scientific Computing Center Vision.

Slides:



Advertisements
Similar presentations
Scale & Affine Invariant Interest Point Detectors Mikolajczyk & Schmid presented by Dustin Lennon.
Advertisements

Compatible Spatial Discretizations for Partial Differential Equations May 14, 2004 Compatible Reconstruction of Vectors Blair Perot Dept. of Mechanical.
2D/3D Shape Manipulation, 3D Printing
Biomedical Person Identification via Eye Printing Masoud Alipour Ali Farhadi Ali Farhadi Nima Razavi.
Level set based Image Segmentation Hang Xiao Jan12, 2013.
Surface Reconstruction From Unorganized Point Sets
Surface normals and principal component analysis (PCA)
Discrete Differential Geometry Planar Curves 2D/3D Shape Manipulation, 3D Printing March 13, 2013 Slides from Olga Sorkine, Eitan Grinspun.
November 12, 2013Computer Vision Lecture 12: Texture 1Signature Another popular method of representing shape is called the signature. In order to compute.
Greedy Routing with Guaranteed Delivery Using Ricci Flow Jie Gao Stony Brook University Rik Sarkar, Xiaotian Yin, Feng Luo, Xianfeng David Gu.
 Distance Problems: › Post Office Problem › Nearest Neighbors and Closest Pair › Largest Empty and Smallest Enclosing Circle  Sub graphs of Delaunay.
Computational Geometry II Brian Chen Rice University Computer Science.
Extended Gaussian Images
CDS 301 Fall, 2009 Image Visualization Chap. 9 November 5, 2009 Jie Zhang Copyright ©
Ruslana Mys Delaunay Triangulation Delaunay Triangulation (DT)  Introduction  Delaunay-Voronoi based method  Algorithms to compute the convex hull 
3D Shape Histograms for Similarity Search and Classification in Spatial Databases. Mihael Ankerst,Gabi Kastenmuller, Hans-Peter-Kriegel,Thomas Seidl Univ.
3/5/15CMPS 3130/6130 Computational Geometry1 CMPS 3130/6130 Computational Geometry Spring 2015 Delaunay Triangulations II Carola Wenk Based on: Computational.
Discrete Geometry Tutorial 2 1
1st Meeting Industrial Geometry Computational Geometry ---- Some Basic Structures 1st IG-Meeting.
Surface Classification Using Conformal Structures Xianfeng Gu 1, Shing-Tung Yau 2 1. Computer and Information Science and Engineering, University of Florida.
CSCE 620: Open Problem Voronoi Diagram of Moving Points Asish Ghoshal Problem 2 from The Open Problems Project 1.
Active Contour Models (Snakes) 건국대학교 전산수학과 김 창 호.
Discrete geometry Lecture 2 1 © Alexander & Michael Bronstein
3. Delaunay triangulation
Delaunay Triangulation on the GPU Dan Maljovec. CPU Delaunay Triangulation Randomized Incremental Algorithm 1.Construct Bounding triangle 2.Choose point.
CENG 789 – Digital Geometry Processing 01- Introduction Asst. Prof. Yusuf Sahillioğlu Computer Eng. Dept,, Turkey.
International Workshop on Computer Vision - Institute for Studies in Theoretical Physics and Mathematics, April , Tehran 1 II SIZE FUNCTIONS:
International Workshop on Computer Vision
Abstract We present a model of curvilinear grouping using piecewise linear representations of contours and a conditional random field to capture continuity.
Chamfer Matching & Hausdorff Distance Presented by Ankur Datta Slides Courtesy Mark Bouts Arasanathan Thayananthan.
1 International Workshop on Computer Vision April 26-30, 2004 Tehran,Iran Singular Value Decompositions with applications to Singular Value Decompositions.
CS443: Digital Imaging and Multimedia Filters Spring 2008 Ahmed Elgammal Dept. of Computer Science Rutgers University Spring 2008 Ahmed Elgammal Dept.
Extension of M-VOTE: Improving Feature Detection
Hui Kong, Member, IEEE, Jean- Yves Audibert, and Jean Ponce, Fellow, IEEE.
Computing the Delaunay Triangulation By Nacha Chavez Math 870 Computational Geometry; Ch.9; de Berg, van Kreveld, Overmars, Schwarzkopf By Nacha Chavez.
CS 376b Introduction to Computer Vision 03 / 04 / 2008 Instructor: Michael Eckmann.
Information that lets you recognise a region.
CS4670: Computer Vision Kavita Bala Lecture 8: Scale invariance.
CS CS 175 – Week 4 Triangle Mesh Smoothing Discrete Differential Geometry.
00/4/103DVIP-011 Part Three: Descriptions of 3-D Objects and Scenes.
Linear Algebra and Image Processing
Introduction --Classification Shape ContourRegion Structural Syntactic Graph Tree Model-driven Data-driven Perimeter Compactness Eccentricity.
Presentation Image Filters
Intrinsic Parameterization for Surface Meshes Mathieu Desbrun, Mark Meyer, Pierre Alliez CS598MJG Presented by Wei-Wen Feng 2004/10/5.
05 - Feature Detection Overview Feature Detection –Intensity Extrema –Blob Detection –Corner Detection Feature Descriptors Feature Matching Conclusion.
Chapter 5 Image Restoration.
OBJECT RECOGNITION. The next step in Robot Vision is the Object Recognition. This problem is accomplished using the extracted feature information. The.
Digital Image Processing, 2nd ed. © 2002 R. C. Gonzalez & R. E. Woods Chapter 11 Representation & Description Chapter 11 Representation.
Course 12 Calibration. 1.Introduction In theoretic discussions, we have assumed: Camera is located at the origin of coordinate system of scene.
Positioning in Ad-Hoc Networks - Directions and Results Jan Beutel Computer Engineering and Networks Lab Swiss Federal Institute of Technology Zurich August.
Computational Photography Derek Hoiem, University of Illinois
Digital Image Processing, 2nd ed. © 2002 R. C. Gonzalez & R. E. Woods Representation & Description.
Acquiring 3D models of objects via a robotic stereo head David Virasinghe Department of Computer Science University of Adelaide Supervisors: Mike Brooks.
Differential Geometry Computer Vision #8. Differential Geometry 1. Curvature of curve 2. Curvature of surface 3. Application of curvature.
Introduction --Classification Shape ContourRegion Structural Syntactic Graph Tree Model-driven Data-driven Perimeter Compactness Eccentricity.
Many slides from Steve Seitz and Larry Zitnick
Mesh Coarsening zhenyu shu Mesh Coarsening Large meshes are commonly used in numerous application area Modern range scanning devices are used.
Geometric Modeling using Polygonal Meshes Lecture 3: Discrete Differential Geometry and its Application to Mesh Processing Office: South B-C Global.
Approximate Inference: Decomposition Methods with Applications to Computer Vision Kyomin Jung ( KAIST ) Joint work with Pushmeet Kohli (Microsoft Research)
Meeting 19 System of Linear Equations. Linear Equations A solution of a linear equation in n variables is a sequence of n real numbers s 1, s 2,..., s.
1 Section 5.3 Linear Systems of Equations. 2 THREE EQUATIONS WITH THREE VARIABLES Consider the linear system of three equations below with three unknowns.
Outline ● Introduction – What is the problem ● Generate stochastic textures ● Improve realism ● High level approach - Don't just jump into details – Why.
CDS 301 Fall, 2008 Domain-Modeling Techniques Chap. 8 November 04, 2008 Jie Zhang Copyright ©
Chapter 3 Lesson 2 The Graph Translation Theorem.
Correspondence search using Delaunay triangulation Rishu Gupta
Image Morphing © Zooface Many slides from Alexei Efros, Berkeley.
Mean Shift Segmentation
Domain-Modeling Techniques
Review: Linear Systems
Lecture 3 : Isosurface Extraction
Presentation transcript:

How to tell the differences between a Cat and a Dog Masoud Alipour Ali Farhadi IPM – Scientific Computing Center Vision Group Institute for Studies in Theoretical Physics and Mathematics Tehran-Iran

Outlines - Linear Predictive Coding Coefficients - Linear Predictive Coding Coefficients - Surfaces Associated to the LPC Coefficients. - Surfaces Associated to the LPC Coefficients. - Application of Computational Geometry. - Application of Computational Geometry. - Detection via Geometric Characteristics of - Detection via Geometric Characteristics of LPC Surface. LPC Surface. - Results - Results

Making Surfaces – LPC Coefficients. zoom

LPC Surfaces : 1) By Computing the LPC coefficients for each window W of the image, we obtain a set of data in R 20. 1) By Computing the LPC coefficients for each window W of the image, we obtain a set of data in R 20. 2) Each window is identified by its upper left corner index (x,y). 2) Each window is identified by its upper left corner index (x,y). 3) Project the data for each window to R by taking the average of the marked neighbors. 3) Project the data for each window to R by taking the average of the marked neighbors.

Projection to R: -Take average of 6,10,11,15 coefficients. -Take average of 6,10,11,15 coefficients. Origin

LPC Surface (continued): 4) Denote this average by F(x,y). 4) Denote this average by F(x,y). 5) Sliding window with overlaps defines a function on a grid. 5) Sliding window with overlaps defines a function on a grid. LPC Surface = Graph of F(x,y) LPC Surface = Graph of F(x,y)

(i p, j p) (i p’, j p’) ZpZpZpZp Z p’ (i p, j p, z p ) (i p’,j p’,z p’ )

Surfaces

Quantifying the Oscillations where k1 and k2 are the minimum and maximum (principal) surface curvature, respectively. Strain Energy (total curvature) Bending energy function (roughness measure)

Quantifying Oscillations (continued): Gaussian Curvature of a surface z=F(x,y) Gaussian Curvature of a surface z=F(x,y)

High curvature Low curvature Images from Caltech Multires Lab

Discrete Curvature M a triangulated surface (not necessarily smooth) M a triangulated surface (not necessarily smooth) Discrete Curvature at a vertex

Euler Number (characteristic)

Discrete Curvature Discrete Curvature satisfies some basic theorems of Differential Geometry cast in the discrete framework. Discrete Curvature satisfies some basic theorems of Differential Geometry cast in the discrete framework. 1. Gauss Bonnet Theorem is valid 1. Gauss Bonnet Theorem is valid 2. Every closed surface has triangulation of constant curvature. 2. Every closed surface has triangulation of constant curvature.

Triangulations 1)Uniform Triangulation 2)Delaunay Triangulation

Delaunay Triangulations Empty circle property Delaunay Triangulation and diagram Delaunay Triangulation and Voronoi diagram

Triangulated Surface

Counting the Number of Incident Edges. 1. Mapping center of gravity of each Triangle on the plate z=0. 2.Generating a uniform grid on z=o; 3. Centroid Matrix

Number of triangles per area Thus a triangle is assigned to a square grid if the orthogonal projection of the centroid of the triangle is located in that windows. Count the number of triangles which is assigned to the each window. Hence a matrix D is obtained.

LPC coefficients. Centroid Matrix

Comparing for detection The differences between the centroid matrices for cats and dogs are obvious. The differences between the centroid matrices for cats and dogs are obvious. Simply by using the means of matrices we can differentiate between cat and dog matrices. Simply by using the means of matrices we can differentiate between cat and dog matrices. Better statistical invariants are also applicable to the matrix D. For example,  - σ 2, etc. Better statistical invariants are also applicable to the matrix D. For example,  - σ 2, etc.

Results

Conclusion - This is not a image matching algorithm - This is not a shape matching algorithm - Objects are discriminated via texture analysis

? Questions