Applications of Shape Similarity.

Slides:



Advertisements
Similar presentations
Pseudo-Relevance Feedback For Multimedia Retrieval By Rong Yan, Alexander G. and Rong Jin Mwangi S. Kariuki
Advertisements

Complex Networks for Representation and Characterization of Images For CS790g Project Bingdong Li 9/23/2009.
CMPUT 615 Applications of Machine Learning in Image Analysis
Presented by Xinyu Chang
Kien A. Hua Division of Computer Science University of Central Florida.
1 s-t Graph Cuts for Binary Energy Minimization  Now that we have an energy function, the big question is how do we minimize it? n Exhaustive search is.
Image Indexing and Retrieval using Moment Invariants Imran Ahmad School of Computer Science University of Windsor – Canada.
Object Detection by Matching Longin Jan Latecki. Contour-based object detection Database shapes: …..
Content Based Image Clustering and Image Retrieval Using Multiple Instance Learning Using Multiple Instance Learning Xin Chen Advisor: Chengcui Zhang Department.
A Similarity Retrieval System for Multimodal Functional Brain Images Rosalia F. Tungaraza Advisor: Prof. Linda G. Shapiro Ph.D. Defense Computer Science.
Event prediction CS 590v. Applications Video search Surveillance – Detecting suspicious activities – Illegally parked cars – Abandoned bags Intelligent.
Iterative closest point algorithms
A Study of Approaches for Object Recognition
Research Update and Future Work Directions – Jan 18, 2006 – Ognjen Arandjelović Roberto Cipolla.
Motion based Correspondence for Distributed 3D tracking of multiple dim objects Ashok Veeraraghavan.
Video Google: Text Retrieval Approach to Object Matching in Videos Authors: Josef Sivic and Andrew Zisserman ICCV 2003 Presented by: Indriyati Atmosukarto.
Prénom Nom Document Analysis: Data Analysis and Clustering Prof. Rolf Ingold, University of Fribourg Master course, spring semester 2008.
Visual Querying By Color Perceptive Regions Alberto del Bimbo, M. Mugnaini, P. Pala, and F. Turco University of Florence, Italy Pattern Recognition, 1998.
Announcements Take home quiz given out Thursday 10/23 –Due 10/30.
Video Google: Text Retrieval Approach to Object Matching in Videos Authors: Josef Sivic and Andrew Zisserman University of Oxford ICCV 2003.
Radial Basis Function Networks
CSC 4510 – Machine Learning Dr. Mary-Angela Papalaskari Department of Computing Sciences Villanova University Course website:
Introduction --Classification Shape ContourRegion Structural Syntactic Graph Tree Model-driven Data-driven Perimeter Compactness Eccentricity.
Computer Vision and Data Mining Research Projects Longin Jan Latecki Computer and Information Sciences Dept. Temple University
Shape-Representation and Shape Similarity Dr. Rolf Lakaemper Part 1: Shapes.
A 3D Model Alignment and Retrieval System Ding-Yun Chen and Ming Ouhyoung.
Chapter 9 DTW and VQ Algorithm  9.1 Basic idea of DTW  9.2 DTW algorithm  9.3 Basic idea of VQ  9.4 LBG algorithm  9.5 Improvement of VQ.
SOFTWARE ENGINEERING MCS-2 LECTURE # 4. PROTOTYPING PROCESS MODEL  A prototype is an early sample, model or release of a product built to test a concept.
A survey of different shape analysis techniques 1 A Survey of Different Shape Analysis Techniques -- Huang Nan.
Efficient EMD-based Similarity Search in Multimedia Databases via Flexible Dimensionality Reduction / 16 I9 CHAIR OF COMPUTER SCIENCE 9 DATA MANAGEMENT.
CSE 185 Introduction to Computer Vision Face Recognition.
INTERACTIVELY BROWSING LARGE IMAGE DATABASES Ronald Richter, Mathias Eitz and Marc Alexa.
Object Recognition Based on Shape Similarity Longin Jan Latecki Computer and Information Sciences Dept. Temple Univ.,
Halftoning With Pre- Computed Maps Objective Image Quality Measures Halftoning and Objective Quality Measures for Halftoned Images.
Data Mining, ICDM '08. Eighth IEEE International Conference on Duy-Dinh Le National Institute of Informatics Hitotsubashi, Chiyoda-ku Tokyo,
CIS 350 Principles and Applications Of Computer Vision Dr. Rolf Lakaemper.
Shape-Representation and Shape Similarity PART 2 Dr. Rolf Lakaemper.
Vector Quantization Vector quantization is used in many applications such as image and voice compression, voice recognition (in general statistical pattern.
Shape similarity and Visual Parts Longin Jan Latecki Temple Univ., In cooperation with Rolf Lakamper (Temple Univ.),
Discrete Approach to Curve and Surface Evolution
Using the Particle Filter Approach to Building Partial Correspondences between Shapes Rolf Lakaemper, Marc Sobel Temple University, Philadelphia,PA,USA.
Shape-Representation and Shape Similarity Dr. Rolf Lakaemper Part 1: Shapes.
Collaborative Filtering via Euclidean Embedding M. Khoshneshin and W. Street Proc. of ACM RecSys, pp , 2010.
Cluster Analysis Dr. Bernard Chen Assistant Professor Department of Computer Science University of Central Arkansas.
Introduction to Scale Space and Deep Structure. Importance of Scale Painting by Dali Objects exist at certain ranges of scale. It is not known a priory.
Imran N. Junejo, Omar Javed and Mubarak Shah University of Central Florida, Proceedings of the 17th International Conference on Pattern Recognition, pp ,
Video Google: Text Retrieval Approach to Object Matching in Videos Authors: Josef Sivic and Andrew Zisserman University of Oxford ICCV 2003.
Cluster Analysis What is Cluster Analysis? Types of Data in Cluster Analysis A Categorization of Major Clustering Methods Partitioning Methods.
Cluster Analysis This work is created by Dr. Anamika Bhargava, Ms. Pooja Kaul, Ms. Priti Bali and Ms. Rajnipriya Dhawan and licensed under a Creative Commons.
Hough Transform Elegant method for direct object recognition
Naifan Zhuang, Jun Ye, Kien A. Hua
Agglomerative clustering (AC)
Fast Subsequence Matching in Time-Series Databases.
Unsupervised Riemannian Clustering of Probability Density Functions
A Perceptual Shape Descriptor
Video Google: Text Retrieval Approach to Object Matching in Videos
CIS Introduction to Computer Vision
CAP 5415 Computer Vision Fall 2012 Dr. Mubarak Shah Lecture-5
Aim of the project Take your image Submit it to the search engine
Outline H. Murase, and S. K. Nayar, “Visual learning and recognition of 3-D objects from appearance,” International Journal of Computer Vision, vol. 14,
Object Recognition Today we will move on to… April 12, 2018
Similarity Search: A Matching Based Approach
CS4670: Intro to Computer Vision
Video Google: Text Retrieval Approach to Object Matching in Videos
Color Image Retrieval based on Primitives of Color Moments
Dept. of Computer and Information Sciences
Pattern Recognition and Training
Pattern Recognition and Training
Color Image Retrieval based on Primitives of Color Moments
Iterative Projection and Matching: Finding Structure-preserving Representatives and Its Application to Computer Vision.
Presentation transcript:

Applications of Shape Similarity

Robotics: Shape Screening ASR: Applications in Computer Vision Robotics: Shape Screening (Movie: Robot2.avi) Straightforward Training Phase Recognition of Rough Differences Recognition of Differences in Detail Recognition of Parts

View Invariant Human Activity Recognition ASR: Applications in Computer Vision Application 2: View Invariant Human Activity Recognition (Dr. Cen Rao and Mubarak Shah, School of Electrical Engineering and Computer Science, University of Central Florida)

Human Action Defined by Trajectory Application: Human Activity Recognition Human Action Defined by Trajectory Action Recognition by Comparison of Trajectories (Movie: Trajectories) Rao / Shah: Extraction of ‘Dynamic Instants’ by Analysis of Spatiotemporal Curvature Comparison of ‘Dynamic Instants’ (Sets of unconnected points !) ASR: Simplification of Trajectories by Curve Evolution Comparison of Trajectories

Application: Human Activity Recognition Simplification Trajectory

Activity Recognition: Typical Set of Trajectories

Trajectories in Tangent Space

Trajectory Comparison by ASR: Results

Recognition of 3D Objects by Projection Background: MPEG 7 uses fixed view angles Improvement: Automatic Detection of Key Views

Automatic Detection of Key Views (Pairwise) Comparison of Adjacent Views Detects Appearance of Hidden Parts

Automatic Detection of Key Views Result (work in progress):

The Database Implementation Application: ASR The Database Implementation

The Main Application: Back to ISS Task: Create Image Database Problem: Response Time Comparison of 2 Shapes: 23ms on Pentium1Ghz ISS contains 15,000 images: Response Time about 6 min. Clustering not possible: ASR failed on measuring dissimilarities !

Vantage Objects Solution: Full search on entire database using a simpler comparison Vantage Objects (Vleugels / Veltkamp, 2000) provide a simple comparison of n- dimensional vectors (n typically < 100)

Vantage Objects The Idea: Compare the query-shape q to a predefined subset S of the shapes in the database D The result is an n-dimensional Vantage Vector V, n = |S| s1 v1 s2 v2 q s3 v3 … sn vn

Vantage Objects - Each shape can be represented by a single Vantage Vector - The computation of the Vantage Vector calls the ASR – comparison only n times - ISS uses 54 Vantage Objects, reducing the comparison time (needed to create the Vantage Vector) to < 1.5s - How to compare the query object to the database ?

Vantage Objects - Create the Vantage Vector vi for every shape di in the database D - Create the Vantage Vector vq for the query-shape q - compute the (euclidean) distance between vq and vi - best response is minimum distance Note: computing the Vantage Vectors for the database objects is an offline process !

How to define the set S of Vantage Objects ?

k=1..i-1 e(di , sk) maximal. (e = eucl. dist.) Vantage Objects Algorithm 1 (Vleugels / Veltkamp 2000): Predefine the number n of Vantage Objects S0 = { } Iteratively add shapes di  D\Si-1 to Si-1 such that Si = Si-1  di and k=1..i-1 e(di , sk) maximal. (e = eucl. dist.) Stop if i = n.

Vantage Objects Result: Did not work for ISS.

Algorithm 2 (Latecki / Henning / Lakaemper): Vantage Objects Algorithm 2 (Latecki / Henning / Lakaemper): Def.: A(s1,s2): ASR distance of shapes s1,s2 q: query shape ‘Vantage Query’ : determining the result r by minimizing e(vq , vi ) vi = Vantage Vector to si ‘ASR Query’: determining the result r by minimizing A(q,di ) Vantage Query has certain loss of retrieval quality compared to ASR query. Define a loss function l to model the extent of retrieval performance

Vantage Objects Given a Database D and a set V of Vantage Vectors, the loss of retrieval performance for a single query by shape q is given by: lV,D (q) = A(q,r), Where r denotes the resulting shape of the vantage query to D using q. Property: lV,D (q) is minimal if r is the result of the ASR-Query.

L(S) = 1/n  lS,D\{si} (si) Vantage Objects Now define retrieval error function L(S) of set S={s1 ,…, sn }  D of Vantage Vectors of Database D: L(S) = 1/n  lS,D\{si} (si) Task: Find subset S  D such that L(S) is minimal.

Vantage Objects Algorithm: V0={ } iteratively determine sj in D\Sj-1 such that Sj =Sj-1  sj and L(Vj) minimal. Stop if improvement is low

Number of Vantage Objects Result: Worked fine for ISS, though handpicked objects still performed better. Handpicked Algorithm 2 L(S) Number of Vantage Objects

Vantage Objects …some of the Vantage Objects used in ISS:

Vantage Objects and ISS The Vantage Objects are used in the ASR in the first (handdrawn) query. The query is compared to 54 Objects, then a vector comparison is computed with the whole database. The first result, also called ‘first guess’, is the result of the vantage vector search. Searching for a ‘grabbed’ a shape on the user interface leads to direct comparison with the ASR, these results are precomputed, since the query is a known shape !

Vantage Objects and ISS A: the handdrawn sketch B: the result of the Vantage search C: the result of the exact match