complex networks for representation and characterization of object

16
Complex Networks for Representation and Characterization of Object For CS790g Project Bingdong Li 11/9/2009

Upload: yvon

Post on 25-Feb-2016

33 views

Category:

Documents


0 download

DESCRIPTION

Complex Networks for Representation and Characterization of Object. For CS790g Project Bingdong Li 11/9/2009. Outline Of Methodology. Re-introduce Traditional Approaches Proposed Methods Issues Summary Questions and Comments. Re-introduce Traditional Approaches . - PowerPoint PPT Presentation

TRANSCRIPT

Page 1: Complex Networks for Representation and Characterization of Object

Complex Networks for Representation and

Characterization of Object

For CS790g ProjectBingdong Li11/9/2009

Page 2: Complex Networks for Representation and Characterization of Object

Outline Of Methodology• Re-introduce Traditional Approaches • Proposed Methods• Issues• Summary• Questions and Comments

Page 3: Complex Networks for Representation and Characterization of Object

Re-introduce Traditional Approaches

• External characteristics:– boundary and shape– chain codes, polygonal approximations, skeletons

• Internal characteristics:– color and texture, – statistical approaches, structural approaches,

spectral approaches• Both external and internal characteristics.

Source: CS674 Image Processing Lecture

Page 4: Complex Networks for Representation and Characterization of Object

Proposed Methods:Representation

• Define the network– a regular lattice network in 2-D background, each

node is connected to its nearest neighbors depending on the Euclidean distance

– Each node is addressed by its normalized degree

Source: CS674 Image Processing Lecture

Page 5: Complex Networks for Representation and Characterization of Object

Proposed Methods:Representation

• Two pixel A and B on the contourA <-->B <==> d(A, B) <= r and d(A, B) >= n

– r is the shape control threshold– n is noise control threshold– d is the normalized distance– k is the average degree

Page 6: Complex Networks for Representation and Characterization of Object

From Raw Image

Page 7: Complex Networks for Representation and Characterization of Object

To Matrices

Page 8: Complex Networks for Representation and Characterization of Object

Proposed Methods:Representation

Page 9: Complex Networks for Representation and Characterization of Object

Proposed Methods:Characterization

• Network similarity algorithm: structural similarities

Mehler, Alexander(2008) 'STRUCTURAL SIMILARITIES OF COMPLEX NETWORKS: A COMPUTATIONAL MODEL BY EXAMPLE OF WIKI GRAPHS',Applied Artificial Intelligence,22:7,619 — 683

Page 10: Complex Networks for Representation and Characterization of Object

Algorithm

1. Raw image2. Segmentation3. Build the complex network4. Classifying the object using network similarity

algorithm

Page 11: Complex Networks for Representation and Characterization of Object

Expected Results

• In most case, it will be a small world network

Page 12: Complex Networks for Representation and Characterization of Object

Expected Results

• A methods for object classification that– Leverage complex network technology– Represent the geometric information– Represent the spatial information– Invariant to rotation– Invariant to translation

Page 13: Complex Networks for Representation and Characterization of Object

Issues

• the photometric information was not represented

• Thresholds

Page 14: Complex Networks for Representation and Characterization of Object

Summary

• In this project, we tried a new approach for representation and characterization of object

• Firstly, traditional approaches and complex network related approaches are reviewed

• Then, proposed a new methods, its definition of network, characterization, and algorithm to classify an object

Page 15: Complex Networks for Representation and Characterization of Object

Questions and Comments

Page 16: Complex Networks for Representation and Characterization of Object

Thanks