Image Parsing Unifying Segmentation and Detection Z Tu
- Slides: 38
Image Parsing: Unifying Segmentation and Detection Z. Tu, X. Chen, A. L. Yuille and S-C. Hz ICCV 2003 (Marr Prize) & IJCV 2005 Sanketh Shetty
Outline • • Why Image Parsing? Introduction to Concepts in DDMCMC applied to Image Parsing Combining Discriminative and Generative Models for Parsing • Results • Comments
Image Parsing Optimize p(W|I) Image I Parse Structure W
Properties of Parse Structure • Dynamic and reconfigurable – Variable number of nodes and node types • Defined by a Markov Chain – Data Driven Markov Chain Monte Carlo (earlier work in segmentation, grouping and recognition)
Key Concepts • Joint model for Segmentation & Recognition – Combine different modules to obtain cues • Fully generative explanation for Image generation – Uses Generative and Discriminative Models + DDMCMC framework – Concurrent Top-Down & Bottom-Up Parsing
Pattern Classes 62 characters Faces Regions
MCMC: A Quick Tour • Key Concepts: – Markov Chains – Markov Chain Monte Carlo • Metropolis-Hastings [Metropolis 1953, Hastings 1970] • Reversible Jump [Green 1995] – Data Driven Markov Chain Monte Carlo
Markov Chains Notes: Slides by Zhu, Dellaert and Tu at ICCV 2005
Markov Chain Monte Carlo Notes: Slides by Zhu, Dellaert and Tu at ICCV 2005
Metropolis-Hastings Algorithm Notes: Slides by Zhu, Dellaert and Tu at ICCV 2005
Metropolis-Hastings Algorithm Invariant Distribution Proposal Distribution Notes: Slides by Zhu, Dellaert and Tu at ICCV 2005
Reversible Jumps MCMC • Many competing models to explain data – Need to explore this complicated state space Notes: Slides by Zhu, Dellaert and Tu at ICCV 2005
DDMCMC Motivation Unifies Notes: Slides by Zhu, Dellaert and Tu at ICCV 2005
DDMCMC Motivation Generative Model p(I|W)p(W) State Space
DDMCMC Motivation Generative Model p(I|W)p(W) State Space Discriminative Model q( wj | I ) Dramatically reduce search space by focusing sampling to highly probable states.
DDMCMC Framework • Moves: – Node Creation – Node Deletion – Change Node Attributes
Transition Kernel Satisfies detailed balanced equation Full Transition Kernel
Convergence to p(W|I) Monotonically at a geometric rate
Criteria for Designing Transition Kernels
Image Generation Model Regions: Constant Intensity Textures Shading State of parse graph
62 characters Faces 3 Regions
Designed to penalize high model complexity Uniform
Shape Prior Faces 3 Regions
Shape Prior: Text
Intensity Models
Intensity Model: Faces
Discriminative Cues Used • Adaboost Trained – Face Detector – Text Detector • Adaptive Binarization Cues • Edge Cues – Canny at 3 scales • Shape Affinity Cues • Region Affinity Cues
Transition Kernel Design • Remember
Possible Transitions 1. 2. 3. 4. 5. Birth/Death of a Face Node Birth/Death of Text Node Boundary Evolution Split/Merge Region Change node attributes
Face/Text Transitions
Region Transitions
Change Node Attributes
Basic Control Algorithm
Results
Comments • Well motivated but very complicated approach to THE HOLY GRAIL problem in vision – Good global convergence results for inference with very minor dependence on initial W. – Extensible to larger set of primitives and pattern types. • • Many details of the algorithm are missing and it is hard to understand the motivation for choices of values for some parameters Unclear if the p(W|I)’s for configurations with different class compositions are comparable. Derek’s comment on Adaboost false positives and their failure to report their exact improvement No quantitative results/comparison to other algorithms and approaches – It should be possible to design a simple experiment to measure performance on recognition/detection/localization tasks.
Thank You
- Image segmentation in digital image processing
- Image parsing
- Edge detection segmentation
- Unifying concepts of animal structure and function
- Archegoniates
- Five unifying themes of biology
- Concept map about unifying themes about life
- A unifying review of linear gaussian models
- Types of plate boundaries
- 4 unifying themes of biology
- 5 themes of biology
- Unifying theme definition
- Unifying healthcare data
- 5 themes of biology
- Zhiting hu
- Trecvid
- What is canny edge detection in image processing
- Image detection
- Line detection in image processing
- Steps of query processing
- Threshold image matlab
- Oerdigital
- Image segmentation course
- Filteration
- Deep automatic portrait matting
- Segmentation is the process of: *
- Medical image segmentation tutorial
- Functional segmentation
- Regional park indore
- Oliver van kaick
- Image segmentation
- Recursive descent parsing
- Semantic parsing
- Recursive descent parsing
- Top down parsing in nlp
- Ll(1) parser solved example
- Parsing syntax
- Panic mode error recovery in predictive parsing
- Syntax analysis