Lecture 3: Region Based Vision

Slides:



Advertisements
Similar presentations
Applications of one-class classification
Advertisements

Filling Algorithms Pixelwise MRFsChaos Mosaics Patch segments are pasted, overlapping, across the image. Then either: Ambiguities are removed by smoothing.
Active Shape Models Suppose we have a statistical shape model –Trained from sets of examples How do we use it to interpret new images? Use an “Active Shape.
Chapter 3 cont’d. Adjacency, Histograms, & Thresholding.
Change Detection C. Stauffer and W.E.L. Grimson, “Learning patterns of activity using real time tracking,” IEEE Trans. On PAMI, 22(8): , Aug 2000.
Supervised Learning Recap
Image Segmentation Image segmentation (segmentace obrazu) –division or separation of the image into segments (connected regions) of similar properties.
電腦視覺 Computer and Robot Vision I Chapter2: Binary Machine Vision: Thresholding and Segmentation Instructor: Shih-Shinh Huang 1.
Computer Vision Lecture 16: Region Representation
Foreground Modeling The Shape of Things that Came Nathan Jacobs Advisor: Robert Pless Computer Science Washington University in St. Louis.
Segmentation and Region Detection Defining regions in an image.
On Constrained Optimization Approach To Object Segmentation Chia Han, Xun Wang, Feng Gao, Zhigang Peng, Xiaokun Li, Lei He, William Wee Artificial Intelligence.
Instructor: Mircea Nicolescu Lecture 13 CS 485 / 685 Computer Vision.
Lecture 6 Image Segmentation
EE 7730 Image Segmentation.
Thresholding Otsu’s Thresholding Method Threshold Detection Methods Optimal Thresholding Multi-Spectral Thresholding 6.2. Edge-based.
Hierarchical Region-Based Segmentation by Ratio-Contour Jun Wang April 28, 2004 Course Project of CSCE 790.
Motion Detection And Analysis Michael Knowles Tuesday 13 th January 2004.
Region Segmentation. Find sets of pixels, such that All pixels in region i satisfy some constraint of similarity.
Segmentation CSE P 576 Larry Zitnick Many slides courtesy of Steve Seitz.
Lecture 5: Learning models using EM
Announcements  Project proposal is due on 03/11  Three seminars this Friday (EB 3105) Dealing with Indefinite Representations in Pattern Recognition.
Cluster Analysis.  What is Cluster Analysis?  Types of Data in Cluster Analysis  A Categorization of Major Clustering Methods  Partitioning Methods.
Multiple Human Objects Tracking in Crowded Scenes Yao-Te Tsai, Huang-Chia Shih, and Chung-Lin Huang Dept. of EE, NTHU International Conference on Pattern.
Segmentation (Section 10.3 & 10.4) CS474/674 – Prof. Bebis.
Active Appearance Models Suppose we have a statistical appearance model –Trained from sets of examples How do we use it to interpret new images? Use an.
Lecture 4: Edge Based Vision Dr Carole Twining Thursday 18th March 2:00pm – 2:50pm.
CS292 Computational Vision and Language Segmentation and Region Detection.
Review Rong Jin. Comparison of Different Classification Models  The goal of all classifiers Predicating class label y for an input x Estimate p(y|x)
DIGITAL IMAGE PROCESSING Instructors: Dr J. Shanbehzadeh M.Yekke Zare M.Yekke Zare ( J.Shanbehzadeh M.Yekke Zare )
Introduction to machine learning
Tal Mor  Create an automatic system that given an image of a room and a color, will color the room walls  Maintaining the original texture.
Image Segmentation Image segmentation is the operation of partitioning an image into a collection of connected sets of pixels. 1. into regions, which usually.
Introduction to Image Processing Grass Sky Tree ? ? Review.
Computer Vision James Hays, Brown
Digital Image Processing In The Name Of God Digital Image Processing Lecture8: Image Segmentation M. Ghelich Oghli By: M. Ghelich Oghli
CSC321: Neural Networks Lecture 12: Clustering Geoffrey Hinton.
CSE 185 Introduction to Computer Vision Pattern Recognition 2.
Automated Detection and Classification Models SAR Automatic Target Recognition Proposal J.Bell, Y. Petillot.
Line detection Assume there is a binary image, we use F(ά,X)=0 as the parametric equation of a curve with a vector of parameters ά=[α 1, …, α m ] and X=[x.
Digital Image Processing Lecture 18: Segmentation: Thresholding & Region-Based Prof. Charlene Tsai.
Chapter 10 Image Segmentation.
EECS 274 Computer Vision Segmentation by Clustering II.
Image Segmentation and Edge Detection Digital Image Processing Instructor: Dr. Cheng-Chien LiuCheng-Chien Liu Department of Earth Sciences National Cheng.
MACHINE LEARNING 8. Clustering. Motivation Based on E ALPAYDIN 2004 Introduction to Machine Learning © The MIT Press (V1.1) 2  Classification problem:
CS654: Digital Image Analysis Lecture 30: Clustering based Segmentation Slides are adapted from:
CS654: Digital Image Analysis
Levels of Image Data Representation 4.2. Traditional Image Data Structures 4.3. Hierarchical Data Structures Chapter 4 – Data structures for.
Radiometric Normalization Spring 2009 Ben-Gurion University of the Negev.
ECE 8443 – Pattern Recognition ECE 8423 – Adaptive Signal Processing Objectives: Supervised Learning Resources: AG: Conditional Maximum Likelihood DP:
Lecture 2: Statistical learning primer for biologists
October 1, 2013Computer Vision Lecture 9: From Edges to Contours 1 Canny Edge Detector However, usually there will still be noise in the array E[i, j],
Machine Vision ENT 273 Regions and Segmentation in Images Hema C.R. Lecture 4.
Visual Tracking by Cluster Analysis Arthur Pece Department of Computer Science University of Copenhagen
November 5, 2013Computer Vision Lecture 15: Region Detection 1 Basic Steps for Filtering in the Frequency Domain.
Thresholding Foundation:. Thresholding In A: light objects in dark background To extract the objects: –Select a T that separates the objects from the.
May 2003 SUT Color image segmentation – an innovative approach Amin Fazel May 2003 Sharif University of Technology Course Presentation base on a paper.
Unsupervised Classification
Grid-Based Genetic Algorithm Approach to Colour Image Segmentation Marco Gallotta Keri Woods Supervised by Audrey Mbogho.
Machine Vision ENT 273 Lecture 4 Hema C.R.
DIGITAL SIGNAL PROCESSING
Motion Detection And Analysis
Nonparametric Semantic Segmentation
Mean Shift Segmentation
REMOTE SENSING Multispectral Image Classification
Chapter 10 – Image Segmentation
Image Segmentation.
EM Algorithm and its Applications
Presentation transcript:

Lecture 3: Region Based Vision Dr Carole Twining Thursday 18th March 1:00pm – 1:50pm

Segmenting an Image Assigning labels to pixels (cat, ball, floor) Point processing: colour or grayscale values, thresholding Neighbourhood Processing: Regions of similar colours or textures Edge information (next lecture) Prior information: (model-based vision) I know what I expect a cat to look like

Overview Automatic threshold detection Multi-Spectral segmentation Earlier, we did by inspection/guessing Multi-Spectral segmentation satellite and medical image data Split and Merge Hierarchical, region-based approach Relaxation labelling probabilistic, learning approach Segmentation as optimisation

Automatic Threshold Selection

Automatic Thresholding: Optimal Segmentation Rule Image Histogram Assume scene mixture of substances, each with normal/gaussian distribution of possible image values Minimum error in probabilistic terms But sum of gaussians not easy to find Doesn’t always fit actual distribution

Automatic Thresholding: Otsu’s Method Extend to multiple classes T 3 4

Automatic Thresholding: Max Entropy Makes two sub-populations as peaky as possible

Automatic Thresholding: Example cat floor ball combine

Automatic Thresholding: Summary Geometric shape of histogram (bumps, curves etc) Algorithm or just by inspection Statistics of sub-populations Otsu & variance Entropy methods Model-based methods: Mixture of gaussians And so on. > 40 methods surveyed in literature Fundamental limit on effectiveness: Never give great result if distributions overlap Whatever method, need further processing

Multi-Spectral Segmentation

Multi-spectral Segmentation Multiple measurements at each pixel: Satellite remote imaging, various wavebands MR imaging, various imaging sequences Colour (RGB channels, HSB etc) Scattergram of pixels in vector space: Can’t separate using single measurement Can using multiple f2 f1

Multi-Spectral Segmentation:Example Spectral Bands Over-ripe Orange Scratched Orange Multispectral Image Segmentation by Energy Minimization for Fruit Quality Estimation: Martínez-Usó, Pla, and García-Sevilla,  Pattern Recognition and Image Analysis , 2005

Split and Merge

Split and Merge Combine A & B A B C D Obvious approaches to segmentation: Start from small regions and stitch them together Start from large regions and split them Start with large regions , split non-uniform regions e.g. variance 2 > threshold Merge similar adjacent regions e.g. combined variance 2 < threshold Region adjacency graph housekeeping for adjacency as regions become irregular regions are nodes, adjacency relations arcs simple update rules during splitting and merging Combine A & B A B C D

Split and Merge Original Split Merge Split Merge Split

Split and Merge: Example Original Splitting Merge

Relaxation Labelling

Aside: Conditional Probability of A given that B is the case ( + ) ALL P(pet) = etc P( pet | mammal) = P( mammal | pet) = Bayes Theorem: P( pet | mammal )P(mammal) = P( mammal | pet )P(pet) All Animal Species Mammals whale Pets fish dog cat ( + ) ( + ) ( + ) ALL x =

Relaxation Labelling: Image histogram, object/background Overlap: mistakes in labelling Values from object pixels Context: threshold Values from background Context to resolve ambiguity Label assignments

Relaxation Labelling Evidence for a label at a pixel: Measurements at that pixel (e.g., pixel value) Context for that pixel (i.e., what neighbours are doing) Iterative approach, labelling evolves Soft-assignment of labels: Soft-assignment allows you to consider all possibilities Let context act to find stable solution

Relaxation Labelling Compatibility: Contextual support for label  at pixel i : If not neighbours no effect Neighbours & same label support Neighbours & different label oppose look at all other pixels all possible labels & how strong degree of compatibility

Relaxation Labelling: Update soft labelling given context: The more support, more likely the label Iterate Noisy Image Threshold labelling After iterating

 = 0.75  = 0.90 Relaxation Labeling: Value of  alters final result Fields Trees  = 0.90 Initialisation

Segmentation as Optimisation

Segmentation as Optimisation Maximise probability of labelling given image: Re-write by taking logs, minimise cost function: How to find the appropriate form for the two terms. How to find the optimum. label at i given value at i label at i given labels in neighbourhood of i label-data match label consistency

Segmentation as Optimisation Exact form depends on type of data Histogram gives: Model of histogram (e.g., sum of gaussians, relaxation case) label consistency label-data match Learning approach: Explicit training data (i.e., similar labelled images) Unsupervised, from image itself (e.g., histogram model): E-step Expectation/Maximization Image & Labelling Model Parameters Given labels, construct model Given model, update labels Repeat M-step

Segmentation as Optimisation General case: High-dimensional search space, local minima Analogy to statistical mechanics crystalline solid finding minimum energy state stochastic optimisation simulated annealing Search: Downhill Allow slight uphill label-data match term label consistency label values cost

Segmentation as Optimisation  = 0.90 Relaxation Fields Trees Original Optimisation

Split and Merge: Example 1 8x8 split Completed split Merge Remove small regions

Colour Segmentation