Object Recognition Using Genetic Algorithms CS773C Advanced Machine Intelligence Applications Spring 2008: Object Recognition.

Slides:



Advertisements
Similar presentations
Image Registration  Mapping of Evolution. Registration Goals Assume the correspondences are known Find such f() and g() such that the images are best.
Advertisements

Biologically Inspired AI (mostly GAs). Some Examples of Biologically Inspired Computation Neural networks Evolutionary computation (e.g., genetic algorithms)
EvoNet Flying Circus Introduction to Evolutionary Computation Brought to you by (insert your name) The EvoNet Training Committee The EvoNet Flying Circus.
Institute of Intelligent Power Electronics – IPE Page1 Introduction to Basics of Genetic Algorithms Docent Xiao-Zhi Gao Department of Electrical Engineering.
1 Wendy Williams Metaheuristic Algorithms Genetic Algorithms: A Tutorial “Genetic Algorithms are good at taking large, potentially huge search spaces and.
1 Lecture 8: Genetic Algorithms Contents : Miming nature The steps of the algorithm –Coosing parents –Reproduction –Mutation Deeper in GA –Stochastic Universal.
EvoNet Flying Circus Introduction to Evolutionary Computation Brought to you by (insert your name) The EvoNet Training Committee The EvoNet Flying Circus.
COMP305. Part II. Genetic Algorithms. Genetic Algorithms.
1 Genetic Algorithms. CS The Traditional Approach Ask an expert Adapt existing designs Trial and error.
Introduction to Object Recognition CS773C Machine Intelligence Advanced Applications Spring 2008: Object Recognition.
Algebraic Functions of Views for 3D Object Recognition CS773C Advanced Machine Intelligence Applications Spring 2008: Object Recognition.
Genetic Algorithm for Variable Selection
Object Recognition Using Geometric Hashing
Intro to AI Genetic Algorithm Ruth Bergman Fall 2002.
MSU CSE 803 Stockman CV: Matching in 2D Matching 2D images to 2D images; Matching 2D images to 2D maps or 2D models; Matching 2D maps to 2D maps.
Genetic Algorithm Genetic Algorithms (GA) apply an evolutionary approach to inductive learning. GA has been successfully applied to problems that are difficult.
Intro to AI Genetic Algorithm Ruth Bergman Fall 2004.
Genetic Feature Subset Selection for Gender Classification: A Comparison Study Zehang Sun, George Bebis, Xiaojing Yuan, and Sushil Louis Computer Vision.
Genetic Programming. Agenda What is Genetic Programming? Background/History. Why Genetic Programming? How Genetic Principles are Applied. Examples of.
Optimization of thermal processes2007/2008 Optimization of thermal processes Maciej Marek Czestochowa University of Technology Institute of Thermal Machinery.
Genetic Programming.
Genetic Algorithms: A Tutorial
1. Optimization and its necessity. Classes of optimizations problems. Evolutionary optimization. –Historical overview. –How it works?! Several Applications.
Genetic Algorithm.
Genetic Algorithms and Ant Colony Optimisation
Computer Implementation of Genetic Algorithm
Evolutionary Intelligence
© Negnevitsky, Pearson Education, CSC 4510 – Machine Learning Dr. Mary-Angela Papalaskari Department of Computing Sciences Villanova University.
SOFT COMPUTING (Optimization Techniques using GA) Dr. N.Uma Maheswari Professor/CSE PSNA CET.
Intro. ANN & Fuzzy Systems Lecture 36 GENETIC ALGORITHM (1)
Lecture 8: 24/5/1435 Genetic Algorithms Lecturer/ Kawther Abas 363CS – Artificial Intelligence.
Zorica Stanimirović Faculty of Mathematics, University of Belgrade
Genetic Algorithms Michael J. Watts
Genetic algorithms Charles Darwin "A man who dares to waste an hour of life has not discovered the value of life"
More on Heuristics Genetic Algorithms (GA) Terminology Chromosome –candidate solution - {x 1, x 2,...., x n } Gene –variable - x j Allele –numerical.
An Introduction to Genetic Algorithms Lecture 2 November, 2010 Ivan Garibay
Computational Complexity Jang, HaYoung BioIntelligence Lab.
1 “Genetic Algorithms are good at taking large, potentially huge search spaces and navigating them, looking for optimal combinations of things, solutions.
Genetic Algorithms Siddhartha K. Shakya School of Computing. The Robert Gordon University Aberdeen, UK
Derivative Free Optimization G.Anuradha. Contents Genetic Algorithm Simulated Annealing Random search method Downhill simplex method.
Kansas State University Department of Computing and Information Sciences CIS 732: Machine Learning and Pattern Recognition Friday, 16 February 2007 William.
© Negnevitsky, Pearson Education, Lecture 9 Evolutionary Computation: Genetic algorithms Introduction, or can evolution be intelligent? Introduction,
1 Genetic Algorithms and Ant Colony Optimisation.
Genetic Algorithms Przemyslaw Pawluk CSE 6111 Advanced Algorithm Design and Analysis
Genetic Algorithms CSCI-2300 Introduction to Algorithms
Genetic Algorithms Genetic algorithms provide an approach to learning that is based loosely on simulated evolution. Hypotheses are often described by bit.
Probabilistic Algorithms Evolutionary Algorithms Simulated Annealing.
Chapter 12 FUSION OF FUZZY SYSTEM AND GENETIC ALGORITHMS Chi-Yuan Yeh.
EE749 I ntroduction to Artificial I ntelligence Genetic Algorithms The Simple GA.
D Nagesh Kumar, IIScOptimization Methods: M8L5 1 Advanced Topics in Optimization Evolutionary Algorithms for Optimization and Search.
Genetic Algorithms MITM613 (Intelligent Systems).
An Introduction to Genetic Algorithms Lecture 2 November, 2010 Ivan Garibay
Genetic Algorithm Dr. Md. Al-amin Bhuiyan Professor, Dept. of CSE Jahangirnagar University.
Artificial Intelligence By Mr. Ejaz CIIT Sahiwal Evolutionary Computation.
Advanced AI – Session 6 Genetic Algorithm By: H.Nematzadeh.
Genetic Algorithms. Solution Search in Problem Space.
Genetic Algorithms And other approaches for similar applications Optimization Techniques.
Genetic Algorithm. Outline Motivation Genetic algorithms An illustrative example Hypothesis space search.
Advanced AI – Session 7 Genetic Algorithm By: H.Nematzadeh.
Evolutionary Computation: Advanced Algorithms and Operators
Genetic Algorithm in TDR System
Evolutionary Algorithms Jim Whitehead
Genetic Algorithms: A Tutorial
CV: Matching in 2D Matching 2D images to 2D images; Matching 2D images to 2D maps or 2D models; Matching 2D maps to 2D maps MSU CSE 803 Stockman.
Genetic Algorithms CSCI-2300 Introduction to Algorithms
George Bebis and Wenjing Li Computer Vision Laboratory
EE368 Soft Computing Genetic Algorithms.
Searching for solutions: Genetic Algorithms
Artificial Intelligence CIS 342
Traveling Salesman Problem by Genetic Algorithm
Presentation transcript:

Object Recognition Using Genetic Algorithms CS773C Advanced Machine Intelligence Applications Spring 2008: Object Recognition

2D Case Recover the geometric transformation that aligns the model(s) with the scene. (affine transformation)

Image-Space Approaches Identify a set of features from the unknown scene which approximately match a set of features from a model object. Recover the geometric transformation that the model object has undergone. Examples: –Interpretation tree (Grimson & Lozano-Perez, 1987) –Alignment (Huttenlocher and Ullman, 1990) –Geometric hashing (Lamdan et al., 1990)

Transformation-Space Approaches Search the transformation space. Find a transformation which aligns a large number of model features with the scene. Examples: –Hough-transform based methods (Ballard, 1981). –Pose clustering techniques (Cass, 1988)

Why Using GAs for Object Recognition? Genetic algorithms were designed to efficiently search large solution spaces. Both the image and transformation spaces are very large! Image space: M 3 S 3 possible alignments Transformation space: much larger! G. Bebis. S. Louis, Y. Varol, and A. Yfantis, "Genetic Object Recognition Using Combinations of Views", IEEE Transactions on Evolutionary Computation, vol 6, no. 2, pp , April 2002.

Genetic Algorithms (GAs) Review What is a GA? –An optimization technique for searching very large spaces. –Inspired by the biological mechanisms of natural selection and reproduction. What are the main characteristics of a GA? –Global optimization technique. –Uses objective function information, not derivatives. –Searches probabilistically using a population of structures (i.e., candidate solutions using some encoding). selection crossovermutation –Structures are modified at each iteration using selection, crossover, and mutation.

Structure of GA … … … … … … … … … Evaluation and Selection Crossover Mutation Current GenerationNext Genaration

Encoding and Fitness Evaluation Encoding scheme –Transforms solutions in parameter space into finite length strings (chromosomes) over some finite set of symbols. Fitness function –Evaluates the goodness of a solution.

Selection Operator exploitProbabilistically filters out solutions that perform poorly, choosing high performance solutions to exploit. –Chromosomes with high fitness are copied over to the next generation. fitness

Crossover and Mutation Operators explorationGenerate new solutions for exploration. Crossover –Allows information exchange between points. Mutation –Its role is to restore lost genetic material. Mutated bit

Object Recognition Using Gas: Two Approaches Genetic search in the image space (GA-IS) Genetic search in the transformation space (GA-TS) Important issues: –How to encode solutions? –How to modify solutions ? –How to evaluate solutions?

GA-IS: Encoding At least three model-scene point matches are need to compute the affine transformation. Chromosome contains the binary encoded identities of the three pairs of points. –Model points: 19 (5 bits) –Scene points: (6 bits) –Chromosome length: 3 x x 6 = 33 bits

GA-IS: Decoding Some encoded solutions might be invalid –5 bits can encode at most 32 values. –[0, 31] was linearlymapped to [0, 18] –6 bits can encode at most 64 values. –[0, 63] was linearly mapped to [0, 44]

GA-IS: Fitness Evaluation Compute affine transformation. Apply the transformation on all the model points. Compute the back-projection error (BE) between the model and scene. (d j min distance between the j-th model point and the scene)

GA-TS: Encoding Need to estimate the range of values that the parameters of affine transformation can assume.

GA-TS: Encoding (cont’d) Each chromosome contains six fields. Only the range of each coefficient needs to be represented. –e.g., a 11 assumes values in [-0.408, 0.408] –Its range is: (-0.408) = –2 decimal digit accuracy: 82 values must be encoded. –7 bits are needed to encode 82 values. –Chromosome length: 6 x 7 = 42 bits

GA-TS: Decoding Some encoded solutions might be invalid –7 bits can encode at most 128 values. –[0, 127] should be mapped to [0, 81]

GA-TS: Fitness Evaluation Same as before Less expensive to compute in this case …

Experiments Three scenes (S 1, S 2, S 3 ) of increasing complexity. S 2, S 3 are shown below (S 1 was the same as model). 10 trials per scene – tried to find model1 each time

Experiments (cont’d) We searched for the model below in a number of scenes.

GA Parameters Two-point crossover (prcoss: 0.95). Point mutation (pmut: 0.05). Cross generational selection strategy. Fitness scaling (scaling factor: 1.2).

Results – Scene 1 Correct solutions were found in all 10 trials.

Results – Scene 2 Correct solutions were found in all 10 trials.

Results – Scene 3 Correct solution was missed once!

Efficiency: GA-IS

Efficiency: GA-TS

3D case – GA-TS Apply Genetic Search in the space of the AFoVs parameters. We used 2 views per model

Experiments Four scenes (S 1, S 2, S 3,S 4 ) of increasing complexity. S 1 was the same as model 10 trials per scene

Experiments (cont’d) We searched for the model below in a number of scenes.

GA Parameters Two-point crossover (prcoss: 0.95). Point mutation (pmut: 0.05). Cross generational selection strategy. Fitness scaling (scaling factor: 1.2). Population size: 200 Number of generations: 150

Results - Scene 1 Correct solutions were found in all 10 trials.

Results – Scene 2 Correct solutions were found in all 10 trials.

Results – Scene 3 Correct solutions were found in all 10 trials.

Results – Scene 4 Correct solutions were found in all 10 trials.

Efficiency: GA-TS ~ 2 x 10 15

More Challenging Scene GAs can find near-exact matches. Could be used as input to more sophisticated recognition algorithms.