An Introduction to Pattern Recognition

Similar documents
2. Basic Task of Pattern Classification

9.913 Pattern Recognition for Vision. Class I - Overview. Instructors: B. Heisele, Y. Ivanov, T. Poggio

Introduction to Pattern Recognition Part II. Selim Aksoy Bilkent University Department of Computer Engineering

PATTERN CLASSIFICATION AND SCENE ANALYSIS

Texture Classification by Combining Local Binary Pattern Features and a Self-Organizing Map

Invariant Recognition of Hand-Drawn Pictograms Using HMMs with a Rotating Feature Extraction

ECG782: Multidimensional Digital Signal Processing

Pattern Recognition. Kjell Elenius. Speech, Music and Hearing KTH. March 29, 2007 Speech recognition

Ensembles. An ensemble is a set of classifiers whose combined results give the final decision. test feature vector

Neural Networks. CE-725: Statistical Pattern Recognition Sharif University of Technology Spring Soleymani

More Learning. Ensembles Bayes Rule Neural Nets K-means Clustering EM Clustering WEKA

Image retrieval based on bag of images

Baseball Game Highlight & Event Detection

EE 6882 Statistical Methods for Video Indexing and Analysis

Practical Image and Video Processing Using MATLAB

Machine Learning Lecture 3

Machine Learning Lecture 3

MACHINE LEARNING: CLUSTERING, AND CLASSIFICATION. Steve Tjoa June 25, 2014

More on Learning. Neural Nets Support Vectors Machines Unsupervised Learning (Clustering) K-Means Expectation-Maximization

Building Multi Script OCR for Brahmi Scripts: Selection of Efficient Features

Object Recognition. Lecture 11, April 21 st, Lexing Xie. EE4830 Digital Image Processing

Contents. Preface to the Second Edition

A Computer Vision System for Graphical Pattern Recognition and Semantic Object Detection

The Automatic Musicologist

Support Vector Machines

Feature Selection. CE-725: Statistical Pattern Recognition Sharif University of Technology Spring Soleymani

Case-Based Reasoning. CS 188: Artificial Intelligence Fall Nearest-Neighbor Classification. Parametric / Non-parametric.

CS 188: Artificial Intelligence Fall 2008

ABSTRACT 1. INTRODUCTION 2. METHODS

Recap: Gaussian (or Normal) Distribution. Recap: Minimizing the Expected Loss. Topics of This Lecture. Recap: Maximum Likelihood Approach

TWO-STEP SEMI-SUPERVISED APPROACH FOR MUSIC STRUCTURAL CLASSIFICATION. Prateek Verma, Yang-Kai Lin, Li-Fan Yu. Stanford University

Classification and Regression using Linear Networks, Multilayer Perceptrons and Radial Basis Functions

Modeling time series with hidden Markov models

Neural Networks (Overview) Prof. Richard Zanibbi

SYDE Winter 2011 Introduction to Pattern Recognition. Clustering

CAP 6412 Advanced Computer Vision

Image Classification. RS Image Classification. Present by: Dr.Weerakaset Suanpaga

Some questions of consensus building using co-association

Bayes Risk. Classifiers for Recognition Reading: Chapter 22 (skip 22.3) Discriminative vs Generative Models. Loss functions in classifiers

Introduction to SLAM Part II. Paul Robertson

1 Introduction. 3 Data Preprocessing. 2 Literature Review

A Robust Hand Gesture Recognition Using Combined Moment Invariants in Hand Shape

Using the Forest to See the Trees: Context-based Object Recognition

Classifiers for Recognition Reading: Chapter 22 (skip 22.3)

Pattern Recognition ( , RIT) Exercise 1 Solution

Latent Variable Models for Structured Prediction and Content-Based Retrieval

Hidden Markov Models. Gabriela Tavares and Juri Minxha Mentor: Taehwan Kim CS159 04/25/2017

INF 4300 Classification III Anne Solberg The agenda today:

Client Dependent GMM-SVM Models for Speaker Verification

WP1: Video Data Analysis

Fundamentals of Digital Image Processing

the number of states must be set in advance, i.e. the structure of the model is not t to the data, but given a priori the algorithm converges to a loc

SD 372 Pattern Recognition

Content-based image and video analysis. Machine learning

Bus Detection and recognition for visually impaired people

CANCER PREDICTION USING PATTERN CLASSIFICATION OF MICROARRAY DATA. By: Sudhir Madhav Rao &Vinod Jayakumar Instructor: Dr.

COSC160: Detection and Classification. Jeremy Bolton, PhD Assistant Teaching Professor

International Journal of Innovative Research in Computer and Communication Engineering

Machine Learning. Unsupervised Learning. Manfred Huber

Textural Features for Image Database Retrieval

Dietrich Paulus Joachim Hornegger. Pattern Recognition of Images and Speech in C++

Machine Learning Classifiers and Boosting

Color Image Segmentation

Machine Learning and Pervasive Computing

Introduction to digital image classification

Several pattern recognition approaches for region-based image analysis

ModelStructureSelection&TrainingAlgorithmsfor an HMMGesture Recognition System

Multimedia Databases. Wolf-Tilo Balke Younès Ghammad Institut für Informationssysteme Technische Universität Braunschweig

Fully Automatic Methodology for Human Action Recognition Incorporating Dynamic Information

A Fast Approximated k Median Algorithm

Classification. Vladimir Curic. Centre for Image Analysis Swedish University of Agricultural Sciences Uppsala University

Conditional Random Fields for Object Recognition

Segmentation, Classification &Tracking of Humans for Smart Airbag Applications

Classification. Vladimir Curic. Centre for Image Analysis Swedish University of Agricultural Sciences Uppsala University

Data Mining Classification: Bayesian Decision Theory

The exam is closed book, closed notes except your one-page (two-sided) cheat sheet.

Machine Learning for. Artem Lind & Aleskandr Tkachenko

Digital Image Processing

Shape Classification and Cell Movement in 3D Matrix Tutorial (Part I)

NOVEL HYBRID GENETIC ALGORITHM WITH HMM BASED IRIS RECOGNITION

CS 534: Computer Vision Texture

CS6716 Pattern Recognition

Adaptive Learning of an Accurate Skin-Color Model

Motion Estimation for Video Coding Standards

CLASSIFICATION OF BOUNDARY AND REGION SHAPES USING HU-MOMENT INVARIANTS

HAND-GESTURE BASED FILM RESTORATION

A Comparison of Sequence-Trained Deep Neural Networks and Recurrent Neural Networks Optical Modeling For Handwriting Recognition

Machine Learning for Music Discovery

Segmentation and Tracking of Partial Planar Templates

Applying Supervised Learning

Image and speech recognition Exercises

Evaluation of Moving Object Tracking Techniques for Video Surveillance Applications

A Visualization Tool to Improve the Performance of a Classifier Based on Hidden Markov Models

DEEP LEARNING REVIEW. Yann LeCun, Yoshua Bengio & Geoffrey Hinton Nature Presented by Divya Chitimalla

In this assignment, we investigated the use of neural networks for supervised classification

Detection and Recognition of Objects in a Real Time

Lecture 11: Clustering Introduction and Projects Machine Learning

Person Authentication from Video of Faces: A Behavioral and Physiological Approach Using Pseudo Hierarchical Hidden Markov Models

Short Survey on Static Hand Gesture Recognition

Image Classification Using Wavelet Coefficients in Low-pass Bands

Transcription:

An Introduction to Pattern Recognition Speaker : Wei lun Chao Advisor : Prof. Jian-jiun Ding DISP Lab Graduate Institute of Communication Engineering 1 Abstract Not a new research field Wide range included Enhancement by some factors: Computer architecture Machine learning Computer vision New way of thinking Improving human s life 2 1

Outline What s included What is pattern recognition Basic structure Different techniques Performance Care Example of applications Related works 3 Content 1. Introduction 2. Basic Structure 3. Classification method I 4. Classification method II 5. Classification method III 6. Feature Generation 7. Feature Selection 8. Outstanding Application 9. Relation between IT and D&E 10. Conclusion 4 2

1. Introduction Pattern recognition is a process that taking in raw data and making an action based on the category of the pattern. What does a pattern means? A pattern is essentially an arrangement, N. Wiener [1] A pattern is the opposite of a chaos, Watanabe To be simplified, the interesting part 5 What can we do after analysis? Classification (Supervised learning) Clustering (Unsupervised learning) Other applications Category A Category B Classification Clustering 6 3

Why we need pattern recognition? Human beings can easily recognize things or objects based on past learning experiences! Then how about computers? 7 2. Basic Structure Two basic factors: Feature & Classifier Feature: Car Boundary Classifier: Mechanisms and methods to define what the pattern is 8 4

System structure The feature should be well-chosen to describe the pattern!! Knowledge: experience, analysis, trial & error The classifier should contain the knowledge of each pattern category and also the criterion or metric to discriminate among patterns classes. Knowledge : direct defined or training 9 Figure of system structure 10 5

Four basic recognition models Template matching Syntactic Statistical Neural Network 11 Another category idea Quantitative description: Using length, measure of area, and texture No relation between each component Structure descriptions: Qualitative factors Strings and trees Order, permutation, or hierarchical relations between each component 12 6

3. Classification method I Look-up table Decision-theoretic methods Distance Correlation Bayesian Classifier Neural network Popular methods nowadays 13 3.1 Bayesian classifier Two pattern classes: x is a pattern vector choose w1 for a specific x if P(w1 x)>p(w2 x) could be written as P(w1)P(x w1)>p(w2)p(x w2) based on the criterion to achieve the minimum overall error 14 7

Bayesian classifier Multiple pattern classes: Risk based: conditional risk c R( x) ( ) p( x) i j1 Minimum overall error based: 0, i j ( i j ), i, j 1,, c 1, i j c i j R( i x) ( i j ) P( j x) 1 P( i x) j1 j 15 Bayesian classifier Decision function: A classifier assigns x to class wi if di(x)>dj(x) for all i j where di(x) are called decision (discriminant) functions Decision Boundary: The decision boundary between wi and wj for i j is that di(x)=dj(x) 16 8

Bayesian classifier The most important point: probability model The widely-used model: Gaussian distribution for x is one-dimensional: p( x) 2 1 1 x 2 exp ~ N(, ) 2 2 for x is multi-dimensional: p( x) 2 μ E[x] 1 d / 2 Σ 1/ 2 1 exp 2 Σ E x μx μ T 1 x μ Σ x μ ~ N( μ, Σ) T 17 3.2 Neural network Without using statistical information Try to imitate how human learn A structure is generated based on perceptrons (hyperplane) 18 9

Neural networks Multi-layer neural network 19 Neural network What we need to define? Set the criterion for finding the best classifier Set the desired output Set the adapting mechanism The learning step: 1. Initialization: Assigning an arbitrary set of weights 2. Iterative step: Backward propagated modification 3. Stopping mechanism: Convergence under a threshold 20 10

Neural network Complexity of Decision Surface Layer 1: line Layer 2: line intersection Layer 3: region intersection 21 Popular methods nowadays Boosting: combining multiple learners Gaussian mixture model (GMM): Support vector machine (SVM): 22 11

4. Classification method II Template matching: There exists some relation between components of a pattern vector Methods: Measures based on correlation Computational consideration and improvement Measures based on optimal path searching techniques Deformable template matching 23 4.1 Measures based on correlation Distance: Normalized correlation: where i, j means the overlap region under translation Challenge: rotation, scaling, translation (RST) 24 12

4.2 Computational consideration and improvement Cross-correlation via its Fourier transform Direct computation: Improvement: via the search window Two-dimensional logarithmic search Hierarchical search Sequential methods 25 4.3 Measures based on optimal path searching techniques Pattern vectors are of different lengths Basic structure: Two-dimensional grid Elements of sequences on axes Each grid means correspondence between respective elements of the two sequences A path: Associated overall cost D: means the distance between respective elements of two strings 26 13

Measures based on optimal path searching techniques Fast algorithm: Bellman s principle the optimal path Necessary settings: Local constraint: Allowable transitions Global constraints: Dynamic programming End point constraints Cost measure: or 27 4.4 Deformable template matching Deformation parameters: Prototype A mechanism to deform the prototype A criterion to define the best match: -deformation parameter -matching energy -deformation energy 28 14

5. Classification method III Context-dependent methods: the class to which a feature vector is assigned depends (a) on its own value (b) on the values of the other feature vectors (c) on the existing relation among the various classes we have to consider more about the mutual information, which resides within the feature vectors Extension of the Bayesian classifier: N observations X: and possible sequence, M classes: 29 Markov chain model First-order and two assumptions are made to simplify the task: We can get the probability terms: 30 15

The Viterbi Algorithm Computational complexity: Direct way: Fast algorithm: Optimal path Cost function of a transition: The overall cost: Take the logarithm: Bellman s principle: 31 Hidden Markov models Indirect observations of training data: Since the labeling has to obey the model structure Two cases: One model for (1) each class or (2) just an event Recognition: Assume we already know all PDF and types of states All path method: Each HMM could be described as: Best path method: Viterbi algorithm 32 16

Training of HMM The most beautiful part of HMM For all path method: Baum-Welch re-estimation For best path method: Viterbi re-estimation Probability term: Discrete observation: Look-up table Continuous observation: Mixture model 33 6. Feature Generation Inability to use the raw data: (1) the raw data is too big to deal with (2) the raw data can t give the classifier the same sense what people feel about the image 34 17

6.1 Regional feature First-order statistical features: mean, variance, skewness, kurtosis Second-order statistical features Co-occurrence matrices 35 Regional feature Local linear transforms for texture extraction Geometric moments: Zernike moments Parametric models: AR model 36 18

6.2 Shape & Size Boundary: Segmentation algorithm -> binarization -> and boundary extraction Invertible transform: Fourier transform Fourier-Mellin transform 37 6.2 Shape & Size Chain Codes: Moment-based features: Geometric moments 38 19

6.3 Audio feature Timbre: MFCC Rhythm: beat Melody: pitch 39 7. Feature Selection The main problem is the curse of dimensionality Reasons to reduce the number of features: Computational complexity: Trade-off between effectiveness & complexity Generalization properties: Related to the ratio of # training patterns to # classifier parameters Performance evaluation stage Basic criterion: Maintain large between-class distance and small within-class variance 40 20

8. Outstanding Application Speech recognition Movement recognition Personal ID Image retrieval by object query Camera & video recorder Remote sensing Monitoring 41 Outstanding Application Retrieval: 42 21

Evaluation method P-R curve: Precision: a/c Recall: a/b a: # true got b: # retrieval c: # ground truth 43 9. Relation between IT and D&E Transmission: Pattern recognition: 44 22

Graph of my idea 45 10. Conclusion Pattern recognition is nearly everywhere in our life, each case relevant to decision, detection, retrieval can be a research topic of pattern recognition. The mathematics of pattern recognition is widely-inclusive, the methods of game theory, random process, decision and detection, or even machine learning. Feature cases: New features Better classifier Theory 46 23

Idea of feature Different features perform well on different application: Ex: Video segmentation, video copy detection, video retrieval all use features from images (frame), while the features they use are different. Create new features 47 Idea of training Basic setting: Decision criterion Adaptation mechanism Initial condition Challenge: Insufficient training data Over-fitting 48 24

Reference [1] R. C. Gonzalez, Object Recognition, in Digital image processing, 3 rd ed. Pearson, August 2008, pp. 861-909. [2] Shyh-Kang Jeng, Pattern recognition - Course Website, 2009. [online] Available: http://cc.ee.ntu.edu.tw/~skjeng/patternrecognition2007.htm. [Accessed Sep. 30, 2009]. [3] D. A. Forsyth, CS 543 Computer Vision," Jan. 2009. [Online]. Available: http://luthuli.cs.uiuc.edu/~daf/courses/cs5432009/index.html. [Accessed: Oct. 21, 2009]. [4] Ke-Jie Liao, Image-based Pattern Recognition Principles, August 2008. [online] Available: http://disp.ee.ntu.edu.tw/research.php. [Accessed Sep. 19, 2009]. [5] E. Alpaydin, Introduction to Machine Learning. The MIT Press, 2004. [6] S. Theodoridis, K. Koutroumbas, Pattern Recognition, 2 nd ed. Academic Press, 2003. [7] A. Yuille, P. Hallinan, and D. Cohen, Feature Extraction from Faces Using Deformable Templates, Int l J. Computer Vision, vol. 8, no. 2, pp. 99-111, 1992. [8] J.S. Boreczky, L.D. Wilcox, A hidden Markov model framework for video segmentation using audio and image features," in Proc. Int. Conf. Acoustics, Speech, and Signal Processing (ICASSP-98), Vol. 6, Seattle, WA, May 1998. [9] Ming-Sui Lee, Digital Image Processing - Course Website, 2009. [online] Available: http://www.csie.ntu.edu.tw/~dip/. [Accessed Oct. 21, 2009]. [10] W. Hsu, Multimedia Analysis and Indexing Course Website, 2009. [online] Available: http://www.csie.ntu.edu.tw/~winston/courses/mm.ana.idx/index.html. [Accessed Oct. 21, 2009]. [11] R. O. Duda, P. E. Hart, and D. G. Stork, Pattern Classification, ed. John Wiley & Sons, 2001. 49 25