2: Image Display and Digital Images. EE547 Computer Vision: Lecture Slides. 2: Digital Images. 1. Introduction: EE547 Computer Vision

Size: px
Start display at page:

Download "2: Image Display and Digital Images. EE547 Computer Vision: Lecture Slides. 2: Digital Images. 1. Introduction: EE547 Computer Vision"

Transcription

1 EE547 Computer Vision: Lecture Slides Anthony P. Reeves November 24, 1998 Lecture 2: Image Display and Digital Images 2: Image Display and Digital Images Image Display: - True Color, Grey, Pseudo Color, Color LUT s Digital Images: - Gray levels, Resolution and Tessellation. Readings: Jain 2:25-60 Lecture 1: Introduction 1. Introduction: EE547 Computer Vision Course Overview Use the www for information ee547 1st half: fundamentals and fixed labs 2nd half: advanced topics and project What is Computer Vision? 1. Applications 2. Capabilites Image Sensors 1. Video camera (vidicon and CCD) 2. Scanners (light or camera) 3. Reconstruction from projections (CT,MR) 4. Range image sensing: (structured light, stereo, active (time-of-flight)) Readings: Jain Chapter 1:1-18, Chapter 2: : Digital Images Quantization (Number of gray levels): 8-12 bits typical Sampling (spatial frequency) Tessellation (Grid Pattern) Tessellation A plane can be tiled with three regular polygons: the triangle, the square and the hexagon. (a) Rectangular - Two types of connectivity: 4-connected and 8-connected - Local Distance problem 4-c = 1, 8-c = - Distance measures 1. Euclidean 2. City Block 3. Chess Board (b) Triangular Tessellation 1. Three types of connectivity 2. Not very useful for planar surfaces. Sometimes used for tessellating the surface of a sphere.

2 2: Digital Images 3: Moments: Size and Location (c) Hexagonal Tessellation 1. Only one type of connectivity 2. Cell indexing is more complicated than for the rectangular case. 3. Does not extend to three dimensions 4. Hexagonal tessellation my be achieved directly from a scanning imaging device. The two-dimensional Cartesian moment,, of order, of a density distribution function,, is defined as The two-dimensional moment for a, is discretized image, A complete moment set of order consists of all moments,, such that and contains elements. Note that the monomial product is the basis function for this moment definition. Size The size of a region is given by : Location The location of a region is given by its center of mass (COM) Lecture 3: Image Geometry and Algorithms 3: Image Geometry and Algorithm Types Image Geometry 1. The Perspective Transform: - How object points map into image points 2. Image Functions: - pixels and voxels. 3. Coordinate Systems: - Jain et. al., VisionX Image Algorithms: - Point, Local, Global, and Object. Binary Image Processing (Introduction) - Binary Image Formation: Thresholding Geometric Properties: Moments - Size, Location, Rotation Readings: Jain 2: : Moments (Rotation) Central Moments If the origin of the coordinate system is at the COM of the region; i.e.. ( ) and ( ), then the moments are referred to as central moments. Central moments are given by: where and. Rotation When the coordinate axis are aligned with principal axis of the region. The angle between the coordinate axis and the principle axis of the region is given by:

3 Lecture 4: Binary Image Processing 4: Binary Image Processing 5: VisionX Parameter Conventions Parameter Passing Conventions Image Algorithms: - Point, Local, Global, and Object. Image Formation: Thresholding Geometric Properties: Moments - Size, Location, Rotation Readings: Jain 2: All parameters have prefixes and are position independent Type Syntax Example option -[letter,name] -q value name = value maximum=100 file names name = fname of=outputfile input file if= fname if=image1 output file of= fname of=image2 output file -o fname -o image2 help -H -H help The -H option is defined for all VisionX commands and prints the commands syntax. 3. The - option is defined for all VisionX commands and prints the commands syntax and additional descriptive information. 4. If parameters are given without a prefix they satisfy value parameters (in the order given by -H). Lecture 5: VisionX and Binary Image Algorithms 5: VisionX and Binary Image Algorithms 5: VisionX Features VisionX commands can be used as UNIX filters The VisionX software package and Lab2 1. Command conventions 2. Data structures 3. Program example Binary Image Algorithms 1. Connected Component Labeling 2. Boundary Extraction Readings: Jain 2:25-60 Some commands are VisionX V3 (the old system) All new programs use VisionX V4 tools. VisionX V3 and VisonX file formats are different -VisionX V4 programs accept the main VisionX V3 formats -VisionX V3 programs accept simple VisionX V4 formats File name extensions can modify the file format Example:,o will make a VisionX V4 program create a VisionX V3 file

4 Lecture 6: Binary Image Algorithms II 6: Binary Image Algorithms II Lecture 7: Regions 7: Regions Connected Component Labeling Geometric Properties: Moments - Size, Location, Rotation Shape Description Medial Axis Transform: (Thinning) Readings: Jain 2:25-60 Local Operations (Convolution review) Local Operations (Binary Images) 1. Expanding, Shrinking 2. Dilation, Erosion 3. Opening (Erosion + Dilation), Closing (Dilation + Erosion) Automatic Threshold Selection 1. Peakiness Detection 2. Iterative Threshold Selection 3. Adaptive Thresholding Region Growing Readings: Jain 3: : Local Operations: (Convolution) 7: Morphological Operations: (Dilation) Convolution:See Jain 4: Dilation: is defined by: is defined by: For a discrete function where - the structuring element is a small binary valued matrix. Dilation may also be expressed by: Image Processing Local Operations Usually and are images - same size Border elements of may not be valid. - the convolution mask is a small matrix. convolution, correlation: Erosion: is defined by: Erosion gives all locations where a structuring element fits within a region.

5 Lecture 8: Segmentation 8: Segmentation Lecture 10: Image Filtering 10: Image Filtering II Morphological Filtering Opening (Erosion + Dilation), Closing (Dilation + Erosion) Region Representation 1. Array, Moments, Medial Axis 2. Quad Trees, Pyramids 3. Region Adjacency graphs, Supergrids (see book) Region Growing 1. Region Growing Criteria 2. Region Growing Order: Split and Merge, Boundary Melting Readings: Jain 3: Readings: Jain 4: Project Introduction The Fourier Transform 5. Sampling (digital images) Reconstruction by interpolation 6. The Discrete Fourier Transform (DFT) 7. Fourier Transforms and Convolution The Fast Fourier Transform (FFT) Practical issues Contrast Enhancement 1. Linear Scaling 2. Log Function 3. Histogram Equalization Readings: Jain 4: Lecture 9; Image Filtering: The Fourier Transform 9: Image Filtering: The Fourier Transform Split and Merge Region Growing Region merging by boundary melting The Fourier Transform 1. Review 2. Fourier Transform Pairs delta, comb, Gaussian, sin, cos, rect, sinc 3. Convolution 4. 2-D DFT Examples Readings: Jain 4: : Fourier Transform: Practical Issues 1. Arithmetic: complex numbers, large dynamic range - use floating point (or scaled fixed point with special hardware). 2. Fourier transform requires a large amount of computation - use the FFT algorithm (data size must be a power of 2) 3. Gibbs effect at the edges of an image (i) double the number of samples (a fix for convolution) (ii) taper the image to zero at the edges (frequency estimation) (ii) Use the discrete cosine transform (DCT) (image compression)

6 10: Image Enhancement vppr himage histeq -lin himage vppr histeq -log himage vppr histeq -lin himage of=himage.lin histeq -log himage.lin vppr histeq -equ himage vppr Lecture 12: Spatial Filtering Contrast Enhancement 1. Linear Scaling 2. Log Function 12: Spatial Filtering 3. Histogram Equalization Spatial Filtering High Pass and Low Pass Filters Linear Filtering (low pass) 1. The Mean filter Computational complexity - Separable - Update algorithm 2. Gaussian Smoothing - smooth in space and frequency - separable and rotationally symmetric Readings: Jain 4: Readings: Jain 5: Lecture 11: Image Filtering 11: Image Filtering Lecture 13: Edge Detection 13: Spatial Filtering and Edge Detection Fourier Transform: Practical Issues 1. Computation Complexity (FFT) 2. Gibbs Effect. Contrast Enhancement 1. Linear Scaling 2. Log Function Readings: Jain 4: Readings: Jain 5: Gaussian Smoothing - smooth in space and frequency - separable and rotationally symmetric High Pass Filtering Background Subtraction (Unsharp masking) Non-linear filtering (Median Filtering) Edge Detection Gradient Operators 1. Roberts Cross 2. Sobel 3. Prewitt Readings: Jain 5: , ,

7 Lecture 14: Edge Detection and Template Matching 14: Edge Detection and Template Matching Lecture 16: Curves and the Hough Transform 16: Curves and the Hough Transform Edge Detection (Lapalcian),Laplacian of the Gaussian Canny Edge Operator Nonmaxima Suppression Thresholding with Hysteresis Readings: Jain 5: , , Curves and Boundary Approximation Circular arc and Spline segments B-Splines (Cubic B-Splines) Cubic Splines B-Splines Reading: Jain 13: The Hough Transform 1. The Straight Line Hough Transform Readings: Jain 6: , , Lecture 15: Template Matching and Contour Representation 15: Template Matching and Contour Representation Lecture 17: The Hough Transform 17: The Hough Transform Template Matching Reading: Jain 15: Correlation 2. Cross Correlation 3. Normalized Correlation Contours Polylines Chain codes Curves 1. curve length 2. normal to a curve point 3. curvature of a curve point Readings: Jain 6: , , The Hough Transform 1. The Straight Line Hough Transform 2. The Parametric Hough Transform 3. The Generalized Hough Transform: Rotation Invariant GHT (RIGHT), R-tables, Reference point Readings: Jain 6: , ,

8 Lecture 18: Fourier Descriptors 18: Fourier Descriptors Lecture 19:Standard Moments and Object Recognition 19: Standard Moments and Object Recognition Fourier Descriptors: 1. Translation 2. Scale 3. Rotation (and starting point) 4. Normalization Readings: Jain 6: Readings: Jain 15: Standard Moments 1. Translation 2. Scale 3. Rotation 4. Reflection and Aspect Ratio 5. Image types: Binary, Grey and Range Object Recognition: An example Readings: Jain 6: Readings: Jain 15: : Global Features 19: Standard Moments 1. Template Matching Preprocessing:(a) none, (b) segment object from background. (c) edge operator Very sensitive to rotation and scale Identification: Threshold(peak detect) correlation image Other parameters: window size, matching criterion 2. Rotation Invariant Generalized Hough transform (RIGHT) Preprocessing: directed edge image Insensitive to rotation, sensitive to scale Occlusion: can handle some missing information Identification: Threshold(peak detect) accumulation image 3. Fourier Descriptors Preprocessing: whole closed contour Invariant to rotation and scale. Occlusion: Cannot handle missing contour information Identification: feature vector classification 4. Standard Moments Preprocessing:(a) none, (b) segment object from background. Invariant to rotation and scale. Occlusion: Cannot handle missing segment information Other features: can be used with grey level images and range images Moment Definition: The two-dimensional Cartesian moment,, of order, of a density distribution function,, is defined as The two-dimensional moment for a, is discretized image, A complete moment set of order consists of all moments,, such that and contains elements. Note that the monomial product is the basis function for this moment definition. Translation: A translation of in the dimension and in the dimension of an image,, results in a new image,, defined by The transformed moment values are expressed in terms of the original moment values of as

9 Scale: Rotation: 19: Standard Moments Lecture 20: Feature Vector Classification 20: Feature Vector Classification Statistical Classification: 1. Bayes Theorem 2. Discriminant Functions 3. Multivariate Gaussian Distributions 4. Linear Discriminant Functions The Nearest Neighbor Classifier Neural Networks Readings: Jain 15: Reflection: 19: Standard Moment Normalization Size: Location:, Rotation:,, Reflection: Aspect Ratio: Lecture 21: Classification and Neural Networks 21: Classification and Neural Networks The Nearest Neighbor Classifier Neural Networks 1. Perceptrons 2. Multi-layer Feed-forward Networks Object Recognition: An example Readings: Jain 15:

10 21: Classification Methods Linear Discriminant Functions Realize hyperplanes in decision space Multivariate Gaussian Distribution Parametric Classifier Gaussian shaped cluster assumption. Realizes hyperquadratic decision functions in hyperspace. In general, a large training set is required to estimate parameters. The Nearest Neighbor Classifier Problem: operation computation increases with size of training set. The K-Nearest Neighbor Classifier More robust version of Nearest Neighbor Classifier. Neural Networks: Perceptrons Implement hyperplanes in hyperspace Neural Networks: Multi-layer Feed-forward Networks Implement arbitrary complex decision surfaces in hyperspace with three layers. Issues: how many neurons in hidden layer, how to efficiently train, how to deal with contradictory training information. Lecture 23: Radiometry and Color 23: Radiometry and Color Radiometry Readings: Jain 9: Irradiance and Radiance 2. Reflectance, Bidirectional Reflectance Distribution Function (BRDF) 3. Surface types: Lambertian, Specular, Combination 4. Shape from Shading: Photometric Stereo Color Readings: Jain 10: Color coding schemes RGB, opponent processes, YIQ, IHS Depth Readings: Jain 11: Lecture 22: 3D Object Recognition Example 22: 3D Object Recognition Example Lecture 24: Depth etc. 24: Depth and Stereo Vision Object Recognition: An example 1. Multiple View Representation for Three-Dimensional Objects 2. Tessellation of the surface of a sphere 3. Feature Vector Conditioning: Variance Balancing, Aspect Ratio Normalization 4. Performance Evaluation 5. Other issues: The use of Range Information Confidence Estimation Multiple Camera Views Radiometry Readings: Jain 9: Color Readings: Jain 10: Depth Readings: Jain 11: Stereo Imaging 1. Perspective Projection Model 2. Stereo Geometry - Depth 3. Homogeneous Coordinates 4. 3D Rotations and Translations 5. Coordinate Systems 6. Disparity Computation Readings: Jain 15:

11 Lecture 25: Reconstruction from Projections 25: Reconstrcution from Projections Reconstruction from Projections 1. The Radon Transform 2. Simple Back Projection 3. The Fourier Transfrom Method 4. Filtered Back Projection Lecture 26: 3D Image Analysis 26: Bits and Pieces Prelim 2: Post Mortem The Final Project Report: Due December 3 The Project Poster: Setup by EARLY December 3 A 3-Dimensional Vision Application: Classifying Pulmonary Nodules from Helical CT Images 1. The Pulmonary Nodule Problem 2. 3D Image Filtering 3. 3D Shape Characterization 4. 3D Shape Classification

Digital Image Processing

Digital Image Processing Digital Image Processing Third Edition Rafael C. Gonzalez University of Tennessee Richard E. Woods MedData Interactive PEARSON Prentice Hall Pearson Education International Contents Preface xv Acknowledgments

More information

CHAPTER 1 Introduction 1. CHAPTER 2 Images, Sampling and Frequency Domain Processing 37

CHAPTER 1 Introduction 1. CHAPTER 2 Images, Sampling and Frequency Domain Processing 37 Extended Contents List Preface... xi About the authors... xvii CHAPTER 1 Introduction 1 1.1 Overview... 1 1.2 Human and Computer Vision... 2 1.3 The Human Vision System... 4 1.3.1 The Eye... 5 1.3.2 The

More information

Feature Extraction and Image Processing, 2 nd Edition. Contents. Preface

Feature Extraction and Image Processing, 2 nd Edition. Contents. Preface , 2 nd Edition Preface ix 1 Introduction 1 1.1 Overview 1 1.2 Human and Computer Vision 1 1.3 The Human Vision System 3 1.3.1 The Eye 4 1.3.2 The Neural System 7 1.3.3 Processing 7 1.4 Computer Vision

More information

Fundamentals of Digital Image Processing

Fundamentals of Digital Image Processing \L\.6 Gw.i Fundamentals of Digital Image Processing A Practical Approach with Examples in Matlab Chris Solomon School of Physical Sciences, University of Kent, Canterbury, UK Toby Breckon School of Engineering,

More information

COMPUTER AND ROBOT VISION

COMPUTER AND ROBOT VISION VOLUME COMPUTER AND ROBOT VISION Robert M. Haralick University of Washington Linda G. Shapiro University of Washington A^ ADDISON-WESLEY PUBLISHING COMPANY Reading, Massachusetts Menlo Park, California

More information

Image Processing, Analysis and Machine Vision

Image Processing, Analysis and Machine Vision Image Processing, Analysis and Machine Vision Milan Sonka PhD University of Iowa Iowa City, USA Vaclav Hlavac PhD Czech Technical University Prague, Czech Republic and Roger Boyle DPhil, MBCS, CEng University

More information

Babu Madhav Institute of Information Technology Years Integrated M.Sc.(IT)(Semester - 7)

Babu Madhav Institute of Information Technology Years Integrated M.Sc.(IT)(Semester - 7) 5 Years Integrated M.Sc.(IT)(Semester - 7) 060010707 Digital Image Processing UNIT 1 Introduction to Image Processing Q: 1 Answer in short. 1. What is digital image? 1. Define pixel or picture element?

More information

Review for the Final

Review for the Final Review for the Final CS 635 Review (Topics Covered) Image Compression Lossless Coding Compression Huffman Interpixel RLE Lossy Quantization Discrete Cosine Transform JPEG CS 635 Review (Topics Covered)

More information

Anno accademico 2006/2007. Davide Migliore

Anno accademico 2006/2007. Davide Migliore Robotica Anno accademico 6/7 Davide Migliore migliore@elet.polimi.it Today What is a feature? Some useful information The world of features: Detectors Edges detection Corners/Points detection Descriptors?!?!?

More information

Topic 6 Representation and Description

Topic 6 Representation and Description Topic 6 Representation and Description Background Segmentation divides the image into regions Each region should be represented and described in a form suitable for further processing/decision-making Representation

More information

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

Dietrich Paulus Joachim Hornegger. Pattern Recognition of Images and Speech in C++ Dietrich Paulus Joachim Hornegger Pattern Recognition of Images and Speech in C++ To Dorothea, Belinda, and Dominik In the text we use the following names which are protected, trademarks owned by a company

More information

DEPARTMENT OF ELECTRONICS AND COMMUNICATION ENGINEERING DS7201 ADVANCED DIGITAL IMAGE PROCESSING II M.E (C.S) QUESTION BANK UNIT I 1. Write the differences between photopic and scotopic vision? 2. What

More information

Image Processing Fundamentals. Nicolas Vazquez Principal Software Engineer National Instruments

Image Processing Fundamentals. Nicolas Vazquez Principal Software Engineer National Instruments Image Processing Fundamentals Nicolas Vazquez Principal Software Engineer National Instruments Agenda Objectives and Motivations Enhancing Images Checking for Presence Locating Parts Measuring Features

More information

EXAM SOLUTIONS. Image Processing and Computer Vision Course 2D1421 Monday, 13 th of March 2006,

EXAM SOLUTIONS. Image Processing and Computer Vision Course 2D1421 Monday, 13 th of March 2006, School of Computer Science and Communication, KTH Danica Kragic EXAM SOLUTIONS Image Processing and Computer Vision Course 2D1421 Monday, 13 th of March 2006, 14.00 19.00 Grade table 0-25 U 26-35 3 36-45

More information

Digital Image Processing COSC 6380/4393

Digital Image Processing COSC 6380/4393 Digital Image Processing COSC 6380/4393 Lecture 21 Nov 16 th, 2017 Pranav Mantini Ack: Shah. M Image Processing Geometric Transformation Point Operations Filtering (spatial, Frequency) Input Restoration/

More information

EE 584 MACHINE VISION

EE 584 MACHINE VISION EE 584 MACHINE VISION Binary Images Analysis Geometrical & Topological Properties Connectedness Binary Algorithms Morphology Binary Images Binary (two-valued; black/white) images gives better efficiency

More information

Digital Image Processing

Digital Image Processing Digital Image Processing Part 9: Representation and Description AASS Learning Systems Lab, Dep. Teknik Room T1209 (Fr, 11-12 o'clock) achim.lilienthal@oru.se Course Book Chapter 11 2011-05-17 Contents

More information

EXAM SOLUTIONS. Computer Vision Course 2D1420 Thursday, 11 th of march 2003,

EXAM SOLUTIONS. Computer Vision Course 2D1420 Thursday, 11 th of march 2003, Numerical Analysis and Computer Science, KTH Danica Kragic EXAM SOLUTIONS Computer Vision Course 2D1420 Thursday, 11 th of march 2003, 8.00 13.00 Exercise 1 (5*2=10 credits) Answer at most 5 of the following

More information

Final Exam Study Guide

Final Exam Study Guide Final Exam Study Guide Exam Window: 28th April, 12:00am EST to 30th April, 11:59pm EST Description As indicated in class the goal of the exam is to encourage you to review the material from the course.

More information

Image Processing: Final Exam November 10, :30 10:30

Image Processing: Final Exam November 10, :30 10:30 Image Processing: Final Exam November 10, 2017-8:30 10:30 Student name: Student number: Put your name and student number on all of the papers you hand in (if you take out the staple). There are always

More information

IT Digital Image ProcessingVII Semester - Question Bank

IT Digital Image ProcessingVII Semester - Question Bank UNIT I DIGITAL IMAGE FUNDAMENTALS PART A Elements of Digital Image processing (DIP) systems 1. What is a pixel? 2. Define Digital Image 3. What are the steps involved in DIP? 4. List the categories of

More information

Chapter 11 Arc Extraction and Segmentation

Chapter 11 Arc Extraction and Segmentation Chapter 11 Arc Extraction and Segmentation 11.1 Introduction edge detection: labels each pixel as edge or no edge additional properties of edge: direction, gradient magnitude, contrast edge grouping: edge

More information

Practical Image and Video Processing Using MATLAB

Practical Image and Video Processing Using MATLAB Practical Image and Video Processing Using MATLAB Chapter 18 Feature extraction and representation What will we learn? What is feature extraction and why is it a critical step in most computer vision and

More information

Three-Dimensional Computer Vision

Three-Dimensional Computer Vision \bshiaki Shirai Three-Dimensional Computer Vision With 313 Figures ' Springer-Verlag Berlin Heidelberg New York London Paris Tokyo Table of Contents 1 Introduction 1 1.1 Three-Dimensional Computer Vision

More information

Chapter 11 Representation & Description

Chapter 11 Representation & Description Chain Codes Chain codes are used to represent a boundary by a connected sequence of straight-line segments of specified length and direction. The direction of each segment is coded by using a numbering

More information

CS4733 Class Notes, Computer Vision

CS4733 Class Notes, Computer Vision CS4733 Class Notes, Computer Vision Sources for online computer vision tutorials and demos - http://www.dai.ed.ac.uk/hipr and Computer Vision resources online - http://www.dai.ed.ac.uk/cvonline Vision

More information

Biometrics Technology: Image Processing & Pattern Recognition (by Dr. Dickson Tong)

Biometrics Technology: Image Processing & Pattern Recognition (by Dr. Dickson Tong) Biometrics Technology: Image Processing & Pattern Recognition (by Dr. Dickson Tong) References: [1] http://homepages.inf.ed.ac.uk/rbf/hipr2/index.htm [2] http://www.cs.wisc.edu/~dyer/cs540/notes/vision.html

More information

Lecture 18 Representation and description I. 2. Boundary descriptors

Lecture 18 Representation and description I. 2. Boundary descriptors Lecture 18 Representation and description I 1. Boundary representation 2. Boundary descriptors What is representation What is representation After segmentation, we obtain binary image with interested regions

More information

Digital Image Processing Fundamentals

Digital Image Processing Fundamentals Ioannis Pitas Digital Image Processing Fundamentals Chapter 7 Shape Description Answers to the Chapter Questions Thessaloniki 1998 Chapter 7: Shape description 7.1 Introduction 1. Why is invariance to

More information

Matching and Recognition in 3D. Based on slides by Tom Funkhouser and Misha Kazhdan

Matching and Recognition in 3D. Based on slides by Tom Funkhouser and Misha Kazhdan Matching and Recognition in 3D Based on slides by Tom Funkhouser and Misha Kazhdan From 2D to 3D: Some Things Easier No occlusion (but sometimes missing data instead) Segmenting objects often simpler From

More information

Using Hierarchical Warp Stereo for Topography. Introduction

Using Hierarchical Warp Stereo for Topography. Introduction Using Hierarchical Warp Stereo for Topography Dr. Daniel Filiberti ECE/OPTI 531 Image Processing Lab for Remote Sensing Introduction Topography from Stereo Given a set of stereoscopic imagery, two perspective

More information

Lecture 8 Object Descriptors

Lecture 8 Object Descriptors Lecture 8 Object Descriptors Azadeh Fakhrzadeh Centre for Image Analysis Swedish University of Agricultural Sciences Uppsala University 2 Reading instructions Chapter 11.1 11.4 in G-W Azadeh Fakhrzadeh

More information

CoE4TN4 Image Processing

CoE4TN4 Image Processing CoE4TN4 Image Processing Chapter 11 Image Representation & Description Image Representation & Description After an image is segmented into regions, the regions are represented and described in a form suitable

More information

EE795: Computer Vision and Intelligent Systems

EE795: Computer Vision and Intelligent Systems EE795: Computer Vision and Intelligent Systems Spring 2012 TTh 17:30-18:45 WRI C225 Lecture 04 130131 http://www.ee.unlv.edu/~b1morris/ecg795/ 2 Outline Review Histogram Equalization Image Filtering Linear

More information

ELEC Dr Reji Mathew Electrical Engineering UNSW

ELEC Dr Reji Mathew Electrical Engineering UNSW ELEC 4622 Dr Reji Mathew Electrical Engineering UNSW Review of Motion Modelling and Estimation Introduction to Motion Modelling & Estimation Forward Motion Backward Motion Block Motion Estimation Motion

More information

Final Review. Image Processing CSE 166 Lecture 18

Final Review. Image Processing CSE 166 Lecture 18 Final Review Image Processing CSE 166 Lecture 18 Topics covered Basis vectors Matrix based transforms Wavelet transform Image compression Image watermarking Morphological image processing Segmentation

More information

Robotics Programming Laboratory

Robotics Programming Laboratory Chair of Software Engineering Robotics Programming Laboratory Bertrand Meyer Jiwon Shin Lecture 8: Robot Perception Perception http://pascallin.ecs.soton.ac.uk/challenges/voc/databases.html#caltech car

More information

Image representation. 1. Introduction

Image representation. 1. Introduction Image representation Introduction Representation schemes Chain codes Polygonal approximations The skeleton of a region Boundary descriptors Some simple descriptors Shape numbers Fourier descriptors Moments

More information

C E N T E R A T H O U S T O N S C H O O L of H E A L T H I N F O R M A T I O N S C I E N C E S. Image Operations II

C E N T E R A T H O U S T O N S C H O O L of H E A L T H I N F O R M A T I O N S C I E N C E S. Image Operations II T H E U N I V E R S I T Y of T E X A S H E A L T H S C I E N C E C E N T E R A T H O U S T O N S C H O O L of H E A L T H I N F O R M A T I O N S C I E N C E S Image Operations II For students of HI 5323

More information

The. Handbook ijthbdition. John C. Russ. North Carolina State University Materials Science and Engineering Department Raleigh, North Carolina

The. Handbook ijthbdition. John C. Russ. North Carolina State University Materials Science and Engineering Department Raleigh, North Carolina The IMAGE PROCESSING Handbook ijthbdition John C. Russ North Carolina State University Materials Science and Engineering Department Raleigh, North Carolina (cp ) Taylor &. Francis \V J Taylor SiFrancis

More information

Edge detection. Convert a 2D image into a set of curves. Extracts salient features of the scene More compact than pixels

Edge detection. Convert a 2D image into a set of curves. Extracts salient features of the scene More compact than pixels Edge Detection Edge detection Convert a 2D image into a set of curves Extracts salient features of the scene More compact than pixels Origin of Edges surface normal discontinuity depth discontinuity surface

More information

Broad field that includes low-level operations as well as complex high-level algorithms

Broad field that includes low-level operations as well as complex high-level algorithms Image processing About Broad field that includes low-level operations as well as complex high-level algorithms Low-level image processing Computer vision Computational photography Several procedures and

More information

Generalized Hough Transform, line fitting

Generalized Hough Transform, line fitting Generalized Hough Transform, line fitting Introduction to Computer Vision CSE 152 Lecture 11-a Announcements Assignment 2: Due today Midterm: Thursday, May 10 in class Non-maximum suppression For every

More information

Lecture 6: Multimedia Information Retrieval Dr. Jian Zhang

Lecture 6: Multimedia Information Retrieval Dr. Jian Zhang Lecture 6: Multimedia Information Retrieval Dr. Jian Zhang NICTA & CSE UNSW COMP9314 Advanced Database S1 2007 jzhang@cse.unsw.edu.au Reference Papers and Resources Papers: Colour spaces-perceptual, historical

More information

Multimedia Computing: Algorithms, Systems, and Applications: Edge Detection

Multimedia Computing: Algorithms, Systems, and Applications: Edge Detection Multimedia Computing: Algorithms, Systems, and Applications: Edge Detection By Dr. Yu Cao Department of Computer Science The University of Massachusetts Lowell Lowell, MA 01854, USA Part of the slides

More information

An Introduc+on to Mathema+cal Image Processing IAS, Park City Mathema2cs Ins2tute, Utah Undergraduate Summer School 2010

An Introduc+on to Mathema+cal Image Processing IAS, Park City Mathema2cs Ins2tute, Utah Undergraduate Summer School 2010 An Introduc+on to Mathema+cal Image Processing IAS, Park City Mathema2cs Ins2tute, Utah Undergraduate Summer School 2010 Luminita Vese Todd WiCman Department of Mathema2cs, UCLA lvese@math.ucla.edu wicman@math.ucla.edu

More information

Other Linear Filters CS 211A

Other Linear Filters CS 211A Other Linear Filters CS 211A Slides from Cornelia Fermüller and Marc Pollefeys Edge detection Convert a 2D image into a set of curves Extracts salient features of the scene More compact than pixels Origin

More information

Types of Edges. Why Edge Detection? Types of Edges. Edge Detection. Gradient. Edge Detection

Types of Edges. Why Edge Detection? Types of Edges. Edge Detection. Gradient. Edge Detection Why Edge Detection? How can an algorithm extract relevant information from an image that is enables the algorithm to recognize objects? The most important information for the interpretation of an image

More information

Application of optimal sampling lattices on CT image reconstruction and segmentation or three dimensional printing

Application of optimal sampling lattices on CT image reconstruction and segmentation or three dimensional printing Application of optimal sampling lattices on CT image reconstruction and segmentation or three dimensional printing XIQIANG ZHENG Division of Health and Natural Sciences, Voorhees College, Denmark, SC 29042

More information

Binary Image Processing. Introduction to Computer Vision CSE 152 Lecture 5

Binary Image Processing. Introduction to Computer Vision CSE 152 Lecture 5 Binary Image Processing CSE 152 Lecture 5 Announcements Homework 2 is due Apr 25, 11:59 PM Reading: Szeliski, Chapter 3 Image processing, Section 3.3 More neighborhood operators Binary System Summary 1.

More information

Machine Vision: Theory, Algorithms, Practicalities

Machine Vision: Theory, Algorithms, Practicalities Machine Vision: Theory, Algorithms, Practicalities 2nd Edition E.R. DAVIES Department of Physics Royal Holloway University of London Egham, Surrey, UK ACADEMIC PRESS San Diego London Boston New York Sydney

More information

MEDICAL IMAGE ANALYSIS

MEDICAL IMAGE ANALYSIS SECOND EDITION MEDICAL IMAGE ANALYSIS ATAM P. DHAWAN g, A B IEEE Engineering in Medicine and Biology Society, Sponsor IEEE Press Series in Biomedical Engineering Metin Akay, Series Editor +IEEE IEEE PRESS

More information

Image processing and features

Image processing and features Image processing and features Gabriele Bleser gabriele.bleser@dfki.de Thanks to Harald Wuest, Folker Wientapper and Marc Pollefeys Introduction Previous lectures: geometry Pose estimation Epipolar geometry

More information

PATTERN CLASSIFICATION AND SCENE ANALYSIS

PATTERN CLASSIFICATION AND SCENE ANALYSIS PATTERN CLASSIFICATION AND SCENE ANALYSIS RICHARD O. DUDA PETER E. HART Stanford Research Institute, Menlo Park, California A WILEY-INTERSCIENCE PUBLICATION JOHN WILEY & SONS New York Chichester Brisbane

More information

Processing 3D Surface Data

Processing 3D Surface Data Processing 3D Surface Data Computer Animation and Visualisation Lecture 12 Institute for Perception, Action & Behaviour School of Informatics 3D Surfaces 1 3D surface data... where from? Iso-surfacing

More information

Image Processing. Bilkent University. CS554 Computer Vision Pinar Duygulu

Image Processing. Bilkent University. CS554 Computer Vision Pinar Duygulu Image Processing CS 554 Computer Vision Pinar Duygulu Bilkent University Today Image Formation Point and Blob Processing Binary Image Processing Readings: Gonzalez & Woods, Ch. 3 Slides are adapted from

More information

COMPUTER AND ROBOT VISION

COMPUTER AND ROBOT VISION VOLUME COMPUTER AND ROBOT VISION Robert M. Haralick University of Washington Linda G. Shapiro University of Washington T V ADDISON-WESLEY PUBLISHING COMPANY Reading, Massachusetts Menlo Park, California

More information

Understanding Variability

Understanding Variability Understanding Variability Why so different? Light and Optics Pinhole camera model Perspective projection Thin lens model Fundamental equation Distortion: spherical & chromatic aberration, radial distortion

More information

Shape Context Matching For Efficient OCR

Shape Context Matching For Efficient OCR Matching For Efficient OCR May 14, 2012 Matching For Efficient OCR Table of contents 1 Motivation Background 2 What is a? Matching s Simliarity Measure 3 Matching s via Pyramid Matching Matching For Efficient

More information

Edges and Lines Readings: Chapter 10: better edge detectors line finding circle finding

Edges and Lines Readings: Chapter 10: better edge detectors line finding circle finding Edges and Lines Readings: Chapter 10: 10.2.3-10.3 better edge detectors line finding circle finding 1 Lines and Arcs Segmentation In some image sets, lines, curves, and circular arcs are more useful than

More information

CS443: Digital Imaging and Multimedia Binary Image Analysis. Spring 2008 Ahmed Elgammal Dept. of Computer Science Rutgers University

CS443: Digital Imaging and Multimedia Binary Image Analysis. Spring 2008 Ahmed Elgammal Dept. of Computer Science Rutgers University CS443: Digital Imaging and Multimedia Binary Image Analysis Spring 2008 Ahmed Elgammal Dept. of Computer Science Rutgers University Outlines A Simple Machine Vision System Image segmentation by thresholding

More information

ECG782: Multidimensional Digital Signal Processing

ECG782: Multidimensional Digital Signal Processing Professor Brendan Morris, SEB 3216, brendan.morris@unlv.edu ECG782: Multidimensional Digital Signal Processing Spring 2014 TTh 14:30-15:45 CBC C313 Lecture 10 Segmentation 14/02/27 http://www.ee.unlv.edu/~b1morris/ecg782/

More information

Edge and local feature detection - 2. Importance of edge detection in computer vision

Edge and local feature detection - 2. Importance of edge detection in computer vision Edge and local feature detection Gradient based edge detection Edge detection by function fitting Second derivative edge detectors Edge linking and the construction of the chain graph Edge and local feature

More information

Lecture 6: Edge Detection

Lecture 6: Edge Detection #1 Lecture 6: Edge Detection Saad J Bedros sbedros@umn.edu Review From Last Lecture Options for Image Representation Introduced the concept of different representation or transformation Fourier Transform

More information

Example 1: Regions. Image Segmentation. Example 3: Lines and Circular Arcs. Example 2: Straight Lines. Region Segmentation: Segmentation Criteria

Example 1: Regions. Image Segmentation. Example 3: Lines and Circular Arcs. Example 2: Straight Lines. Region Segmentation: Segmentation Criteria Image Segmentation Image segmentation is the operation of partitioning an image into a collection of connected sets of pixels. 1. into regions, which usually cover the image Example 1: Regions. into linear

More information

Introduction to Medical Imaging (5XSA0)

Introduction to Medical Imaging (5XSA0) 1 Introduction to Medical Imaging (5XSA0) Visual feature extraction Color and texture analysis Sveta Zinger ( s.zinger@tue.nl ) Introduction (1) Features What are features? Feature a piece of information

More information

Example 2: Straight Lines. Image Segmentation. Example 3: Lines and Circular Arcs. Example 1: Regions

Example 2: Straight Lines. Image Segmentation. Example 3: Lines and Circular Arcs. Example 1: Regions Image Segmentation Image segmentation is the operation of partitioning an image into a collection of connected sets of pixels. 1. into regions, which usually cover the image Example : Straight Lines. into

More information

Chapter 3 Image Registration. Chapter 3 Image Registration

Chapter 3 Image Registration. Chapter 3 Image Registration Chapter 3 Image Registration Distributed Algorithms for Introduction (1) Definition: Image Registration Input: 2 images of the same scene but taken from different perspectives Goal: Identify transformation

More information

Short Survey on Static Hand Gesture Recognition

Short Survey on Static Hand Gesture Recognition Short Survey on Static Hand Gesture Recognition Huu-Hung Huynh University of Science and Technology The University of Danang, Vietnam Duc-Hoang Vo University of Science and Technology The University of

More information

Processing 3D Surface Data

Processing 3D Surface Data Processing 3D Surface Data Computer Animation and Visualisation Lecture 17 Institute for Perception, Action & Behaviour School of Informatics 3D Surfaces 1 3D surface data... where from? Iso-surfacing

More information

Edge detection. Gradient-based edge operators

Edge detection. Gradient-based edge operators Edge detection Gradient-based edge operators Prewitt Sobel Roberts Laplacian zero-crossings Canny edge detector Hough transform for detection of straight lines Circle Hough Transform Digital Image Processing:

More information

SECTION 5 IMAGE PROCESSING 2

SECTION 5 IMAGE PROCESSING 2 SECTION 5 IMAGE PROCESSING 2 5.1 Resampling 3 5.1.1 Image Interpolation Comparison 3 5.2 Convolution 3 5.3 Smoothing Filters 3 5.3.1 Mean Filter 3 5.3.2 Median Filter 4 5.3.3 Pseudomedian Filter 6 5.3.4

More information

Computer Vision 2. SS 18 Dr. Benjamin Guthier Professur für Bildverarbeitung. Computer Vision 2 Dr. Benjamin Guthier

Computer Vision 2. SS 18 Dr. Benjamin Guthier Professur für Bildverarbeitung. Computer Vision 2 Dr. Benjamin Guthier Computer Vision 2 SS 18 Dr. Benjamin Guthier Professur für Bildverarbeitung Computer Vision 2 Dr. Benjamin Guthier 1. IMAGE PROCESSING Computer Vision 2 Dr. Benjamin Guthier Content of this Chapter Non-linear

More information

Introduction to Computer Vision. Human Eye Sampling

Introduction to Computer Vision. Human Eye Sampling Human Eye Sampling Sampling Rough Idea: Ideal Case 23 "Digitized Image" "Continuous Image" Dirac Delta Function 2D "Comb" δ(x,y) = 0 for x = 0, y= 0 s δ(x,y) dx dy = 1 f(x,y)δ(x-a,y-b) dx dy = f(a,b) δ(x-ns,y-ns)

More information

Graphics and Interaction Rendering pipeline & object modelling

Graphics and Interaction Rendering pipeline & object modelling 433-324 Graphics and Interaction Rendering pipeline & object modelling Department of Computer Science and Software Engineering The Lecture outline Introduction to Modelling Polygonal geometry The rendering

More information

Segmentation and Grouping

Segmentation and Grouping Segmentation and Grouping How and what do we see? Fundamental Problems ' Focus of attention, or grouping ' What subsets of pixels do we consider as possible objects? ' All connected subsets? ' Representation

More information

HOUGH TRANSFORM CS 6350 C V

HOUGH TRANSFORM CS 6350 C V HOUGH TRANSFORM CS 6350 C V HOUGH TRANSFORM The problem: Given a set of points in 2-D, find if a sub-set of these points, fall on a LINE. Hough Transform One powerful global method for detecting edges

More information

Image Analysis Lecture Segmentation. Idar Dyrdal

Image Analysis Lecture Segmentation. Idar Dyrdal Image Analysis Lecture 9.1 - Segmentation Idar Dyrdal Segmentation Image segmentation is the process of partitioning a digital image into multiple parts The goal is to divide the image into meaningful

More information

Introduction. Introduction. Related Research. SIFT method. SIFT method. Distinctive Image Features from Scale-Invariant. Scale.

Introduction. Introduction. Related Research. SIFT method. SIFT method. Distinctive Image Features from Scale-Invariant. Scale. Distinctive Image Features from Scale-Invariant Keypoints David G. Lowe presented by, Sudheendra Invariance Intensity Scale Rotation Affine View point Introduction Introduction SIFT (Scale Invariant Feature

More information

M. Sc. (Artificial Intelligence and Machine Learning)

M. Sc. (Artificial Intelligence and Machine Learning) Course Name: Advanced Python Course Code: MSCAI 122 This course will introduce students to advanced python implementations and the latest Machine Learning and Deep learning libraries, Scikit-Learn and

More information

Advanced Video Content Analysis and Video Compression (5LSH0), Module 4

Advanced Video Content Analysis and Video Compression (5LSH0), Module 4 Advanced Video Content Analysis and Video Compression (5LSH0), Module 4 Visual feature extraction Part I: Color and texture analysis Sveta Zinger Video Coding and Architectures Research group, TU/e ( s.zinger@tue.nl

More information

Feature descriptors. Alain Pagani Prof. Didier Stricker. Computer Vision: Object and People Tracking

Feature descriptors. Alain Pagani Prof. Didier Stricker. Computer Vision: Object and People Tracking Feature descriptors Alain Pagani Prof. Didier Stricker Computer Vision: Object and People Tracking 1 Overview Previous lectures: Feature extraction Today: Gradiant/edge Points (Kanade-Tomasi + Harris)

More information

Computer Vision I - Image Matching and Image Formation

Computer Vision I - Image Matching and Image Formation Computer Vision I - Image Matching and Image Formation Carsten Rother 10/12/2014 Computer Vision I: Image Formation Process Computer Vision I: Image Formation Process 10/12/2014 2 Roadmap for next five

More information

Edges and Lines Readings: Chapter 10: better edge detectors line finding circle finding

Edges and Lines Readings: Chapter 10: better edge detectors line finding circle finding Edges and Lines Readings: Chapter 10: 10.2.3-10.3 better edge detectors line finding circle finding 1 Lines and Arcs Segmentation In some image sets, lines, curves, and circular arcs are more useful than

More information

Image Segmentation. Ross Whitaker SCI Institute, School of Computing University of Utah

Image Segmentation. Ross Whitaker SCI Institute, School of Computing University of Utah Image Segmentation Ross Whitaker SCI Institute, School of Computing University of Utah What is Segmentation? Partitioning images/volumes into meaningful pieces Partitioning problem Labels Isolating a specific

More information

Contents I IMAGE FORMATION 1

Contents I IMAGE FORMATION 1 Contents I IMAGE FORMATION 1 1 Geometric Camera Models 3 1.1 Image Formation............................. 4 1.1.1 Pinhole Perspective....................... 4 1.1.2 Weak Perspective.........................

More information

Lecture 7: Most Common Edge Detectors

Lecture 7: Most Common Edge Detectors #1 Lecture 7: Most Common Edge Detectors Saad Bedros sbedros@umn.edu Edge Detection Goal: Identify sudden changes (discontinuities) in an image Intuitively, most semantic and shape information from the

More information

Boundary descriptors. Representation REPRESENTATION & DESCRIPTION. Descriptors. Moore boundary tracking

Boundary descriptors. Representation REPRESENTATION & DESCRIPTION. Descriptors. Moore boundary tracking Representation REPRESENTATION & DESCRIPTION After image segmentation the resulting collection of regions is usually represented and described in a form suitable for higher level processing. Most important

More information

All good things must...

All good things must... Lecture 17 Final Review All good things must... UW CSE vision faculty Course Grading Programming Projects (80%) Image scissors (20%) -DONE! Panoramas (20%) - DONE! Content-based image retrieval (20%) -

More information

Lecture 14 Shape. ch. 9, sec. 1-8, of Machine Vision by Wesley E. Snyder & Hairong Qi. Spring (CMU RI) : BioE 2630 (Pitt)

Lecture 14 Shape. ch. 9, sec. 1-8, of Machine Vision by Wesley E. Snyder & Hairong Qi. Spring (CMU RI) : BioE 2630 (Pitt) Lecture 14 Shape ch. 9, sec. 1-8, 12-14 of Machine Vision by Wesley E. Snyder & Hairong Qi Spring 2018 16-725 (CMU RI) : BioE 2630 (Pitt) Dr. John Galeotti The content of these slides by John Galeotti,

More information

coding of various parts showing different features, the possibility of rotation or of hiding covering parts of the object's surface to gain an insight

coding of various parts showing different features, the possibility of rotation or of hiding covering parts of the object's surface to gain an insight Three-Dimensional Object Reconstruction from Layered Spatial Data Michael Dangl and Robert Sablatnig Vienna University of Technology, Institute of Computer Aided Automation, Pattern Recognition and Image

More information

Albert M. Vossepoel. Center for Image Processing

Albert M. Vossepoel.   Center for Image Processing Albert M. Vossepoel www.ph.tn.tudelft.nl/~albert scene image formation sensor pre-processing image enhancement image restoration texture filtering segmentation user analysis classification CBP course:

More information

Local Features: Detection, Description & Matching

Local Features: Detection, Description & Matching Local Features: Detection, Description & Matching Lecture 08 Computer Vision Material Citations Dr George Stockman Professor Emeritus, Michigan State University Dr David Lowe Professor, University of British

More information

Region-based Segmentation

Region-based Segmentation Region-based Segmentation Image Segmentation Group similar components (such as, pixels in an image, image frames in a video) to obtain a compact representation. Applications: Finding tumors, veins, etc.

More information

Digital Image Processing Chapter 11: Image Description and Representation

Digital Image Processing Chapter 11: Image Description and Representation Digital Image Processing Chapter 11: Image Description and Representation Image Representation and Description? Objective: To represent and describe information embedded in an image in other forms that

More information

Operators-Based on Second Derivative double derivative Laplacian operator Laplacian Operator Laplacian Of Gaussian (LOG) Operator LOG

Operators-Based on Second Derivative double derivative Laplacian operator Laplacian Operator Laplacian Of Gaussian (LOG) Operator LOG Operators-Based on Second Derivative The principle of edge detection based on double derivative is to detect only those points as edge points which possess local maxima in the gradient values. Laplacian

More information

Perception. Autonomous Mobile Robots. Sensors Vision Uncertainties, Line extraction from laser scans. Autonomous Systems Lab. Zürich.

Perception. Autonomous Mobile Robots. Sensors Vision Uncertainties, Line extraction from laser scans. Autonomous Systems Lab. Zürich. Autonomous Mobile Robots Localization "Position" Global Map Cognition Environment Model Local Map Path Perception Real World Environment Motion Control Perception Sensors Vision Uncertainties, Line extraction

More information

A Visual Programming Environment for Machine Vision Engineers. Paul F Whelan

A Visual Programming Environment for Machine Vision Engineers. Paul F Whelan A Visual Programming Environment for Machine Vision Engineers Paul F Whelan Vision Systems Group School of Electronic Engineering, Dublin City University, Dublin 9, Ireland. Ph: +353 1 700 5489 Fax: +353

More information

Algorithms for Recognition of Low Quality Iris Images. Li Peng Xie University of Ottawa

Algorithms for Recognition of Low Quality Iris Images. Li Peng Xie University of Ottawa Algorithms for Recognition of Low Quality Iris Images Li Peng Xie University of Ottawa Overview Iris Recognition Eyelash detection Accurate circular localization Covariance feature with LDA Fourier magnitude

More information

Topics to be Covered in the Rest of the Semester. CSci 4968 and 6270 Computational Vision Lecture 15 Overview of Remainder of the Semester

Topics to be Covered in the Rest of the Semester. CSci 4968 and 6270 Computational Vision Lecture 15 Overview of Remainder of the Semester Topics to be Covered in the Rest of the Semester CSci 4968 and 6270 Computational Vision Lecture 15 Overview of Remainder of the Semester Charles Stewart Department of Computer Science Rensselaer Polytechnic

More information