Digital Image Processing

Size: px
Start display at page:

Download "Digital Image Processing"

Transcription

1 Digital Image Processing Part 9: Representation and Description AASS Learning Systems Lab, Dep. Teknik Room T1209 (Fr, o'clock) Course Book Chapter

2 Contents 1. Representation and Description 2. Boundary Representation 3. Boundary Descriptors 4. Regional Descriptors 5. Texture Descriptors 6. Global Appearance Descriptors

3 Contents Representation and Description

4 1 Representation and Description Goal description of image information suitable to use for classification, recognition and interpretation decrease the amount of data with as little loss of information as possible Representation Schemes boundary or region-based? external or internal reconstruction? stable under scaling, rotation, and translation? recognition by incomplete or noisy representation?

5 1 Representation and Description Representation and Description based on region boundaries (external characteristics) chain codes, polygonal approximation, signature, Fourier descriptors,... based on regions (internal characteristics) area, P2A, topology, moments, colour distribution,... Descriptors should be discriminative should be stable under variations such as scaling, translation, image plane rotation, out of plane rotation, noise, occlusion, illumination

6 Contents Boundary Representation

7 2 Boundary Representation Representation compact form of the input data that is (more) useful to compute descriptors

8 2 Boundary Representation Chain Codes (Freeman Chain Code) direction of each segment is coded direct application leads to long chain codes that are sensitive to noise to avoid these problems re-sampling using a larger grid spacing is often applied first 4-connected grid 8-connected grid

9 2 Boundary Representation Freeman Chain Code 4-connected grid 8-connected grid

10 2 Boundary Representation Chain Code Issues long chain code + sensitive to noise sub-sample using a coarser grid

11 2 Boundary Representation Chain Code Issues long chain code + sensitive to noise sub-sample using a coarser grid value depends on the starting point treat chain code as circular sequence of direction numbers select cyclic permutation that forms the minimum number not rotation invariant consider the first difference of the chain code (count number of direction changes between consecutive elements of the code) instead of the code itself invariant to 90 /45 rotations

12 2 Boundary Representation Chain Code Issues long chain code + sensitive to noise sub-sample using a coarser grid value depends on the starting point treat chain code as circular sequence of direction numbers select cyclic permutation that forms the minimum number not rotation invariant consider the first difference of the chain code (count number of direction changes between consecutive elements of the code) (counter-clockwise rotation)

13 2 Boundary Representation Chain Code Issues long chain code + sensitive to noise sub-sample using a coarser grid value depends on the starting point treat chain code as circular sequence of direction numbers select cyclic permutation that forms the minimum number not rotation invariant consider the first difference of the chain code normalization to arbitrary rotations align to some dominant feature first

14 2 Boundary Representation Chain Code Issues long chain code + sensitive to noise sub-sample using a coarser grid value depends on the starting point treat chain code as circular sequence of direction numbers select cyclic permutation that forms the minimum number not rotation invariant consider the first difference of the chain code normalization to arbitrary rotations align to some dominant feature first depends on the size of the boundary compensate by altering the size of the re-sampling grid

15 2 Boundary Representation Signatures 2D boundary 1D function distance from centroid as function of angle

16 2 Boundary Representation Signatures (Distance versus Angle) 2D boundary 1D function distance from centroid as function of angle not applicable to all shapes

17 2 Boundary Representation Signatures (Distance versus Angle) 2D boundary 1D function distance from centroid as function of angle invariant to translation not invariant to rotation and scale select a distinct starting point point farthest from the centroid point on the major eigen axis that is farthest from the centroid rescale signature min/max rescaling to values [0,1] (sensitive to noise) divide by the variance of the signature

18 2 Boundary Representation Signatures (Distance versus Angle) 2D boundary 1D function distance from centroid as function of angle invariant to translation not invariant to rotation and scale alternative: angle between the tangent in each point and a reference line histogram slope density function

19 2 Boundary Representation Polygonal Approximations minimum perimeter polygons enclose the boundary by a set of concatenated cells think of the boundary as a rubber band which is allowed to shrink minimum perimeter polygon see GW

20 Contents Boundary Descriptors

21 3 Boundary Descriptors Simple Boundary Descriptors length diameter length of the major axis (connecting the extreme boundary points) basic rectangle major axis x minor axis minor axis perpendicular to the major axis length so that the basic rectangle (= box passing through the intersections of the major and minor axis with the boundary) completely encloses the boundary eccentricity = major axis / minor axis diam ( B) = max i, j [ D( p, p )] i j

22 3 Boundary Descriptors Simple Boundary Descriptors length diameter length of the major axis basic rectangle major axis x minor axis eccentricity = major axis / minor axis Shape Number diam ( B) = max [ D( p, p )] cyclic permutation of the first difference of the chain code that forms the minimum number i, j i j

23 3 Boundary Descriptors Fourier Descriptors represent the boundary as a sequence of coordinates identify the x-axis as the real axis and the y-axis as the imaginary axis sequence of complex vectors calculate discrete Fourier transform (DFT)

24 3 Boundary Descriptors Fourier Descriptors represent the boundary as a sequence of coordinates identify the x-axis as the real axis and the y-axis as the imaginary axis sequence of complex vectors calculate discrete Fourier transform (DFT) boundary can be re-constructed using the inverse DFT approximate reconstruction if only the first P coefficents are used

25 3 Boundary Descriptors Fourier Descriptors

26 Contents Regional Descriptors

27 4 Regional Descriptors Simple Region Descriptors area number of pixels blue = 10 green = 4

28 4 Regional Descriptors Simple Region Descriptors area (number of pixels) P 2 / A (compactness of a region) perimeter = length of boundary unit-less insensitive to uniform scale changes rotation invariant minimal for disc compact not compact

29 4 Regional Descriptors Simple Region Descriptors area (number of pixels) P 2 / A (compactness of a region) unit-less rotation invariant area = 3591, perimeter = 221 P 2 /A=13.60, P 2 /A norm =1.08 minimal for disc normalization P 2 /A norm = (circularity ratio) 2 P 4πA area = 10538, perimeter = 798 P 2 /A=60.43, P 2 /A norm =4.81

30 4 Regional Descriptors Simple Region Descriptors area (number of pixels) P 2 / A (compactness of a region) unit-less rotation invariant minimal for disc normalization P 2 /A norm = 2 P 4πA perfect circle P 2 /A norm = 1 square (side length: a) P 2 /A norm = (4a) 2 / (4πa 2 ) = 4/π 1.27

31 4 Regional Descriptors Simple Region Descriptors area (number of pixels) P 2 / A (compactness of a region) unit-less minimal for disc rotation invariant normalization P 2 / A norm = 2 P 4πA eccentricity = major axis / minor axis longest chord / max perpendicular chord

32 4 Regional Descriptors Simple Region Descriptors area (number of pixels) P 2 / A (compactness) unit-less minimal for disc rotation invariant normalization P 2 / A norm = 2 P 4πA eccentricity = major axis / minor axis longest chord / max perpendicular chord rectangularity area of region / area of bounding rectangle

33 4 Regional Descriptors Topological Descriptors invariant under "rubber sheet" transformations number of connected components C

34 4 Regional Descriptors Topological Descriptors invariant under "rubber sheet" transformations number of connected components C number of holes H

35 4 Regional Descriptors Topological Descriptors invariant under "rubber sheet" transformations number of connected components C number of holes H Euler number E E = C H

36 4 Regional Descriptors Euler Number? Achim Digital Image J. Lilienthal Processing

37 Contents Texture Descriptors

38 5 Texture Descriptors Texture Descriptors no formal definition of texture exists intuitively: measure of smoothness, coarseness, regularity,...

39 5 Texture Descriptors Statistical Descriptors statistical moments of the grey-level histogram z: random variable for intensity p(z): corresponding histogram L: number of distinct intensity levels compute n th moments m: mean intensity µ L 1 n ( z) ( z m) p( z ) = n i i i= 0 L 1 i= 0 ( ) m= zp i z i

40 5 Texture Descriptors Statistical Descriptors statistical moments of the grey-level histogram z: random variable for intensity p(z): corresponding histogram L: number of distinct intensity levels compute n th moments m: mean intensity µ 0 = 1, µ 1 = 0 µ 2 = σ 2 (z) (variance) µ 3 (measure of skewness) µ 4 (measure of relative flatness),... µ L 1 n ( z) ( z m) p( z ) = n i i i= 0 L 1 i= 0 ( ) m= zp i z i

41 5 Texture Descriptors Statistical Descriptors σ : measure of average contrast

42 5 Texture Descriptors Statistical Descriptors relative smoothness R = σ ( z) 0 for areas of constant intensity 1 for large values of σ 2 1

43 5 Texture Descriptors Statistical Descriptors relative smoothness 0 for areas of constant intensity measure of uniformity lowest if uniform highest if p(z i ) = 1 and p(z j ) = 0 for j i 1 1+σ R = 1 2 ( z) L 1 2 U( z) = p zi i= 0 ( )

44 5 Texture Descriptors Statistical Descriptors relative smoothness 0 for areas of constant intensity measure of uniformity lowest if uniform average entropy measure of variablility / randomness 0 for p(z i ) = 1 and p(z j ) = 0 for j i positiv otherwise (max. for uniform distribution) L 1 i= σ R = 1 2 ( z) L 1 2 U( z) = p zi i= 0 ( ) ( ) ( ) e( z) p z log p z = i 2 i

45 5 Texture Descriptors Statistical Descriptors

46 5 Texture Descriptors Statistical Descriptors co-occurrence matrix consider also relative positions of pixels for statistical description define position operator P for example: "one pixel to the right and one pixel below" count co-occurring intensity levels i and j in matrix g ij image

47 5 Texture Descriptors Statistical Descriptors co-occurrence matrix consider also relative positions of pixels for statistical description define position operator P for example: "one pixel to the right and one pixel below" count co-occurring intensity levels i and j in matrix g ij image

48 5 Texture Descriptors Statistical Descriptors co-occurrence matrix consider also relative positions of pixels for statistical description define position operator P for example: "one pixel to the right and one pixel below" count co-occurring intensity levels i and j in matrix g ij image

49 5 Texture Descriptors Statistical Descriptors co-occurrence matrix consider also relative positions of pixels for statistical description define position operator P for example: "one pixel to the right and one pixel below" count co-occurring intensity levels i and j in matrix g ij image

50 5 Texture Descriptors Statistical Descriptors co-occurrence matrix consider also relative positions of pixels for statistical description define position operator P for example: "one pixel to the right and one pixel below" count co-occurring intensity levels i and j in matrix g ij image

51 5 Texture Descriptors Statistical Descriptors co-occurrence matrix consider also relative positions of pixels for statistical description define position operator P for example: "one pixel to the right and one pixel below" count co-occurring intensity levels i and j in matrix g ij image

52 5 Texture Descriptors Statistical Descriptors co-occurrence matrix consider also relative positions of pixels for statistical description define position operator P for example: "one pixel to the right and one pixel below" count co-occurring intensity levels i and j in matrix g ij normalize co-occurrence numbers g ij p ij consider statistical measures over p ij max (p ij ) correlation (how strong are values correlated given P) contrast (measure of contrast given P)...

53 Contents Global Appearance Descriptors

54 6 Global Descriptors Global Descriptors objects / scenes represented by a set of views no 3D model needed! Swain/Ballard 1991

55 6 Global Descriptors Global Descriptors objects / scenes represented by a set of views each view represented by a descriptor =

56 6 Global Descriptors Global Descriptors variations translation scale image plane rotations out of plane rotation noise occlusion illumination

57 6 Global Descriptors Global Descriptors variations translation scale image plane rotations out of plane rotation noise occlusion illumination

58 6 Global Descriptors Global Descriptors variations translation scale image plane rotations out of plane rotation noise occlusion illumination some modes of variation built in the descriptor

59 6 Global Descriptors Global Descriptors variations translation scale image plane rotations out of plane rotation noise occlusion illumination some modes of variation built in the descriptor some modes incorporated in the training data

60 6 Global Descriptors Greylevel/Color Histograms no spatial information largely invariant to translation scale image plane rotations out of plane rotation noise occlusion illumination

61 6 Global Descriptors Color Histograms, RGB Swain/Ballard 1991

62 6 Global Descriptors Color Histograms, RGB rg normalize to intensity I = R + G + B "chromatic representation" less affected by illumination changes only two parameters (r + g + b = 1)

63 6 Global Descriptors Color Histograms, Build Object Database store descriptors and their labels Swain/Ballard 1991

64 6 Global Descriptors Color Histograms, Recognize Objects store descriptors and their labels query unknown object compute descriptor compare to database descriptors etc. Swain/Ballard 1991

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

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

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

- Low-level image processing Image enhancement, restoration, transformation

- Low-level image processing Image enhancement, restoration, transformation () Representation and Description - Low-level image processing enhancement, restoration, transformation Enhancement Enhanced Restoration/ Transformation Restored/ Transformed - Mid-level image processing

More information

9 length of contour = no. of horizontal and vertical components + ( 2 no. of diagonal components) diameter of boundary B

9 length of contour = no. of horizontal and vertical components + ( 2 no. of diagonal components) diameter of boundary B 8. Boundary Descriptor 8.. Some Simple Descriptors length of contour : simplest descriptor - chain-coded curve 9 length of contour no. of horiontal and vertical components ( no. of diagonal components

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

Chapter 11 Representation & Description

Chapter 11 Representation & Description Chapter 11 Representation & Description The results of segmentation is a set of regions. Regions have then to be represented and described. Two main ways of representing a region: - external characteristics

More information

Machine vision. Summary # 6: Shape descriptors

Machine vision. Summary # 6: Shape descriptors Machine vision Summary # : Shape descriptors SHAPE DESCRIPTORS Objects in an image are a collection of pixels. In order to describe an object or distinguish between objects, we need to understand the properties

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

Lecture 10: Image Descriptors and Representation

Lecture 10: Image Descriptors and Representation I2200: Digital Image processing Lecture 10: Image Descriptors and Representation Prof. YingLi Tian Nov. 15, 2017 Department of Electrical Engineering The City College of New York The City University of

More information

Ulrik Söderström 21 Feb Representation and description

Ulrik Söderström 21 Feb Representation and description Ulrik Söderström ulrik.soderstrom@tfe.umu.se 2 Feb 207 Representation and description Representation and description Representation involves making object definitions more suitable for computer interpretations

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

EECS490: Digital Image Processing. Lecture #23

EECS490: Digital Image Processing. Lecture #23 Lecture #23 Motion segmentation & motion tracking Boundary tracking Chain codes Minimum perimeter polygons Signatures Motion Segmentation P k Accumulative Difference Image Positive ADI Negative ADI (ADI)

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

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

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

Basic Algorithms for Digital Image Analysis: a course

Basic Algorithms for Digital Image Analysis: a course Institute of Informatics Eötvös Loránd University Budapest, Hungary Basic Algorithms for Digital Image Analysis: a course Dmitrij Csetverikov with help of Attila Lerch, Judit Verestóy, Zoltán Megyesi,

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

ECEN 447 Digital Image Processing

ECEN 447 Digital Image Processing ECEN 447 Digital Image Processing Lecture 8: Segmentation and Description Ulisses Braga-Neto ECE Department Texas A&M University Image Segmentation and Description Image segmentation and description are

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

Digital Image Processing

Digital Image Processing Digital Image Processing Part 2: Image Enhancement in the Spatial Domain AASS Learning Systems Lab, Dep. Teknik Room T1209 (Fr, 11-12 o'clock) achim.lilienthal@oru.se Course Book Chapter 3 2011-04-06 Contents

More information

Image and Multidimensional Signal Processing

Image and Multidimensional Signal Processing Image and Multidimensional Signal Processing Professor William Hoff Dept of Electrical Engineering &Computer Science http://inside.mines.edu/~whoff/ Representation and Description 2 Representation and

More information

Image Acquisition + Histograms

Image Acquisition + Histograms Image Processing - Lesson 1 Image Acquisition + Histograms Image Characteristics Image Acquisition Image Digitization Sampling Quantization Histograms Histogram Equalization What is an Image? An image

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

OBJECT DESCRIPTION - FEATURE EXTRACTION

OBJECT DESCRIPTION - FEATURE EXTRACTION INF 4300 Digital Image Analysis OBJECT DESCRIPTION - FEATURE EXTRACTION Fritz Albregtsen 1.10.011 F06 1.10.011 INF 4300 1 Today We go through G&W section 11. Boundary Descriptors G&W section 11.3 Regional

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

Feature description. IE PŁ M. Strzelecki, P. Strumiłło

Feature description. IE PŁ M. Strzelecki, P. Strumiłło Feature description After an image has been segmented the detected region needs to be described (represented) in a form more suitable for further processing. Representation of an image region can be carried

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

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

Problem definition Image acquisition Image segmentation Connected component analysis. Machine vision systems - 1

Problem definition Image acquisition Image segmentation Connected component analysis. Machine vision systems - 1 Machine vision systems Problem definition Image acquisition Image segmentation Connected component analysis Machine vision systems - 1 Problem definition Design a vision system to see a flat world Page

More information

Processing of binary images

Processing of binary images Binary Image Processing Tuesday, 14/02/2017 ntonis rgyros e-mail: argyros@csd.uoc.gr 1 Today From gray level to binary images Processing of binary images Mathematical morphology 2 Computer Vision, Spring

More information

CS534 Introduction to Computer Vision Binary Image Analysis. Ahmed Elgammal Dept. of Computer Science Rutgers University

CS534 Introduction to Computer Vision Binary Image Analysis. Ahmed Elgammal Dept. of Computer Science Rutgers University CS534 Introduction to Computer Vision Binary Image Analysis Ahmed Elgammal Dept. of Computer Science Rutgers University Outlines A Simple Machine Vision System Image segmentation by thresholding Digital

More information

Feature Descriptors. CS 510 Lecture #21 April 29 th, 2013

Feature Descriptors. CS 510 Lecture #21 April 29 th, 2013 Feature Descriptors CS 510 Lecture #21 April 29 th, 2013 Programming Assignment #4 Due two weeks from today Any questions? How is it going? Where are we? We have two umbrella schemes for object recognition

More information

Motion Estimation and Optical Flow Tracking

Motion Estimation and Optical Flow Tracking Image Matching Image Retrieval Object Recognition Motion Estimation and Optical Flow Tracking Example: Mosiacing (Panorama) M. Brown and D. G. Lowe. Recognising Panoramas. ICCV 2003 Example 3D Reconstruction

More information

Multimedia Information Retrieval

Multimedia Information Retrieval Multimedia Information Retrieval Prof Stefan Rüger Multimedia and Information Systems Knowledge Media Institute The Open University http://kmi.open.ac.uk/mmis Why content-based? Actually, what is content-based

More information

What is an Image? Image Acquisition. Image Processing - Lesson 2. An image is a projection of a 3D scene into a 2D projection plane.

What is an Image? Image Acquisition. Image Processing - Lesson 2. An image is a projection of a 3D scene into a 2D projection plane. mage Processing - Lesson 2 mage Acquisition mage Characteristics mage Acquisition mage Digitization Sampling Quantization mage Histogram What is an mage? An image is a projection of a 3D scene into a 2D

More information

Examination in Image Processing

Examination in Image Processing Umeå University, TFE Ulrik Söderström 203-03-27 Examination in Image Processing Time for examination: 4.00 20.00 Please try to extend the answers as much as possible. Do not answer in a single sentence.

More information

Pattern recognition. Classification/Clustering GW Chapter 12 (some concepts) Textures

Pattern recognition. Classification/Clustering GW Chapter 12 (some concepts) Textures Pattern recognition Classification/Clustering GW Chapter 12 (some concepts) Textures Patterns and pattern classes Pattern: arrangement of descriptors Descriptors: features Patten class: family of patterns

More information

Feature Detectors and Descriptors: Corners, Lines, etc.

Feature Detectors and Descriptors: Corners, Lines, etc. Feature Detectors and Descriptors: Corners, Lines, etc. Edges vs. Corners Edges = maxima in intensity gradient Edges vs. Corners Corners = lots of variation in direction of gradient in a small neighborhood

More information

Digital Image Processing. Lecture # 15 Image Segmentation & Texture

Digital Image Processing. Lecture # 15 Image Segmentation & Texture Digital Image Processing Lecture # 15 Image Segmentation & Texture 1 Image Segmentation Image Segmentation Group similar components (such as, pixels in an image, image frames in a video) Applications:

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

SUMMARY PART I. What is texture? Uses for texture analysis. Computing texture images. Using variance estimates. INF 4300 Digital Image Analysis

SUMMARY PART I. What is texture? Uses for texture analysis. Computing texture images. Using variance estimates. INF 4300 Digital Image Analysis INF 4 Digital Image Analysis SUMMARY PART I Fritz Albregtsen 4.. F 4.. INF 4 What is texture? Intuitively obvious, but no precise definition exists fine, coarse, grained, smooth etc Texture consists of

More information

Chapter 4 - Image. Digital Libraries and Content Management

Chapter 4 - Image. Digital Libraries and Content Management Prof. Dr.-Ing. Stefan Deßloch AG Heterogene Informationssysteme Geb. 36, Raum 329 Tel. 0631/205 3275 dessloch@informatik.uni-kl.de Chapter 4 - Image Vector Graphics Raw data: set (!) of lines and polygons

More information

Machine learning Pattern recognition. Classification/Clustering GW Chapter 12 (some concepts) Textures

Machine learning Pattern recognition. Classification/Clustering GW Chapter 12 (some concepts) Textures Machine learning Pattern recognition Classification/Clustering GW Chapter 12 (some concepts) Textures Patterns and pattern classes Pattern: arrangement of descriptors Descriptors: features Patten class:

More information

COMP_4190 Artificial Intelligence Computer Vision. Computer Vision. Levels of Abstraction. Digital Images

COMP_4190 Artificial Intelligence Computer Vision. Computer Vision. Levels of Abstraction. Digital Images COMP_49 Artificial Intelligence Computer Vision Jacky Baltes Department of Computer Science University of Manitoba Winnipeg, Manitoba Canada, RT N jacky@cs.umanitoba.ca http://www.cs.umanitoba.ca/~jacky

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

SUMMARY: DISTINCTIVE IMAGE FEATURES FROM SCALE- INVARIANT KEYPOINTS

SUMMARY: DISTINCTIVE IMAGE FEATURES FROM SCALE- INVARIANT KEYPOINTS SUMMARY: DISTINCTIVE IMAGE FEATURES FROM SCALE- INVARIANT KEYPOINTS Cognitive Robotics Original: David G. Lowe, 004 Summary: Coen van Leeuwen, s1460919 Abstract: This article presents a method to extract

More information

Schedule for Rest of Semester

Schedule for Rest of Semester Schedule for Rest of Semester Date Lecture Topic 11/20 24 Texture 11/27 25 Review of Statistics & Linear Algebra, Eigenvectors 11/29 26 Eigenvector expansions, Pattern Recognition 12/4 27 Cameras & calibration

More information

OBJECT SORTING IN MANUFACTURING INDUSTRIES USING IMAGE PROCESSING

OBJECT SORTING IN MANUFACTURING INDUSTRIES USING IMAGE PROCESSING OBJECT SORTING IN MANUFACTURING INDUSTRIES USING IMAGE PROCESSING Manoj Sabnis 1, Vinita Thakur 2, Rujuta Thorat 2, Gayatri Yeole 2, Chirag Tank 2 1 Assistant Professor, 2 Student, Department of Information

More information

Afdeling Toegepaste Wiskunde/ Division of Applied Mathematics Representation and description(skeletonization, shape numbers) SLIDE 1/16

Afdeling Toegepaste Wiskunde/ Division of Applied Mathematics Representation and description(skeletonization, shape numbers) SLIDE 1/16 Representation and description(skeletonization, shape numbers) SLIDE 1/16 Chapter 11: Representation and Description Asegmentedregioncanberepresentedby { boundarypixels internal pixels When shape is important,

More information

Feature extraction. Bi-Histogram Binarization Entropy. What is texture Texture primitives. Filter banks 2D Fourier Transform Wavlet maxima points

Feature extraction. Bi-Histogram Binarization Entropy. What is texture Texture primitives. Filter banks 2D Fourier Transform Wavlet maxima points Feature extraction Bi-Histogram Binarization Entropy What is texture Texture primitives Filter banks 2D Fourier Transform Wavlet maxima points Edge detection Image gradient Mask operators Feature space

More information

Pattern recognition. Classification/Clustering GW Chapter 12 (some concepts) Textures

Pattern recognition. Classification/Clustering GW Chapter 12 (some concepts) Textures Pattern recognition Classification/Clustering GW Chapter 12 (some concepts) Textures Patterns and pattern classes Pattern: arrangement of descriptors Descriptors: features Patten class: family of patterns

More information

We are IntechOpen, the world s leading publisher of Open Access books Built by scientists, for scientists. International authors and editors

We are IntechOpen, the world s leading publisher of Open Access books Built by scientists, for scientists. International authors and editors We are IntechOpen, the world s leading publisher of Open Access books Built by scientists, for scientists 3,500 108,000 1.7 M Open access books available International authors and editors Downloads Our

More information

CS 231A Computer Vision (Fall 2012) Problem Set 3

CS 231A Computer Vision (Fall 2012) Problem Set 3 CS 231A Computer Vision (Fall 2012) Problem Set 3 Due: Nov. 13 th, 2012 (2:15pm) 1 Probabilistic Recursion for Tracking (20 points) In this problem you will derive a method for tracking a point of interest

More information

SUPPLEMENTARY FILE S1: 3D AIRWAY TUBE RECONSTRUCTION AND CELL-BASED MECHANICAL MODEL. RELATED TO FIGURE 1, FIGURE 7, AND STAR METHODS.

SUPPLEMENTARY FILE S1: 3D AIRWAY TUBE RECONSTRUCTION AND CELL-BASED MECHANICAL MODEL. RELATED TO FIGURE 1, FIGURE 7, AND STAR METHODS. SUPPLEMENTARY FILE S1: 3D AIRWAY TUBE RECONSTRUCTION AND CELL-BASED MECHANICAL MODEL. RELATED TO FIGURE 1, FIGURE 7, AND STAR METHODS. 1. 3D AIRWAY TUBE RECONSTRUCTION. RELATED TO FIGURE 1 AND STAR METHODS

More information

Analysis of Binary Images

Analysis of Binary Images Analysis of Binary Images Introduction to Computer Vision CSE 52 Lecture 7 CSE52, Spr 07 The appearance of colors Color appearance is strongly affected by (at least): Spectrum of lighting striking the

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

A Survey on Feature Extraction Techniques for Shape based Object Recognition

A Survey on Feature Extraction Techniques for Shape based Object Recognition A Survey on Feature Extraction Techniques for Shape based Object Recognition Mitisha Narottambhai Patel Department of Computer Engineering, Uka Tarsadia University, Gujarat, India Purvi Tandel Department

More information

HISTOGRAMS OF ORIENTATIO N GRADIENTS

HISTOGRAMS OF ORIENTATIO N GRADIENTS HISTOGRAMS OF ORIENTATIO N GRADIENTS Histograms of Orientation Gradients Objective: object recognition Basic idea Local shape information often well described by the distribution of intensity gradients

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

Image features. Image Features

Image features. Image Features Image features Image features, such as edges and interest points, provide rich information on the image content. They correspond to local regions in the image and are fundamental in many applications in

More information

Last update: May 4, Vision. CMSC 421: Chapter 24. CMSC 421: Chapter 24 1

Last update: May 4, Vision. CMSC 421: Chapter 24. CMSC 421: Chapter 24 1 Last update: May 4, 200 Vision CMSC 42: Chapter 24 CMSC 42: Chapter 24 Outline Perception generally Image formation Early vision 2D D Object recognition CMSC 42: Chapter 24 2 Perception generally Stimulus

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

Features Points. Andrea Torsello DAIS Università Ca Foscari via Torino 155, Mestre (VE)

Features Points. Andrea Torsello DAIS Università Ca Foscari via Torino 155, Mestre (VE) Features Points Andrea Torsello DAIS Università Ca Foscari via Torino 155, 30172 Mestre (VE) Finding Corners Edge detectors perform poorly at corners. Corners provide repeatable points for matching, so

More information

DIGITAL IMAGE ANALYSIS. Image Classification: Object-based Classification

DIGITAL IMAGE ANALYSIS. Image Classification: Object-based Classification DIGITAL IMAGE ANALYSIS Image Classification: Object-based Classification Image classification Quantitative analysis used to automate the identification of features Spectral pattern recognition Unsupervised

More information

An Introduction to Content Based Image Retrieval

An Introduction to Content Based Image Retrieval CHAPTER -1 An Introduction to Content Based Image Retrieval 1.1 Introduction With the advancement in internet and multimedia technologies, a huge amount of multimedia data in the form of audio, video and

More information

CS 223B Computer Vision Problem Set 3

CS 223B Computer Vision Problem Set 3 CS 223B Computer Vision Problem Set 3 Due: Feb. 22 nd, 2011 1 Probabilistic Recursion for Tracking In this problem you will derive a method for tracking a point of interest through a sequence of images.

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

One image is worth 1,000 words

One image is worth 1,000 words Image Databases Prof. Paolo Ciaccia http://www-db. db.deis.unibo.it/courses/si-ls/ 07_ImageDBs.pdf Sistemi Informativi LS One image is worth 1,000 words Undoubtedly, images are the most wide-spread MM

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

Image Analysis Sample Submission Form

Image Analysis Sample Submission Form Image Analysis Sample Submission Form 3230 N. Susquehanna Trail, York, PA 17406 For assistance in completing this form, contact your sales representative or Microtrac. Please complete this form and include

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

CEE598 - Visual Sensing for Civil Infrastructure Eng. & Mgmt.

CEE598 - Visual Sensing for Civil Infrastructure Eng. & Mgmt. CEE598 - Visual Sensing for Civil Infrastructure Eng. & Mgmt. Section 10 - Detectors part II Descriptors Mani Golparvar-Fard Department of Civil and Environmental Engineering 3129D, Newmark Civil Engineering

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

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

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

Digital Image Fundamentals

Digital Image Fundamentals Digital Image Fundamentals Image Quality Objective/ subjective Machine/human beings Mathematical and Probabilistic/ human intuition and perception 6 Structure of the Human Eye photoreceptor cells 75~50

More information

Figure 1: Workflow of object-based classification

Figure 1: Workflow of object-based classification Technical Specifications Object Analyst Object Analyst is an add-on package for Geomatica that provides tools for segmentation, classification, and feature extraction. Object Analyst includes an all-in-one

More information

Local invariant features

Local invariant features Local invariant features Tuesday, Oct 28 Kristen Grauman UT-Austin Today Some more Pset 2 results Pset 2 returned, pick up solutions Pset 3 is posted, due 11/11 Local invariant features Detection of interest

More information

Blood Microscopic Image Analysis for Acute Leukemia Detection

Blood Microscopic Image Analysis for Acute Leukemia Detection I J C T A, 9(9), 2016, pp. 3731-3735 International Science Press Blood Microscopic Image Analysis for Acute Leukemia Detection V. Renuga, J. Sivaraman, S. Vinuraj Kumar, S. Sathish, P. Padmapriya and R.

More information

Scale Invariant Feature Transform

Scale Invariant Feature Transform Why do we care about matching features? Scale Invariant Feature Transform Camera calibration Stereo Tracking/SFM Image moiaicing Object/activity Recognition Objection representation and recognition Automatic

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

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

11. Image Data Analytics. Jacobs University Visualization and Computer Graphics Lab

11. Image Data Analytics. Jacobs University Visualization and Computer Graphics Lab 11. Image Data Analytics Motivation Images (and even videos) have become a popular data format for storing information digitally. Data Analytics 377 Motivation Traditionally, scientific and medical imaging

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

Automated Particle Size & Shape Analysis System

Automated Particle Size & Shape Analysis System Biovis PSA2000 Automated Particle Size & Shape Analysis System Biovis PSA2000 is an automated imaging system used to detect, characterize, categorize and report, the individual and cumulative particle

More information

Recognition: Face Recognition. Linda Shapiro EE/CSE 576

Recognition: Face Recognition. Linda Shapiro EE/CSE 576 Recognition: Face Recognition Linda Shapiro EE/CSE 576 1 Face recognition: once you ve detected and cropped a face, try to recognize it Detection Recognition Sally 2 Face recognition: overview Typical

More information

Building a Panorama. Matching features. Matching with Features. How do we build a panorama? Computational Photography, 6.882

Building a Panorama. Matching features. Matching with Features. How do we build a panorama? Computational Photography, 6.882 Matching features Building a Panorama Computational Photography, 6.88 Prof. Bill Freeman April 11, 006 Image and shape descriptors: Harris corner detectors and SIFT features. Suggested readings: Mikolajczyk

More information

Image retrieval based on region shape similarity

Image retrieval based on region shape similarity Image retrieval based on region shape similarity Cheng Chang Liu Wenyin Hongjiang Zhang Microsoft Research China, 49 Zhichun Road, Beijing 8, China {wyliu, hjzhang}@microsoft.com ABSTRACT This paper presents

More information

Unit Activity Correlations to Common Core State Standards. Geometry. Table of Contents. Geometry 1 Statistics and Probability 8

Unit Activity Correlations to Common Core State Standards. Geometry. Table of Contents. Geometry 1 Statistics and Probability 8 Unit Activity Correlations to Common Core State Standards Geometry Table of Contents Geometry 1 Statistics and Probability 8 Geometry Experiment with transformations in the plane 1. Know precise definitions

More information

Histograms of Oriented Gradients

Histograms of Oriented Gradients Histograms of Oriented Gradients Carlo Tomasi September 18, 2017 A useful question to ask of an image is whether it contains one or more instances of a certain object: a person, a face, a car, and so forth.

More information

Killingly Public Schools. Grades Draft Sept. 2002

Killingly Public Schools. Grades Draft Sept. 2002 Killingly Public Schools Grades 10-12 Draft Sept. 2002 ESSENTIALS OF GEOMETRY Grades 10-12 Language of Plane Geometry CONTENT STANDARD 10-12 EG 1: The student will use the properties of points, lines,

More information

Image Segmentation. Segmentation is the process of partitioning an image into regions

Image Segmentation. Segmentation is the process of partitioning an image into regions Image Segmentation Segmentation is the process of partitioning an image into regions region: group of connected pixels with similar properties properties: gray levels, colors, textures, motion characteristics

More information

2D Image Processing Feature Descriptors

2D Image Processing Feature Descriptors 2D Image Processing Feature Descriptors Prof. Didier Stricker Kaiserlautern University http://ags.cs.uni-kl.de/ DFKI Deutsches Forschungszentrum für Künstliche Intelligenz http://av.dfki.de 1 Overview

More information

SIFT: SCALE INVARIANT FEATURE TRANSFORM SURF: SPEEDED UP ROBUST FEATURES BASHAR ALSADIK EOS DEPT. TOPMAP M13 3D GEOINFORMATION FROM IMAGES 2014

SIFT: SCALE INVARIANT FEATURE TRANSFORM SURF: SPEEDED UP ROBUST FEATURES BASHAR ALSADIK EOS DEPT. TOPMAP M13 3D GEOINFORMATION FROM IMAGES 2014 SIFT: SCALE INVARIANT FEATURE TRANSFORM SURF: SPEEDED UP ROBUST FEATURES BASHAR ALSADIK EOS DEPT. TOPMAP M13 3D GEOINFORMATION FROM IMAGES 2014 SIFT SIFT: Scale Invariant Feature Transform; transform image

More information

Texture. Texture is a description of the spatial arrangement of color or intensities in an image or a selected region of an image.

Texture. Texture is a description of the spatial arrangement of color or intensities in an image or a selected region of an image. Texture Texture is a description of the spatial arrangement of color or intensities in an image or a selected region of an image. Structural approach: a set of texels in some regular or repeated pattern

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

Stereo Vision. MAN-522 Computer Vision

Stereo Vision. MAN-522 Computer Vision Stereo Vision MAN-522 Computer Vision What is the goal of stereo vision? The recovery of the 3D structure of a scene using two or more images of the 3D scene, each acquired from a different viewpoint in

More information

Achim J. Lilienthal Mobile Robotics and Olfaction Lab, AASS, Örebro University

Achim J. Lilienthal Mobile Robotics and Olfaction Lab, AASS, Örebro University Achim J. Lilienthal Mobile Robotics and Olfaction Lab, Room T1227, Mo, 11-12 o'clock AASS, Örebro University (please drop me an email in advance) achim.lilienthal@oru.se 1 4. Admin Course Plan Rafael C.

More information

Massachusetts Institute of Technology. Department of Computer Science and Electrical Engineering /6.866 Machine Vision Quiz I

Massachusetts Institute of Technology. Department of Computer Science and Electrical Engineering /6.866 Machine Vision Quiz I Massachusetts Institute of Technology Department of Computer Science and Electrical Engineering 6.801/6.866 Machine Vision Quiz I Handed out: 2004 Oct. 21st Due on: 2003 Oct. 28th Problem 1: Uniform reflecting

More information