1 Background and Introduction 2. 2 Assessment 2

Size: px
Start display at page:

Download "1 Background and Introduction 2. 2 Assessment 2"

Transcription

1 Luleå University of Technology Matthew Thurley Last revision: October 27, 2011 Industrial Image Analysis E0005E Product Development Phase 4 Binary Morphological Image Processing Contents 1 Background and Introduction 2 2 Assessment 2 3 Object Detection in Binary Images Detecting Circles Detecting Rectangles Detecting Squares PCB Component Detection 4 5 Blurp Box Incorporated Detecting Circles Optional Exercise Segmentation of Overlapping Objects Tips for Implementing the Distance Transform Reporting Assessment 10 7 Appendix : Calculating a Best-Fit Circle 11 1

2 1 Background and Introduction Read all of these instructions before starting. This week you will create some of the operations used to detect shapes for Blurp Box Incorporated in addition to learning about binary morphological image processing. Parts of this task are marked Optional and you should only do these if you have time. Remember that you need to write a clear and reasoned report outlining how and what you have done as instructed in the previous development phases. 2 Assessment Each Development Phase will be graded fail (U), pass (3), good (4), or very good (5) based on the following criteria; 1. How well does the report answer all the questions outlined in the development plan. Does the student provide a thorough and complete answer? 2. How clearly written is the report and how well reasoned is the explanation? How easy would it be for a technically qualified person to understand what you have done and why, and then follow the development phase instructions and your report and repeat the results? 3. When you are asked to explain or discuss something, explain why your result is this way in relation to the theory from the course material (necessary in order to achieve a grade of 4 or 5) 4. Have the optional parts of the Development Phase been answered and how thoroughly? (necessary in order to achieve a 5 grade) 3 Object Detection in Binary Images Binary morphological image processing can be used to detect objects in images. Load and view the image lab4shapes.tif The image consists of 2 circles, 2 rectangles and 3 squares. The circles have a diameter of 30 pixels, the lengths of the rectangles sides is 12 by 60 pixels and the squares have side lengths of 12 pixels. In this exercise you will implement three functions that will detect the three objects in the image. The functions will use the morphological operations opening and dilation. 3.1 Detecting Circles First, detect the largest objects in the image. As the circles are the largest objects in the image implement a function C = findcircles(im,radius). The circles are detected using 2

3 an opening by a flat circular disk with the radius less than the circles but greater than the size of other objects. For example: % Construct a Euclidean disk structuring element with radius 20 % Do not use structuring element decomposition. Set third argument to 0 sed=strel( disk,20,0); % Open image Im with structuring element sed C=imopen(Im,sed); Now use findcircles to detect the circles in the image and view the result. You will see that the opening by a flat circular disk removes objects where the disk does not fit. To find other objects in the image, the detected circles from the image have to be removed. The circles are removed from the original image by subtracting C from Im using the following Matlab command: D = im2bw(imsubtract(im,c)); Study the image where the circles are removed. You will notice that most of the circles have been removed but a few pixels at the border of the circles are left. So, the function findcircles detects the circles but fails to detect some pixels at the boundary. To make the detection more robust you should dilate the detected circles so that the size will grow with one pixel at the border. That is done by dilating with a diamond shape structuring element of size 1. As the dilated version of the circles may be bigger than the circles in the original image, the circles are finally detected by the intersection of the original image and the dilated version of the detected circles. The above operation is performed with the following MATLAB command: sex1=strel( diamond,1); Cd=imdilate(C,sex1); C2=and(Im,Cd); Now remove the circles that where detected using the more robust method from the original image and call the new image D2. Study the image D2 where you should see that the circles have completely been removed. Use D2 in the next step where you detect rectangles. 3.2 Detecting Rectangles Now implement a function R = findrectangles(im,[sizei sizej]) that detect rectangles in an image with size greater than sizei * sizej. A rectangular structuring element is generated with: ser=strel( rectangle,[sizei sizej]); Use the function findrectangles to open the image D2 by a rectangular structuring element of size 10 * 58 to detect the rectangles. Call the result E and study the result. Remove the detected rectangles from D2, call the new image F and continue to the next step. 3

4 3.3 Detecting Squares Now implement a function R = findsquares(im,size) that detect squares in an image with side lengths greater than a parameter size. A square structuring element whose width is size pixels is generated with: ses=strel( square,size); Use the function findsquares to open the image F by a square structuring element of size 10 * 10 to detect the remaining squares. Call the result G and study the result. Finally remove the detected squares from F and check that no more objects are in the image. Reporting: There is nothing to report for this section as you will need these functions that you have developed in the next section. 4 PCB Component Detection In this section you will use binary mathematical morphological operations to detect different components on a printed circuit board. Load and view the image pcb.tif shown in figure 1. Figure 1: Binary printed circuit board image You will have to detect six different types of components (not in this order); Circular contacts Square contacts Rectangular contacts Thick tracks Thin tracks Holes Use the functions implemented in section 3 to detect all components and use the same iterative strategy outlined in section 3. You have to find suitable sizes of structuring elements and remember that this is an real image where, for instance, a square contact on the printed 4

5 circuit board is not a perfect square. Remember that to make the detection more robust, use the technique explained when circles where detected. Hint: First fill the holes in the image using the morphological operation imfill mentioned in lecture 4. The residue of the subtraction of the filled image without holes and the original image are the holes. It is easier to detect all components using the filled image. When all components have been detected, the holes can be set to zero to show the final result. Reporting Describe in detail how your detection algorithm works. What structuring elements are used and in what order. Provide images that explain the process of detecting all components. Also provide a final image where each component type is labelled with a specific gray level intensity so that it is easy to see and identify each component in the image. You do not have to supply your code for the findcircles, findsquares, findrectangles functions but supply your code for your method that calls these functions so your technical supervisor can see the structure of your detection algorithm. 5 Blurp Box Incorporated 5.1 Detecting Circles You will now construct a useful operation that will be applied to the Blurp Box conveyor belt manufacturing line. Construct images from the conveyor belt as you have previously done with the following commands; load conveyor box= MakeBoxFrame(conveyor); imagesc(box/255) Produce a grayscale version of box as you did in Development Phase 1. Later in the course we will use a more reliable technique to extract a grayscale image and to threshold it, but for now use the following command; box = 255*rgb2gray(box/255); Your job is now to construct a function Out = IsCircle(Im,Tl,Tu,Tc) that takes as input a grayscale image Im and three threshold values Tl,Tu,Tc. The output from the function should be Out = 1 if the image contains a circular blurp box and Out = 0 otherwise. The suggestion is that you perform the following steps (but you are free to chose other ways): Segment the image as you did in the Blurp Box Incorporated section of lab 1 (using the threshold values Tl and Tu). Apply a binary opening on the segmented image (to remove noise points). Use the function bwfill to get rid of the holes in the object. Use the function bwperim to find the perimeter (edges) of the object. 5

6 Now, using the perimeter points, find estimates of the centre point (x 0,y 0 ) and radius R of a best-fit circle (see Appendix 1 for the equation of a circle and how to estimate x 0,y 0 and R). Figure 2 shows an example of the kind of image and circle estimate you might produce. The object shown in figure 2 might not be very accurately approximated by a circle. One possible measure of how wrong the estimate is is how much the circle deviates from the object boundary such as with the weighted sum of the error area (shown in figure 2) and given by equation 1. Use the weighted sum of the error area calculated in equation 1 to produce Out = 1 (i.e. you detected a circle) if ǫ < Tc and Out = 0 otherwise. A value of 0.1 might be a reasonable value for T c. Figure 2: Rectangular shape on the conveyor belt with an estimated circle draw over the top (left image). The error area is shown as the non intersecting parts of both the rectangle and the circle (right image) ǫ = 1 mr m (xk x 0 ) 2 +(y k y 0 ) 2 R 2 (1) k=1 Optional Exercise: You are free to try other solutions than that outlined above. As you discovered in Phase 1 the threshold operation may not always produce a valid object when applied to the grayscale box images, but we must accept this error for now. We will rectify this problem when we learn about Color Image Processing. Reporting: Supply your well commented code for iscircle and make sure to explain what you have done so your technical supervisor can easily see any additions or modifications to the algorithm suggested here. 5.2 Optional Exercise Warning: this is a very unconstrained optional exercise. Be aware of the time you have available. Some tasks you will face in industry can not be completely resolved in the time you will have available. You may only be able to test a few things and make some comment or recommendation to your technical supervisor. Document ALL your actions and findings in this exercise. 6

7 Energy Technology Centre (ETC) is doing some experiments with high speed images of a liquid jet stream captured at 4000 frames per second. The droplets are moving at high speed from left to right in the images and the camera is setup opposite a light source in an arrangement called back lighting. ETC wants to find individual droplets of liquid in the jet stream and classify them into different sizes. How many droplets of each different size. A sequential series of four of these images is named P1 T1 3mm00000Ns.png where N is the sequence number 1,2,3,4. Image 1 is shown in figure 3. Figure 3: Jet stream of droplets The background illumination in these images is very uneven so you will need to attempt to remove this variation. As these images are of the same scene, and the light source is not moving (only the droplets of liquid), you could combine all four images by taking their maximum value to create an image that approximates the light source, without the droplets. C = max(a,b); % calculate a new image C, that contains the maximum intensity pixels from images A and B Once you have an approximation of the light source, lets call it image L, subtract one of the original images from it. You should get an image that has mostly just the droplets of liquid. Consider whether you should contrast enhance this image further, and how. Perform a threshold operation on your image to obtain a binary image of the droplets. Comment on how this works, are you getting too much background, or not enough droplets, do you need to filter the image in any other way? Once you have a binary image of the droplets, consider how you could use morphological operations with a disk structuring element to remove droplets in a similar way to how you have identified and removed the circles on the circuit board. Start by trying to remove very small droplets first. Remember, this is an optional exercise, you need to manage your time to see what you can achieve in the available time. You are trying to give your technical supervisor a good idea of a strategy for solving this problem, you don t have to solve it perfectly, but make sure you explain and comment on the problems you find. Reporting: Show the images and code for all the methods you tried, and provide comments 7

8 and explanation of your reasoning. 5.3 Segmentation of Overlapping Objects Load the Matlab file circles2.tif and look at it. This is a thresholded (i.e. a binary) image from the Blurp Box Incorporated production line, but obviously something has gone wrong. Several circular shapes has been piled on top of each other on the same frame. It is therefore necessary to find a way to separate the four shapes, and this can be done using the morphological watershed transform to do this. The first step is to calculate the distance transform to make a 3D surface upon which the watershed segmentation can be performed (discussed in lecture 4). Figure 4: A binary image Consider the binary image shown in figure 4. Using this image calculate the distance transform d(i,j) as follows; for each pixel in the input binary image Im(i,j) that equals 1, the distance transform equals the distance to the nearest other pixel (i min,j min ) with value 0. Otherwise the distance transform is 0. The distance is calculated using equation 2. d(i,j) = { 0 ;Im(i,j) = 0 (i imin ) 2 +(j j min ) 2 ;Im(i,j) = 1 (2) Write a function d = disttrans(im) that, given a binary image Im, produces the distance transform d. Refer to section 5.4 for some tips for implementing the distance transform. Apply this operation on the image Im and study the result. Test the 3-D MATLAB plot mesh(-d) and see if the analogy with water basins and watersheds is relevant. Use your distance transform function to produce the distance transform image d of the original image circles2.tif. Segment this image with the help of the watershed transform (as discussed in lecture notes 4). An implementation of this segmentation algorithm is available in MATLAB using the command w = watershed(-d); The matrix w will contain a number of different regions (areas of different graylevel values) each representing one object in the original image circles2.tif. Study the transform d 8

9 and examine how well the segmentation has worked by giving the following command (use rescale) image(circles2.*(w==k)); where k = 0,1,2.3,... (you should have 4-5 areas if the segmentation has worked OK). Reporting:Using rescale supply the image (circles2+w), that is, the sum of the original image and the transform. Comment on the result and present your code for disttrans. 5.4 Tips for Implementing the Distance Transform When calculating the distance transform you will need to detect pixels with value one as shown by the region marked inner area in figure 5. Then determine the position of the closest pixel in the outer area (holding the value zero). It is clear that no such closest pixel can be located anywhere else than on the external boundary (see lecture notes 4 for how to calculate the external boundary) of the inner area. It is therefore only necessary to investigate these pixels. The coordinates of all pixels with value one in a binary perimeter image can be found with the find function (see example in the Appendix). Figure 5: Binary image (left image), External boundary (right image) 9

10 6 Reporting Assessment Using the assessment criteria, assess your own development report and write a short evaluation of how well it satisfies the criteria? How well does your report answer all the questions outlined in the development plan. Do you provide a thorough and complete answer? How clearly written is your report and how well reasoned the discussion. How easy would it be for a technically qualified person to follow your report to repeat the results? Have you answered the optional parts of the Development Phase been answered and how thoroughly? Do you have time for this? (necessary in order to achieve a 5 grade) Are there any problems with your solution? That is, situations where it doesn t work as expected? Your technical supervisor will need to know about these situations so that they can be solved and don t cause unexpected problems later during system integration and installation in week 8. The purpose of this assessment question is for you to evaluate your own work like you would have to in a real work situation before handing it over to your technical supervisor. 10

11 7 Appendix : Calculating a Best-Fit Circle The equation for a circle can be written as shown in equation 3 where (x 0,y 0 ) is the circle centre and R the radius. By using the partial derivatives shown in equation 4 it is possible to construct a linear least-squares problem involving a discrete set of m circle coordinate pairs (x 1,y 1 ),(x 2,y 2 ),...,(x m,y m ). f(x 0,y 0,R) = (x x 0 ) 2 +(y y 0 ) 2 R 2 = 0 (3) δf = 0, δf = 0, δf δx 0 δy 0 δr = 0 (4) The linear system Ma = v can be expressed in equation 5 where M is a m by 3 matrix and v is a m long column vector. x 1 y 1 1 x 2 y 2 1 x m y m 1 a b c = x 2 1 y2 1 x 2 2 y2 2 x 2 m y 2 m (5) The solution is given by a = (M t M) 1 (M t v) where the vector a is given by equation 6 from which x 0,y 0 and R can be determined. a b c = 2x o 2y 0 x 2 o +y 2 0 R2 (6) To form the matrix system for a circle in a binary image Im it is convenient to use the command [X Y] = find(im==1) This will give the column vectors X = [x 1,x 2,,x m ] t (i.e. all the possible circle coordinates in the i dimension), and Y = [y 1,y 2,,y m ] t (all the possible circle coordinates in the j dimension). M, v, a can be finally calculated using the following commands M = [X Y ones(size(x))]; v = -X.^2 - Y.^2; a = inv(m *M)*(M *v); 11

The 2D Fourier transform & image filtering

The 2D Fourier transform & image filtering Luleå University of Technology Matthew Thurley and Johan Carlson Last revision: Oct 27, 2011 Industrial Image Analysis E0005E Product Development Phase 6 The 2D Fourier transform & image filtering Contents

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

Lab 2. Hanz Cuevas Velásquez, Bob Fisher Advanced Vision School of Informatics, University of Edinburgh Week 3, 2018

Lab 2. Hanz Cuevas Velásquez, Bob Fisher Advanced Vision School of Informatics, University of Edinburgh Week 3, 2018 Lab 2 Hanz Cuevas Velásquez, Bob Fisher Advanced Vision School of Informatics, University of Edinburgh Week 3, 2018 This lab will focus on learning simple image transformations and the Canny edge detector.

More information

morphology on binary images

morphology on binary images morphology on binary images Ole-Johan Skrede 10.05.2017 INF2310 - Digital Image Processing Department of Informatics The Faculty of Mathematics and Natural Sciences University of Oslo After original slides

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

09/11/2017. Morphological image processing. Morphological image processing. Morphological image processing. Morphological image processing (binary)

09/11/2017. Morphological image processing. Morphological image processing. Morphological image processing. Morphological image processing (binary) Towards image analysis Goal: Describe the contents of an image, distinguishing meaningful information from irrelevant one. Perform suitable transformations of images so as to make explicit particular shape

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

E0005E - Industrial Image Analysis

E0005E - Industrial Image Analysis E0005E - Industrial Image Analysis The Hough Transform Matthew Thurley slides by Johan Carlson 1 This Lecture The Hough transform Detection of lines Detection of other shapes (the generalized Hough transform)

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

CITS 4402 Computer Vision

CITS 4402 Computer Vision CITS 4402 Computer Vision A/Prof Ajmal Mian Adj/A/Prof Mehdi Ravanbakhsh, CEO at Mapizy (www.mapizy.com) and InFarm (www.infarm.io) Lecture 02 Binary Image Analysis Objectives Revision of image formation

More information

EECS490: Digital Image Processing. Lecture #17

EECS490: Digital Image Processing. Lecture #17 Lecture #17 Morphology & set operations on images Structuring elements Erosion and dilation Opening and closing Morphological image processing, boundary extraction, region filling Connectivity: convex

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

Morphological Image Processing

Morphological Image Processing Morphological Image Processing Binary image processing In binary images, we conventionally take background as black (0) and foreground objects as white (1 or 255) Morphology Figure 4.1 objects on a conveyor

More information

Lecture: Segmentation I FMAN30: Medical Image Analysis. Anders Heyden

Lecture: Segmentation I FMAN30: Medical Image Analysis. Anders Heyden Lecture: Segmentation I FMAN30: Medical Image Analysis Anders Heyden 2017-11-13 Content What is segmentation? Motivation Segmentation methods Contour-based Voxel/pixel-based Discussion What is segmentation?

More information

Introduction. Computer Vision & Digital Image Processing. Preview. Basic Concepts from Set Theory

Introduction. Computer Vision & Digital Image Processing. Preview. Basic Concepts from Set Theory Introduction Computer Vision & Digital Image Processing Morphological Image Processing I Morphology a branch of biology concerned with the form and structure of plants and animals Mathematical morphology

More information

Mathematical morphology (1)

Mathematical morphology (1) Chapter 9 Mathematical morphology () 9. Introduction Morphology, or morphology for short, is a branch of image processing which is particularly useful for analyzing shapes in images. We shall develop basic

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

Education and Training CUFMEM14A. Exercise 2. Create, Manipulate and Incorporate 2D Graphics

Education and Training CUFMEM14A. Exercise 2. Create, Manipulate and Incorporate 2D Graphics Education and Training CUFMEM14A Exercise 2 Create, Manipulate and Incorporate 2D Graphics Menu Exercise 2 Exercise 2a: Scarecrow Exercise - Painting and Drawing Tools... 3 Exercise 2b: Scarecrow Exercise

More information

Mathematical Morphology and Distance Transforms. Robin Strand

Mathematical Morphology and Distance Transforms. Robin Strand Mathematical Morphology and Distance Transforms Robin Strand robin.strand@it.uu.se Morphology Form and structure Mathematical framework used for: Pre-processing Noise filtering, shape simplification,...

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

11/10/2011 small set, B, to probe the image under study for each SE, define origo & pixels in SE

11/10/2011 small set, B, to probe the image under study for each SE, define origo & pixels in SE Mathematical Morphology Sonka 13.1-13.6 Ida-Maria Sintorn ida@cb.uu.se Today s lecture SE, morphological transformations inary MM Gray-level MM Applications Geodesic transformations Morphology-form and

More information

FLUENT Secondary flow in a teacup Author: John M. Cimbala, Penn State University Latest revision: 26 January 2016

FLUENT Secondary flow in a teacup Author: John M. Cimbala, Penn State University Latest revision: 26 January 2016 FLUENT Secondary flow in a teacup Author: John M. Cimbala, Penn State University Latest revision: 26 January 2016 Note: These instructions are based on an older version of FLUENT, and some of the instructions

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

Morphological Image Processing

Morphological Image Processing Morphological Image Processing Ranga Rodrigo October 9, 29 Outline Contents Preliminaries 2 Dilation and Erosion 3 2. Dilation.............................................. 3 2.2 Erosion..............................................

More information

MODULE - 4. e-pg Pathshala

MODULE - 4. e-pg Pathshala e-pg Pathshala MODULE - 4 Subject : Computer Science Paper: Computer Graphics and Visualization Module: Midpoint Circle Drawing Procedure Module No: CS/CGV/4 Quadrant 1 e-text Before going into the Midpoint

More information

Filtering Images. Contents

Filtering Images. Contents Image Processing and Data Visualization with MATLAB Filtering Images Hansrudi Noser June 8-9, 010 UZH, Multimedia and Robotics Summer School Noise Smoothing Filters Sigmoid Filters Gradient Filters Contents

More information

What will we learn? What is mathematical morphology? What is mathematical morphology? Fundamental concepts and operations

What will we learn? What is mathematical morphology? What is mathematical morphology? Fundamental concepts and operations What will we learn? What is mathematical morphology and how is it used in image processing? Lecture Slides ME 4060 Machine Vision and Vision-based Control Chapter 13 Morphological image processing By Dr.

More information

Image Segmentation Techniques for Object-Based Coding

Image Segmentation Techniques for Object-Based Coding Image Techniques for Object-Based Coding Junaid Ahmed, Joseph Bosworth, and Scott T. Acton The Oklahoma Imaging Laboratory School of Electrical and Computer Engineering Oklahoma State University {ajunaid,bosworj,sacton}@okstate.edu

More information

Image Registration for Volume Measurement in 3D Range Data

Image Registration for Volume Measurement in 3D Range Data Image Registration for Volume Measurement in 3D Range Data Fernando Indurain Gaspar Matthew Thurley Lulea May 2011 2 Abstract At this report we will explain how we have designed an application based on

More information

Lossy Coding 2 JPEG. Perceptual Image Coding. Discrete Cosine Transform JPEG. CS559 Lecture 9 JPEG, Raster Algorithms

Lossy Coding 2 JPEG. Perceptual Image Coding. Discrete Cosine Transform JPEG. CS559 Lecture 9 JPEG, Raster Algorithms CS559 Lecture 9 JPEG, Raster Algorithms These are course notes (not used as slides) Written by Mike Gleicher, Sept. 2005 With some slides adapted from the notes of Stephen Chenney Lossy Coding 2 Suppose

More information

EN1610 Image Understanding Lab # 3: Edges

EN1610 Image Understanding Lab # 3: Edges EN1610 Image Understanding Lab # 3: Edges The goal of this fourth lab is to ˆ Understanding what are edges, and different ways to detect them ˆ Understand different types of edge detectors - intensity,

More information

EDEXCEL NATIONAL CERTIFICATE UNIT 4 MATHEMATICS FOR TECHNICIANS OUTCOME 1

EDEXCEL NATIONAL CERTIFICATE UNIT 4 MATHEMATICS FOR TECHNICIANS OUTCOME 1 EDEXCEL NATIONAL CERTIFICATE UNIT 4 MATHEMATICS FOR TECHNICIANS OUTCOME 1 TUTORIAL 4 AREAS AND VOLUMES Determine the fundamental algebraic laws and apply algebraic manipulation techniques to the solution

More information

Applications of Integration. Copyright Cengage Learning. All rights reserved.

Applications of Integration. Copyright Cengage Learning. All rights reserved. Applications of Integration Copyright Cengage Learning. All rights reserved. Volume: The Disk Method Copyright Cengage Learning. All rights reserved. Objectives Find the volume of a solid of revolution

More information

Using Edge Detection in Machine Vision Gauging Applications

Using Edge Detection in Machine Vision Gauging Applications Application Note 125 Using Edge Detection in Machine Vision Gauging Applications John Hanks Introduction This application note introduces common edge-detection software strategies for applications such

More information

HOUGH TRANSFORM. Plan for today. Introduction to HT. An image with linear structures. INF 4300 Digital Image Analysis

HOUGH TRANSFORM. Plan for today. Introduction to HT. An image with linear structures. INF 4300 Digital Image Analysis INF 4300 Digital Image Analysis HOUGH TRANSFORM Fritz Albregtsen 14.09.2011 Plan for today This lecture goes more in detail than G&W 10.2! Introduction to Hough transform Using gradient information to

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

Morphological Image Processing

Morphological Image Processing Morphological Image Processing Morphology Identification, analysis, and description of the structure of the smallest unit of words Theory and technique for the analysis and processing of geometric structures

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

Advanced Image Processing, TNM034 Optical Music Recognition

Advanced Image Processing, TNM034 Optical Music Recognition Advanced Image Processing, TNM034 Optical Music Recognition Linköping University By: Jimmy Liikala, jimli570 Emanuel Winblad, emawi895 Toms Vulfs, tomvu491 Jenny Yu, jenyu080 1 Table of Contents Optical

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

Math Geometry FAIM 2015 Form 1-A [ ]

Math Geometry FAIM 2015 Form 1-A [ ] Math Geometry FAIM 2015 Form 1-A [1530458] Student Class Date Instructions Use your Response Document to answer question 13. 1. Given: Trapezoid EFGH with vertices as shown in the diagram below. Trapezoid

More information

CHAPTER-4 LOCALIZATION AND CONTOUR DETECTION OF OPTIC DISK

CHAPTER-4 LOCALIZATION AND CONTOUR DETECTION OF OPTIC DISK CHAPTER-4 LOCALIZATION AND CONTOUR DETECTION OF OPTIC DISK Ocular fundus images can provide information about ophthalmic, retinal and even systemic diseases such as hypertension, diabetes, macular degeneration

More information

Based on Regression Diagnostics

Based on Regression Diagnostics Automatic Detection of Region-Mura Defects in TFT-LCD Based on Regression Diagnostics Yu-Chiang Chuang 1 and Shu-Kai S. Fan 2 Department of Industrial Engineering and Management, Yuan Ze University, Tao

More information

Digital Image Processing. Prof. P. K. Biswas. Department of Electronic & Electrical Communication Engineering

Digital Image Processing. Prof. P. K. Biswas. Department of Electronic & Electrical Communication Engineering Digital Image Processing Prof. P. K. Biswas Department of Electronic & Electrical Communication Engineering Indian Institute of Technology, Kharagpur Lecture - 21 Image Enhancement Frequency Domain Processing

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

Lab # 2 - ACS I Part I - DATA COMPRESSION in IMAGE PROCESSING using SVD

Lab # 2 - ACS I Part I - DATA COMPRESSION in IMAGE PROCESSING using SVD Lab # 2 - ACS I Part I - DATA COMPRESSION in IMAGE PROCESSING using SVD Goals. The goal of the first part of this lab is to demonstrate how the SVD can be used to remove redundancies in data; in this example

More information

(Section 6.2: Volumes of Solids of Revolution: Disk / Washer Methods)

(Section 6.2: Volumes of Solids of Revolution: Disk / Washer Methods) (Section 6.: Volumes of Solids of Revolution: Disk / Washer Methods) 6.. PART E: DISK METHOD vs. WASHER METHOD When using the Disk or Washer Method, we need to use toothpicks that are perpendicular to

More information

PERSPECTIVES ON GEOMETRY PRE-ASSESSMENT ANSWER SHEET (GEO )

PERSPECTIVES ON GEOMETRY PRE-ASSESSMENT ANSWER SHEET (GEO ) PERSPECTIVES ON GEOMETRY PRE-ASSESSMENT ANSWER SHEET (GEO.11.02.2) Name Date Site TURN IN BOTH TEST AND ANSWER SHEET TO YOUR INSTRUCTOR WHEN DONE. 1. 18. I. 2. 19. 3. 20. 4. 21. 5. 22. 6. 23. 7. 24. 8.

More information

Fig. 1. Input image. Ibw=im2bw(I, 250/255); % threshold value should be between Fig. 2. Thresholded image cercuri-stele.

Fig. 1. Input image. Ibw=im2bw(I, 250/255); % threshold value should be between Fig. 2. Thresholded image cercuri-stele. 1. Thresholding and filterring L3. Pattern recognition in MATLAB After the image is read from the disk and transformed in grayscale (see lab 2), the image is binarized using a threshld that favores the

More information

Bioimage Informatics

Bioimage Informatics Bioimage Informatics Lecture 14, Spring 2012 Bioimage Data Analysis (IV) Image Segmentation (part 3) Lecture 14 March 07, 2012 1 Outline Review: intensity thresholding based image segmentation Morphological

More information

Mathematics Curriculum

Mathematics Curriculum 6 G R A D E Mathematics Curriculum GRADE 6 5 Table of Contents 1... 1 Topic A: Area of Triangles, Quadrilaterals, and Polygons (6.G.A.1)... 11 Lesson 1: The Area of Parallelograms Through Rectangle Facts...

More information

Direct Variations DIRECT AND INVERSE VARIATIONS 19. Name

Direct Variations DIRECT AND INVERSE VARIATIONS 19. Name DIRECT AND INVERSE VARIATIONS 19 Direct Variations Name Of the many relationships that two variables can have, one category is called a direct variation. Use the description and example of direct variation

More information

Introduction to Digital Image Processing

Introduction to Digital Image Processing Fall 2005 Image Enhancement in the Spatial Domain: Histograms, Arithmetic/Logic Operators, Basics of Spatial Filtering, Smoothing Spatial Filters Tuesday, February 7 2006, Overview (1): Before We Begin

More information

(Refer Slide Time 00:17) Welcome to the course on Digital Image Processing. (Refer Slide Time 00:22)

(Refer Slide Time 00:17) Welcome to the course on Digital Image Processing. (Refer Slide Time 00:22) Digital Image Processing Prof. P. K. Biswas Department of Electronics and Electrical Communications Engineering Indian Institute of Technology, Kharagpur Module Number 01 Lecture Number 02 Application

More information

Counting Particles or Cells Using IMAQ Vision

Counting Particles or Cells Using IMAQ Vision Application Note 107 Counting Particles or Cells Using IMAQ Vision John Hanks Introduction To count objects, you use a common image processing technique called particle analysis, often referred to as blob

More information

Understanding Tracking and StroMotion of Soccer Ball

Understanding Tracking and StroMotion of Soccer Ball Understanding Tracking and StroMotion of Soccer Ball Nhat H. Nguyen Master Student 205 Witherspoon Hall Charlotte, NC 28223 704 656 2021 rich.uncc@gmail.com ABSTRACT Soccer requires rapid ball movements.

More information

(Sample) Final Exam with brief answers

(Sample) Final Exam with brief answers Name: Perm #: (Sample) Final Exam with brief answers CS/ECE 181B Intro to Computer Vision March 24, 2017 noon 3:00 pm This is a closed-book test. There are also a few pages of equations, etc. included

More information

Biomedical Image Analysis. Mathematical Morphology

Biomedical Image Analysis. Mathematical Morphology Biomedical Image Analysis Mathematical Morphology Contents: Foundation of Mathematical Morphology Structuring Elements Applications BMIA 15 V. Roth & P. Cattin 265 Foundations of Mathematical Morphology

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

Perfect square numbers are formed when we multiply a number (factor) by itself, or square a number. 9 is a perfect square, and 3 is it s factor.

Perfect square numbers are formed when we multiply a number (factor) by itself, or square a number. 9 is a perfect square, and 3 is it s factor. Math Unit 1: Square Roots and Surface Area. Review from Grade 8: Perfect Squares What is a perfect square? Perfect square numbers are formed when we multiply a number (factor) by itself, or square a number.

More information

Product information. Hi-Tech Electronics Pte Ltd

Product information. Hi-Tech Electronics Pte Ltd Product information Introduction TEMA Motion is the world leading software for advanced motion analysis. Starting with digital image sequences the operator uses TEMA Motion to track objects in images,

More information

Segmentation

Segmentation Lecture 6: Segmentation 24--4 Robin Strand Centre for Image Analysis Dept. of IT Uppsala University Today What is image segmentation? A smörgåsbord of methods for image segmentation: Thresholding Edge-based

More information

Lecture 6: Segmentation by Point Processing

Lecture 6: Segmentation by Point Processing Lecture 6: Segmentation by Point Processing Harvey Rhody Chester F. Carlson Center for Imaging Science Rochester Institute of Technology rhody@cis.rit.edu September 27, 2005 Abstract Applications of point

More information

How to create shapes. Drawing basic shapes. Adobe Photoshop Elements 8 guide

How to create shapes. Drawing basic shapes. Adobe Photoshop Elements 8 guide How to create shapes With the shape tools in Adobe Photoshop Elements, you can draw perfect geometric shapes, regardless of your artistic ability or illustration experience. The first step to drawing shapes

More information

4. Write sets of directions for how to check for direct variation. How to check for direct variation by analyzing the graph :

4. Write sets of directions for how to check for direct variation. How to check for direct variation by analyzing the graph : Name Direct Variations There are many relationships that two variables can have. One of these relationships is called a direct variation. Use the description and example of direct variation to help you

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

UNIVERSITY OF OSLO. Faculty of Mathematics and Natural Sciences

UNIVERSITY OF OSLO. Faculty of Mathematics and Natural Sciences UNIVERSITY OF OSLO Faculty of Mathematics and Natural Sciences Exam: INF 4300 / INF 9305 Digital image analysis Date: Thursday December 21, 2017 Exam hours: 09.00-13.00 (4 hours) Number of pages: 8 pages

More information

Morphological Image Processing

Morphological Image Processing Morphological Image Processing Binary dilation and erosion" Set-theoretic interpretation" Opening, closing, morphological edge detectors" Hit-miss filter" Morphological filters for gray-level images" Cascading

More information

Computer Vision. Image Segmentation. 10. Segmentation. Computer Engineering, Sejong University. Dongil Han

Computer Vision. Image Segmentation. 10. Segmentation. Computer Engineering, Sejong University. Dongil Han Computer Vision 10. Segmentation Computer Engineering, Sejong University Dongil Han Image Segmentation Image segmentation Subdivides an image into its constituent regions or objects - After an image has

More information

Mathematics Curricular Guide Common Core State Standards Transitional Document FOURTH GRADE SCHOOL YEAR MATHEMATICS SCOPE & SEQUENCE

Mathematics Curricular Guide Common Core State Standards Transitional Document FOURTH GRADE SCHOOL YEAR MATHEMATICS SCOPE & SEQUENCE Mathematics Curricular Guide Common Core State Standards Transitional Document FOURTH GRADE 2013-2014 SCHOOL YEAR MATHEMATICS SCOPE & SEQUENCE Unit Title Days 1. Unit 5: Landmarks and Large Numbers 13

More information

Excerpt from "Art of Problem Solving Volume 1: the Basics" 2014 AoPS Inc.

Excerpt from Art of Problem Solving Volume 1: the Basics 2014 AoPS Inc. Chapter 5 Using the Integers In spite of their being a rather restricted class of numbers, the integers have a lot of interesting properties and uses. Math which involves the properties of integers is

More information

Segmentation

Segmentation Lecture 6: Segmentation 215-13-11 Filip Malmberg Centre for Image Analysis Uppsala University 2 Today What is image segmentation? A smörgåsbord of methods for image segmentation: Thresholding Edge-based

More information

Lee County Curriculum Road Map - Grade

Lee County Curriculum Road Map - Grade Unit Standard Test Standard Description Teacher Resources 1 Place Value (15 days) August 8-28 Lee County Curriculum Road Map - Grade 4-2018-2019 4.NBT.2 4.NBT.3 1 st 9 Weeks Midterm: 4.NBT.52 4.NBT.3 4.

More information

13 Vectorizing. Overview

13 Vectorizing. Overview 13 Vectorizing Vectorizing tools are used to create vector data from scanned drawings or images. Combined with the display speed of Image Manager, these tools provide an efficient environment for data

More information

Addition and Subtraction

Addition and Subtraction PART Looking Back At: Grade Number and Operations 89 Geometry 9 Fractions 94 Measurement 9 Data 9 Number and Operations 96 Geometry 00 Fractions 0 Measurement 02 Data 0 Looking Forward To: Grade Number

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 I

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 I 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 I For students of HI 5323

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

Renderer Implementation: Basics and Clipping. Overview. Preliminaries. David Carr Virtual Environments, Fundamentals Spring 2005

Renderer Implementation: Basics and Clipping. Overview. Preliminaries. David Carr Virtual Environments, Fundamentals Spring 2005 INSTITUTIONEN FÖR SYSTEMTEKNIK LULEÅ TEKNISKA UNIVERSITET Renderer Implementation: Basics and Clipping David Carr Virtual Environments, Fundamentals Spring 2005 Feb-28-05 SMM009, Basics and Clipping 1

More information

REGION & EDGE BASED SEGMENTATION

REGION & EDGE BASED SEGMENTATION INF 4300 Digital Image Analysis REGION & EDGE BASED SEGMENTATION Today We go through sections 10.1, 10.2.7 (briefly), 10.4, 10.5, 10.6.1 We cover the following segmentation approaches: 1. Edge-based segmentation

More information

MOUNTAIN VIEW SCHOOL DISTRICT

MOUNTAIN VIEW SCHOOL DISTRICT MOUNTAIN VIEW SCHOOL DISTRICT FIRST GRADE MATH 1.OA.1 Represent and solve problems involving addition and subtraction. Use addition and subtraction within 20 to solve word problems involving situations

More information

Section 7.2 Volume: The Disk Method

Section 7.2 Volume: The Disk Method Section 7. Volume: The Disk Method White Board Challenge Find the volume of the following cylinder: No Calculator 6 ft 1 ft V 3 1 108 339.9 ft 3 White Board Challenge Calculate the volume V of the solid

More information

OBJECT detection in general has many applications

OBJECT detection in general has many applications 1 Implementing Rectangle Detection using Windowed Hough Transform Akhil Singh, Music Engineering, University of Miami Abstract This paper implements Jung and Schramm s method to use Hough Transform for

More information

An Automated Image-based Method for Multi-Leaf Collimator Positioning Verification in Intensity Modulated Radiation Therapy

An Automated Image-based Method for Multi-Leaf Collimator Positioning Verification in Intensity Modulated Radiation Therapy An Automated Image-based Method for Multi-Leaf Collimator Positioning Verification in Intensity Modulated Radiation Therapy Chenyang Xu 1, Siemens Corporate Research, Inc., Princeton, NJ, USA Xiaolei Huang,

More information

(Refer Slide Time: 00:03:51)

(Refer Slide Time: 00:03:51) Computer Graphics Prof. Sukhendu Das Dept. of Computer Science and Engineering Indian Institute of Technology, Madras Lecture 17 Scan Converting Lines, Circles and Ellipses Hello and welcome everybody

More information

Math 6, Unit 8 Notes: Geometric Relationships

Math 6, Unit 8 Notes: Geometric Relationships Math 6, Unit 8 Notes: Geometric Relationships Points, Lines and Planes; Line Segments and Rays As we begin any new topic, we have to familiarize ourselves with the language and notation to be successful.

More information

HIGH ORDER QUESTION STEMS STUDENT SCALE QUESTIONS FCAT ITEM SPECIFICATION

HIGH ORDER QUESTION STEMS STUDENT SCALE QUESTIONS FCAT ITEM SPECIFICATION Benchmark Support Task Cards MA.3.A.1.1 BENCHMARK: MA.3.A.1.1 Model multiplication and division, including problems presented in context: repeated addition, multiplicative comparison, array, how many combinations,

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

New York State Testing Program Mathematics Test

New York State Testing Program Mathematics Test New York State Testing Program Mathematics Test 2013 Turnkey Training Grade 6 Extended-response (3-point) Sample Question Guide Set Page 0 8 2 A closed box in the shape of a rectangular prism has a length

More information

ECEN 447 Digital Image Processing

ECEN 447 Digital Image Processing ECEN 447 Digital Image Processing Lecture 7: Mathematical Morphology Ulisses Braga-Neto ECE Department Texas A&M University Basics of Mathematical Morphology Mathematical Morphology (MM) is a discipline

More information

Grade 4. Massachusetts Curriculum Framework for Mathematics 42

Grade 4. Massachusetts Curriculum Framework for Mathematics 42 Grade 4 Introduction In grade 4, instructional time should focus on three critical areas: (1) developing understanding and fluency with multi-digit multiplication, and developing understanding of dividing

More information

Lab - Introduction to Finite Element Methods and MATLAB s PDEtoolbox

Lab - Introduction to Finite Element Methods and MATLAB s PDEtoolbox Scientific Computing III 1 (15) Institutionen för informationsteknologi Beräkningsvetenskap Besöksadress: ITC hus 2, Polacksbacken Lägerhyddsvägen 2 Postadress: Box 337 751 05 Uppsala Telefon: 018 471

More information

6 Mathematics Curriculum

6 Mathematics Curriculum New York State Common Core 6 Mathematics Curriculum GRADE GRADE 6 MODULE 5 Table of Contents 1 Area, Surface Area, and Volume Problems... 3 Topic A: Area of Triangles, Quadrilaterals, and Polygons (6.G.A.1)...

More information

Adobe Flash CS3 Reference Flash CS3 Application Window

Adobe Flash CS3 Reference Flash CS3 Application Window Adobe Flash CS3 Reference Flash CS3 Application Window When you load up Flash CS3 and choose to create a new Flash document, the application window should look something like the screenshot below. Layers

More information

Application of fuzzy set theory in image analysis. Nataša Sladoje Centre for Image Analysis

Application of fuzzy set theory in image analysis. Nataša Sladoje Centre for Image Analysis Application of fuzzy set theory in image analysis Nataša Sladoje Centre for Image Analysis Our topics for today Crisp vs fuzzy Fuzzy sets and fuzzy membership functions Fuzzy set operators Approximate

More information

Unit 3, Activity 1, Vocabulary Self-Awareness Chart

Unit 3, Activity 1, Vocabulary Self-Awareness Chart Unit 3, Activity, Vocabulary Self-Awareness Chart Vocabulary Self-Awareness Chart Word + - Example Definition Relation Function Domain Range Graph Vertical line test F(x) input output independent dependent

More information

UNIVERSITY OF OSLO. Faculty of Mathematics and Natural Sciences

UNIVERSITY OF OSLO. Faculty of Mathematics and Natural Sciences UNIVERSITY OF OSLO Faculty of Mathematics and Natural Sciences Exam: INF 43 / INF 935 Digital image analysis Date: Thursday December 4, 4 Exam hours: 4.3-8.3 (4 hours) Number of pages: 6 pages Enclosures:

More information

Renyan Ge and David A. Clausi

Renyan Ge and David A. Clausi MORPHOLOGICAL SKELETON ALGORITHM FOR PDP PRODUCTION LINE INSPECTION Renyan Ge and David A. Clausi Systems Design Engineering University of Waterloo, 200 University Avenue West Waterloo, Ontario, Canada

More information

[ ] Review. Edges and Binary Images. Edge detection. Derivative of Gaussian filter. Image gradient. Tuesday, Sept 16

[ ] Review. Edges and Binary Images. Edge detection. Derivative of Gaussian filter. Image gradient. Tuesday, Sept 16 Review Edges and Binary Images Tuesday, Sept 6 Thought question: how could we compute a temporal gradient from video data? What filter is likely to have produced this image output? original filtered output

More information

(Refer Slide Time: 00:02:00)

(Refer Slide Time: 00:02:00) Computer Graphics Prof. Sukhendu Das Dept. of Computer Science and Engineering Indian Institute of Technology, Madras Lecture - 18 Polyfill - Scan Conversion of a Polygon Today we will discuss the concepts

More information

Course Number: Course Title: Geometry

Course Number: Course Title: Geometry Course Number: 1206310 Course Title: Geometry RELATED GLOSSARY TERM DEFINITIONS (89) Altitude The perpendicular distance from the top of a geometric figure to its opposite side. Angle Two rays or two line

More information