DIGITAL IMAGE PROCESSING - SCUT · 2019-03-04 · Digital image processing –perform digital signal processing operations on digital images (by means of digital computers.) MAPPING

Xiangyu Yu

School of Electronic and Information Engineering,

South China University of Technology, P. R. China

[email protected]

DIGITAL IMAGE PROCESSING

ABOUT THIS COURSE(1)

3/4/2019 DIGITAL IMAGE PROCESSING 2

32 Class hours

Date and Time:Week 2-9 Monday 14:30-16:10 330102

Week 2-9 Tuesday 16:20-18:00 330202

No Final Examination!

Course Grading20% Presentation(about 15mins)

30% Programming Assignments(most in python, some in Matlab and C)

50% Project in group(3-5 person a group)

Slides in English lecture in Mandarin

Slide and resource are available on www2.scut.edu.cn/misip/

ABOUT THIS COURSE(2)


Goals of this courseIntroductory course: basic concepts, classical methods, fundamental theorems

Getting acquainted with basic properties of images

Getting acquainted with various representations of image data

Acquire fundamental knowledge in processing and analysis digital images

Prerequisites

Signals and systems

ABOUT THE LECTURER


学习经历1996-2000 武汉大学通信工程专业

2000-2006 武汉大学通信与信息系统专业

工作经历2006-今华南理工大学电子与信息学院（2013年9月晋升副教授）

2016.12-2017.11 英国华威大学访问学者

讲授课程包括2008-2013 2015级《移动通信》

2004级《信号与系统》

2004级交通学院《通信技术基础》

2006-2010级及2007-2011年辅修班《数字通信原理》

2006级计算机学院/2011-2013 2016级电信学院《通信原理》

2010级电信学院/机械学院《数字电子技术》

2006-2007级硕士研究生《接入网技术》

2007年南校区通选课《通信概论》

2013-2015、2017级在职工程硕士《移动通信新进展》

2016-2018级留学生硕士班《Principle of Modern Communications 》

TEXTBOOK


Gonzalez, R. C. and Woods, R. E., "Digital Image Processing", Prentice Hall, 3rd Ed. , 2008

REFERENCE BOOK(1)


Kenneth R. Castelman "Digital Image Processing", Prentice Hall

REFERENCE BOOK(2)


Mark S. Nixon and Alberto S. Aguado, “Feature Extraction and Image Processing”, 2012.

REFERENCE BOOK(3)


Alan C. Bovik, “Handbook of Image and Video Processing”, 2005.

REFERENCE BOOK(4)


John C. Russ, “The Image Processing Handbook”, 7th Edition, CRC Press., 2017.

REFERENCE BOOK(5)


Anil K. Jain, “Fundamentals of Digital Image Processing”, Prentice-Hall, Inc., 1989.

http://images.google.co.il/imgres?imgurl=http://vig-fp.prenhall.com/bigcovers/0133361659.jpg&imgrefurl=http://www.pearsonhighered.com/educator/product/Fundamentals-of-Digital-Image-Processing/9780133361650.page&usg=__l2EoNhXUpxAntUp8ajlVc20qK5g=&h=648&w=464&sz=76&hl=en&start=1&sig2=QmTocY_ZeeBnLwAUC2Ujdw&um=1&itbs=1&tbnid=kBTJEhhwDDZMQM:&tbnh=137&tbnw=98&prev=/images?q=Fundamentals+of+Digital+Image+Processing++Jain&um=1&hl=en&sa=N&rlz=1T4GGHP_enIL366&tbs=isch:1&ei=SD-FS9eVMcye4QbRmZjPAQ

http://images.google.co.il/imgres?imgurl=http://vig-fp.prenhall.com/bigcovers/0133361659.jpg&imgrefurl=http://www.pearsonhighered.com/educator/product/Fundamentals-of-Digital-Image-Processing/9780133361650.page&usg=__l2EoNhXUpxAntUp8ajlVc20qK5g=&h=648&w=464&sz=76&hl=en&start=1&sig2=QmTocY_ZeeBnLwAUC2Ujdw&um=1&itbs=1&tbnid=kBTJEhhwDDZMQM:&tbnh=137&tbnw=98&prev=/images?q=Fundamentals+of+Digital+Image+Processing++Jain&um=1&hl=en&sa=N&rlz=1T4GGHP_enIL366&tbs=isch:1&ei=SD-FS9eVMcye4QbRmZjPAQ

REFERENCE BOOK(6)


William K. Pratt, “Digital Image Processing”, 2nd Edition, Wiley & Sons, Inc., 1991.

REFERENCE BOOK(7)


Milan Sonka · Roger Boyle · Vaclav Hlavac, “Image Processing: Analysis and Machine Vision”, 3nd Edition, Chapman & Hall., 1999.

REFERENCE BOOK(8)


章毓晋图像工程(上册) 图像处理(第三版) 清华大学出版社 2012.

REFERENCE BOOK(9)


Gonzalez, Woods, and Eddins, “Digital Image Processing Using MATLAB”, 2nd Edition, 2009.

REFERENCE BOOK(10)


Alasdair Mcandrew, “An Introduction to Digital Image Processing with Matlab”, 2004.

REFERENCE BOOK(11)


左飞. 数字图像处理：原理与实践（MATLAB版）电子工业出版社 2014.

CONTENTS OF THIS COURSE


L1 Introduction(C1)

L2 Digital Image Fundamentals(C2)

L3 Intensity Transformations(3.1-3.2)

L4 Histogram(3.3)

L5 Spatial Filtering and Edge Detection(3.4-3.8+10.2)

L6 Filtering in Frequency domain(C4)

L7 Image Restoration and Reconstruction(C5)

L8 Image Segmentation(10.3 10.4 10.6)

L9 Morphological Image Processing(C9 10.5)

L10 Representation and Description(C11)

L11 Wavelets and Multiresoluton Processing(C7)

L12 Color Image Processing(C6)

L13 Image Compression(C8)

ABOUT THE PROGRAMMING HOMEWORK


Most In Jupyter Notebook

A few in Matlab or C

Send your homework to [email protected]

https://cviptools.siue.edu/

mailto:[email protected]

ABOUT THE PROJECT


3-5 person a group

Evaluation by you!

Presentation time：Later June or Early July

PROJECT #1

这学期的数字图像处理课，老师不提供课件给学生（不是真的！）。为了课后复习，班上的同学都用手机拍摄每张幻灯片，但有的同学有遗漏，有的同学拍得不清晰（手抖动，对焦错误），有的同学拍摄的图像被前面同学的头遮挡，此外还有光照等问题。班上的A同学决定现学现用，把同学手机拍的幻灯片联合起来形成一组较为完整且版本较清晰的幻灯片供复习。

要求

将一批图像放入文件夹中，软件自动生成课件PDF（由于手机文件通常以拍摄时间命名，所以不同手机图片的先后顺序容易确定）

图片库由学生自建

涉及知识

图像配准、图像融合、图像拼接、图像去模糊等

更高级处理（可选）

对于图片中不够清晰的文字，可以用打印体替换。其他可以自己发挥。


PROJECT #2

毕业季到了，B同学拍了很多毕业照，但发现照片里太多无关的人。Ta想利用图像处理课上学到的知识对这批照片进行一些处理尽可能消除图片中的无关人且让图像看上去较真实。

要求

图像库学生自建

涉及知识

图像背景提取，图像平均等



PROJECT #3

小C很喜欢旅游，并且有一群志同道合的驴友。每次旅行回来，Ta都会将所有驴友拍摄的照片收集并整理，然后在马蜂窝撰写游记。把每个人拍的照片看一遍很费时，Ta想利用图像处理课程学到的知识进行自动图像筛选。

要求

1. 对于同一场景不同人拍摄的图像，系统自动删除拍得不好的（主要是模糊，也包括比如有些建筑或人没拍到顶部）

2.对于少量场景（如一幢建筑，D拍到顶部但没拍到底部，E反之），对于多幅这样的图像进行自动拼接。

3.对于某些场景只有唯一一幅图片但质量不够好（如模糊），尝试提升图像质量。

图片库由学生自建

涉及知识

图像配准、图像拼接、图像去模糊等



PROJECT #4

无人机中目标计数

要求

1. 统计无人机拍摄的图片中，统一类型目标的数量

涉及知识

图像边缘检测、角点检测等



PROJECT #5 AND MORE

Proposed by you


LECTURE 1INTRODUCTION

“One picture is worth more than ten thousand words”

Anonymous


CONTENTS


What is a digital image?

What is digital image processing?

History of digital image processing

State of the art examples of digital image processing

Key stages in digital image processing

Image processing problems

Applications of image processing

IMAGE AND IMAGE PROCESSING


Image – A two-dimensional signal that can be observed by human visual system

Digital image – Representation of images by sampling in time and space.

Digital image processing – perform digital signal processing operations on digital images (by means of digital computers.)

MAPPING 3D REAL WORLD -> 2D IMAGE

2D intensity image = perspective projection of the 3D scene

information lost - transformation is not one-to-one

geometric problem - information recovery

understanding brightness info


THE VISUAL SCIENCES


Computer

Vision

Rendering

Image

Image

Processing

Model

3D Object

Geometric

Modeling

DIGITAL IMAGE

A digital image is a representation of a two-dimensional image as a finite set of digital values, called picture elements or pixels

Imag

es ta

ken fro

m G

onzale

z &

Woods,

Dig

ital Im

age P

rocessin

g (

2002)



Digital image = a multidimensional

array of numbers (such as intensity image)

or vectors (such as color image)

Each component in the image

called pixel associates with

the pixel value (a single number in

the case of intensity images or a

vector in the case of color images).

39871532

22132515

372669

28161010

39656554

42475421

67965432

43567065

99876532

92438585

67969060

78567099

WHY DIGITAL?

Computers store data and understand data in numerical form. We can say that a digital image is a numerical representation of a “picture” –a set of numbers interpreted by the computer which creates a visual representation that is understood by humans.


255 255 199143 97 18732 12 3423 22 11

244 198 179123 94 19532 43 5213 32 11

253 217 23468 185 9713 12 2711 14 26

DIGITIZATION IMPLIES APPROXIMATION

Pixel values typically represent gray levels, colours, heights, opacities etc

Remember digitization implies that a digital image is an approximationof a real scene

1 pixel

Ima

ges ta

ken fro

m G

onzale

z &

Woods,

Dig

ital Im

age P

rocessin

g (

2002)


ANALOG VS DIGITAL IMAGE PROCESSING


WHY DIP?

One picture worth 1000 words!

Support visual communication

Facilitate inspection, diagnosis of complex systems

Human body

Manufacturing

Entertainment

Keep record, history

Managing multimedia information

Security,

monitoring,

watermarking, etc


IMAGE PROCESSING FIELDS

Computer Graphics: The creation of images

Image Processing: Enhancement or other manipulation of the image

Computer Vision: Analysis of the image content


IMAGE PROCESSING V.S. COMPUTER VISION

Image Processing

Computer Vision

Low Level

High Level

Acquisition, representation,

compression, transmission

image enhancement

edge/feature extraction

Pattern matching

image "understanding“

(Recognition, 3D)

Image analysis - Image processing - Computer vision3/4/2019 DIGITAL IMAGE PROCESSING

WHAT IS DIP? (CONT…)

The continuum from image processing to computer vision can be broken up into low-, mid- and high-level processes

Low Level Process

Input: Image

Output: Image

Examples: Noise

removal, image

sharpening

Mid Level Process

Input: Image

Output:

Attributes(Features)

Examples: Object

recognition,

segmentation

High Level Process

Input:

Attributes(Features)

Output:

Understanding(Analysi

s)

Examples: Scene

understanding,

autonomous navigation

In this course we will

stop here3/4/2019 DIGITAL IMAGE PROCESSING 41

IMAGE PROCESSING FIELDS

Input / Output Image Description

Image Image Processing Computer Vision

Description Computer Graphics AI

Sometimes, Image Processing is defined as “a

discipline in which both the input and output of a

process are images

But, according to this classification, trivial tasks of

computing the average intensity of an image would not

be considered an image processing operation


COMPUTERIZED PROCESSES TYPES

Low-Level Processes:

Input and output are images

Tasks: Primitive operations, such as, image processing to reduce noise, contrast enhancement and image sharpening


LOW LEVEL DIGITAL IMAGE PROCESSING

Low level computer vision ~ digital image processing

Image Acquisition

image captured by a sensor (TV camera) and digitized

Preprocessing

suppresses noise (image pre-processing)

enhances some object features - relevant to understanding the image

edge extraction, smoothing, thresholding etc.

Image segmentation

separate objects from the image background

colour segmentation, region growing, edge linking etc

Object description and classification

after segmentation


LOW-LEVEL


blurring

sharpening


Mid-Level Processes:

Inputs, generally, are images. Outputs are attributes extracted from those images (edges, contours, identity of individual objects)

Tasks:

Segmentation (partitioning an image into regions or objects)

Description of those objects to reduce them to a form suitable for computer processing

Classifications (recognition) of objects


MID-LEVEL


K-means

clustering

original color image regions of homogeneous color

(followed by

connected

component

analysis)

data

structure


High-Level Processes: Image analysis and computer vision


KEY STAGES IN DIGITAL IMAGE PROCESSING

Image

Acquisition

Image

Restoration

Image

Compression

Morphological

Processing

Object

Recognition

Image

Enhancement

Segmentation

Real life sceneColour Image

Processing

Representation

& Description

Image

Modelling

(Transforms)


IMAGE ACQUISITION

Image

Acquisition

Image

Restoration

Image

Compression

Morphological

Processing

Object

Recognition

Image

Enhancement

Segmentation


Processing

Representation

& Description

Image

Modelling

(Transforms)


FUNDAMENTAL STEPS IN DIP: (DESCRIPTION)

Step 1: Image Acquisition

The image is captured by a sensor (eg. Camera), and digitized if the output of the camera or sensor is not already in digital form, using analogue-to-digital convertor


IMAGE MODELLING-IMAGE TRANSFORMS (PART 1)

Image

Acquisition

Image

Restoration

Image

Compression

Morphological

Processing

Object

Recognition

Image

Enhancement

Segmentation


Processing

Representation

& Description

Image

Modelling

(Transforms)

Original Image Fourier Transform

Amplitude Phase


http://www.dai.ed.ac.uk/HIPR2/images/cln1.gif

http://www.dai.ed.ac.uk/HIPR2/images/cln1.gif

http://www.dai.ed.ac.uk/HIPR2/images/cln1fur2.gif




IMAGE ENHANCEMENT (PART 2)

Image

Acquisition

Image

Restoration

Image

Compression

Morphological

Processing

Object

Recognition

Image

Enhancement

Segmentation


Processing

Representation

& Description

Image

Modelling

(Transforms)



Step 2: Image Enhancement

The process of manipulating an image so that the result is more suitable than the original for specific applications.

The idea behind enhancement techniques is to bring out details that are hidden, or simple to highlight certain features of interest in an image.


EXAMPLES: IMAGE ENHANCEMENT

One of the most common uses of DIP techniques: improve quality, remove noise etc

Imag

es ta

ken fro

m G

onzale

z &

Woods,

Dig

ital Im

age P

rocessin

g (

2002)


IMAGE RESTORATION (PART 3)

Image

Acquisition

Image

Restoration

Image

Compression

Morphological

Processing

Object

Recognition

Image

Enhancement

Segmentation


Processing

Representation

& Description

Image

Modelling

(Transforms)



Step 3: Image Restoration

- Improving the appearance of an image

- Tend to be mathematical or probabilistic models. Enhancement, on the other hand, is based on human subjective preferences regarding what constitutes a “good” enhancement result.


IMAGE RESTORATION


Distorted Image Restored Image

DISTORTION DUE TO CAMERA MISFOCUS


Original image Distorted image

DISTORTION DUE TO CAMERA MISFOCUS

Camera lens


DISTORTION DUE TO MOTION

Camera lens


DISTORTION DUE TO RANDOM NOISE

Distorted imageOriginal image


IMAGE COMPRESSION (PART 4)

Image

Acquisition

Image

Restoration

Image

Compression

Morphological

Processing

Object

Recognition

Image

Enhancement

Segmentation


Processing

Representation

& Description

Image

Modelling

(Transforms)



Step 6: Compression

Techniques for reducing the storage required to save an image or the bandwidth required to transmit it.


MORPHOLOGICAL PROCESSING

Image

Acquisition

Image

Restoration

Image

Compression

Morphological

Processing

Object

Recognition

Image

Enhancement

Segmentation


Processing

Representation

& Description

Image

Modelling

(Transforms)



Step 7: Morphological Processing

Tools for extracting image components that are useful in the representation and description of shape.

In this step, there would be a transition from processes that output images, to processes that output image attributes.


SEGMENTATION


Image

Acquisition

Image

Restoration

Image

Compression

Morphological

Processing

Object

Recognition

Image

Enhancement

Segmentation


Processing

Representation

& Description

Image

Modelling

(Transforms)


Step 8: Image Segmentation

Segmentation procedures partition an image into its constituent parts or objects.

Important Tip: The more accurate the segmentation, the more likely recognition is to succeed.


OBJECT RECOGNITION

Image

Acquisition

Image

Restoration

Image

Compression

Morphological

Processing

Object

Recognition

Image

Enhancement

Segmentation


Processing

Representation

& Description

Image

Modelling

(Transforms)


REPRESENTATION AND DESCRIPTION

Image

Acquisition

Image

Restoration

Image

Compression

Morphological

Processing

Object

Recognition

Image

Enhancement

Segmentation


Processing

Representation

& Description

Image

Modelling

(Transforms)



Step 9: Representation and Description

-Representation: Make a decision whether the data should be represented as a boundary or as a complete region. It is almost always follows the output of a segmentation stage.

-Boundary Representation: Focus on external shape characteristics, such as corners and inflections (انحناءات)

-Region Representation: Focus on internal properties, such as texture or skeleton (هيكلية) shape



Step 9: Representation and Description

-Choosing a representation is only part of the solution for transforming raw data into a form suitable for subsequent computer processing (mainly recognition)

- Description: also called, feature selection, deals with extracting attributes that result in some information of interest.



Step 9: Recognition and Interpretation

Recognition: the process that assigns label to an object based on the information provided by its description.


COLOUR IMAGE PROCESSING

Image

Acquisition

Image

Restoration

Image

Compression

Morphological

Processing

Object

Recognition

Image

Enhancement

Segmentation


Processing

Representation

& Description

Image

Modelling

(Transforms)



Step 4: Colour Image Processing

Use the colour of the image to extract features of interest in an image


COMPONENTS OF AN IMAGE PROCESSING SYSTEM Network

Image displays Computer Mass storage

HardcopySpecialized image

processing hardware

Image processing

software

Image sensorsProblem Domain

Typical general-

purpose DIP

system

G3E-P.513/4/2019 DIGITAL IMAGE PROCESSING G3C-P.16

COMPONENTS OF AN IMAGE PROCESSING SYSTEM

1. Image Sensors

Two elements are required to acquire digital images. The first isthe physical device that is sensitive to the energy radiated by theobject we wish to image (Sensor). The second, called a digitizer, isa device for converting the output of the physical sensing deviceinto digital form.


G3E-P.50-51G3C-P.16


2. Specialized Image Processing Hardware

Usually consists of the digitizer, mentioned before, plus

hardware that performs other primitive operations, suchas an arithmetic logic unit (ALU), which performsarithmetic and logical operations in parallel on entireimages.

This type of hardware sometimes is called a front-endsubsystem, and its most distinguishing characteristic isspeed. In other words, this unit performs functions thatrequire fast data throughputs that the typical maincomputer cannot handle.


G3E-P.51G3C-P.16


3. Computer

The computer in an image processing system is ageneral-purpose computer and can range from a PC to asupercomputer. In dedicated applications, sometimesspecially designed computers are used to achieve arequired level of performance.


G3E-P.51G3C-P.16


4. Image Processing Software

Software for image processing consists of specializedmodules that perform specific tasks. A well-designedpackage also includes the capability for the user to writecode that, as a minimum, utilizes the specialized modules.


G3E-P.51-52G3C-P.16

IMAGE PROCESSING SOFTWARE



5. Mass Storage Capability

Mass storage capability is a must in a image processingapplications. And image of sized 1024 × 1024 pixelsrequires one megabyte of storage space if the image isnot compressed.

Digital storage for image processing applications fallsinto three principal categories:

1. Short-term storage for use during processing.

2. on line storage for relatively fast recall

3. Archival storage, characterized by infrequent access


G3E-P.52G3C-P.16


5. Mass Storage Capability

One method of providing short-term storage is computer memory.Another is by specialized boards, called frame buffers, that storeone or more images and can be accessed rapidly.

The on-line storage method, allows virtually instantaneous imagezoom, as well as scroll (vertical shifts) and pan (horizontal shifts).On-line storage generally takes the form of magnetic disks andoptical-media storage. The key factor characterizing on-linestorage is frequent access to the stored data.

Finally, archival storage is characterized by massive storagerequirements but infrequent need for access.



6. Image Displays

The displays in use today are mainly color (preferably flat screen) TV monitors. Monitors are driven by the outputs of the image and graphics display cards that are an integral part of a computer system.


G3E-P.52G3C-P.16


7. Hardcopy devices

Used for recording images, include laser printers, film cameras, heat-sensitive devices, inkjet units and digital units, such as optical and CD-Rom disks.


G3E-P.52G3C-P.16


8. Networking

Is almost a default function in any computersystem, in use today. Because of the largeamount of data inherent in image processingapplications the key consideration in imagetransmission is bandwidth.

In dedicated networks, this typically is not aproblem, but communications with remote sitesvia the internet are not always as efficient.


G3E-P.52G3C-P.17

THE FIRST PHOTOGRAPH

The First Photograph, or more specifically, the earliest known surviving photograph made in a camera, was taken by Joseph NicéphoreNiépce in 1826 or 1827. The image depicts the view from an upstairs window at Niépce's estate, Le Gras, in the Burgundy region of France. Learn more about the First Photograph through the links below.

First successful commercial photograph due to Eastman in late 19th

3/4/2019 DIGITAL IMAGE PROCESSING 87the original plate manually enhanced version

Ima

ges taken fro

m W

ikip

edia

.org

PRESENTATION ASSIGMENT#1

Talking about the history of photography


Early 1920s: One of the first applications of digital imaging was in the newspaper industry

The Bartlane cable picture transmission service

Images were transferred by submarine cable between London and New York

Pictures were coded for cable transfer and reconstructed at the receiving end on a telegraph printer

Important to reduce transfer time.

Imag

es ta

ken fro

m d

igic

am

his

tory

.com

& a

tlantic-c

able

.com

HISTORY OF DIGITAL IMAGE PROCESSING

G3E-P.253/4/2019 DIGITAL IMAGE PROCESSING

HISTORY OF DIGITAL IMAGE PROCESSING


Imag

es ta

ken fro

m G

onzale

z &

Woods,

Dig

ital Im

age P

rocessin

g (

2002)

FIGURE A digital picture produced in 1921

from a coded tape by a telegraph printer

with special type faces. (McFarlane.†)

FIGURE A digital picture made in 1922 from a

tape punched after the signals had crossed the

Atlantic twice. Some errors are visible.

(McFarlane.)

Better quality

G3E-P.25-26

HISTORY OF DIP (CONT…)

Mid to late 1920s: Improvements to the Bartlane system resulted in higher quality images

New reproduction processes based on photographic techniques

Increased number of tones in reproduced images

Early 15 tone digital

image

Imag

es ta

ken fro

m G

onzale

z &

Woods,

Dig

ital Im

age P

rocessin

g (

2002)

Digital computers: 1940

1st computer able to do digital image

manipulations: early 1960

Unretouched cable picture of Generals Pershing

and Foch, transmitted in 1929 from London to

New York by 15-tone equipment. (McFarlane.) G3E-P.26

3/4/2019 DIGITAL IMAGE PROCESSING


1960s: Improvements in computing technology and the onset of the space race led to a surge of work in digital image processing

1964: Computers used to improve the quality of images of the moon taken by the Ranger 7 probe

Such techniques were used in other space missions including the Apollo landings

Imag

es ta

ken fro

m G

onzale

z &

Woods,

Dig

ital Im

age P

rocessin

g (

2002)

From computers, meaningful image processing tasks appeared.



Ranger 7

A picture of the moon taken by

the Ranger 7 on 31 July 1964 at

13:09 UT about 17 minutes

before impact

Ima

ges ta

ken fro

m n

asa.g

ov &

Wik

ipedia

.org

Ranger 7 cameras system


1970s: Digital image processing begins to be used in medical applications

1979: Sir Godfrey N. Hounsfield & Prof. Allan M. Cormack share the Nobel Prize in medicine for the invention of tomography, the technology behind Computerised Axial Tomography (CAT) scans

Typical head slice CAT

image

Ima

ges taken fro

m G

onzale

z &

Woods,

Dig

ital Im

age P

rocessin

g (

2002)


MRI



1980s - Today: The use of digital image processing techniques has exploded and they are now used for all kinds of tasks in all kinds of areas

Image enhancement/restoration

Artistic effects

Medical visualisation

Industrial inspection

Law enforcement

Human computer interfaces


PRESENTATION ASSIGMENT#2

Deep learning in image processing. Maybe more than one topic.


APPLICATIONS OF DIGITAL IMAGE PROCESSING?

… virtually, everywhere!

• Industry: inspection/sorting; manufacturing (robot vision)

• Environment: strategic surveillance (hydro-dams, forests, forestfires, mine galleries) by surveillance cameras, autonomousrobots

• Medicine: medical imaging (ultrasound, MRI, CT, visible)

• Culture: digital libraries; cultural heritage preservation (storage,restoration, analysis – indexing)

• Television: broadcasting, video editing, efficient storage

• Education & tourism: multi-modal, intelligent human-computerinterfaces, with emotion recognition components

• Security/authentication (iris recognition, signature verification)

… etc…


APPLICATIONS – IMAGING MODALITIES

Imag

es ta

ken fro

m G

onzale

z &

Woods,

Dig

ital Im

age P

rocessin

g (

2002)

Principal energy source for images today: electromagnetic

energy spectrum.

Electromagnetic energy spectrum

G3E-P.293/4/2019 DIGITAL IMAGE PROCESSING G3C-P.5

GAMMA-RAY IMAGING

Imag

es ta

ken fro

m G

onzale

z &

Woods,

Dig

ital Im

age P

rocessin

g (

2008)

Examples of gamma-ray imaging. (a) Bone scan.

(b) PET image. (c) Cygnus Loop. (d) Gamma

radiation (bright spot) from a reactor valve. G3E-P.30

Gamma rays:

Nuclear medicine

(injection of

radioactive tracer)

Astronomical

observations

(object generate

gamma rays)

3/4/2019 DIGITAL IMAGE PROCESSING G3C-P.5

PET

PET=Positron Emission Tomography

imaging at molecular level


X-RAY IMAGING

G3E-P.32

Figure X-Ray images. (a) Chest X-ray. (b)

Aortic angiogram. (c) Head CT. (d) Circuit

boards. (e) Cygnus Loop.

Imag

es ta

ken fro

m G

onzale

z &

Woods,

Dig

ital Im

age P

rocessin

g (

2008)

X-rays (the oldest radiation-type imaging)

-Discovered in 1895 by German

physicist William Roentgen

(Nobel prize in physics, 1901)

-used in medicine/industry/astronomy

X-ray tube (catode/anode, controlled by

voltage), emitting ray, absorbption by

object, rest captured onto a film,

digitised.

C.A.T. (Computerized Axial Tomography)

uses X-rays.


X-RAY IMAGING

Imag

es ta

ken fro

m G

onzale

z &

Woods,

Dig

ital Im

age P

rocessin

g (

2008)

X-ray of kneeCopyright: Radiology Centennial, Inc.

An x-ray picture

(radiograph) taken by

Röntgen of Albert von

Kölliker's hand at a

public lecture on 23

January 1896


http://en.wikipedia.org/wiki/Albert_von_K%C3%B6lliker

ULTRAVIOLET BAND

microscopy (fluorescence)

the excited electron jumps to another energy level emitting light as a low-energy photon in the red region

lasers

biological imaging

astronomical imaging

industrial inspections


A fluorescent tracer

is bind to a

molecular target

IMAGING IN THE ULTRAVIOLET BAND

G3E-P.34Imag

es ta

ken fro

m G

onzale

z &

Woods,

Dig

ital Im

age P

rocessin

g (

2008)

Examples of ultraviolet imaging. (a) Normal

corn. (b) Corn infected by smut. (c) Cygnus Loop.3/4/2019 DIGITAL IMAGE PROCESSING G3C-P.7

VISIBLE AND INFRARED BAND

the most familiar to us….

light microscopy

infrared: remote sensing, weather prediction,

satellite sensing/ night vision


IMAGING IN THE VISIBLE AND INFRARED BANDS

G3E-P.35

Figure Light microscopy images.

(a) Taxol (anticancer agent),

magnified 250X, (b)

Cholesterol, 40X (c)

microprocessor 60X. (d) Nickel

oxide thin film, 600 X. (e)

Surface of audio CD 1750 X. (f)

Organic superconductor 450 X. Imag

es ta

ken fro

m G

onzale

z &

Woods,

Dig

ital Im

age P

rocessin

g (

2008)


REMOTE SENSING


G3E-P.36G3C-P.8

APPLICATIONS: GIS

Geographic Information Systems

Satellite imagery

Terrain classification (LANDSAT)

Meteorology (NOAA)

LANDSAT satellite images of the Washington,

D.C. area. The numbers refer to the thematic

bands in Table 1.1. G3E-P.36Imag

es ta

ken fro

m G

onzale

z &

Woods,

Dig

ital Im

age P

rocessin

g (

2008)



Mount Everest

Mount Everest is the highest mountain on Earth, rising 29,029 feet above sea level. It is located on the border of Nepal and Tibet in the Himalayan mountain range. In Tibet the mountain is known as Chomolunga and in Nepal it is called Sagarmatha.

This image of Mount Everest was taken from the

International Space Station on November 26, 2003.

In this image you can see Mount Everest covered in white snow with Lhotse, the fourth highest mountain on Earth connected via the South Col — the saddle point between the two peaks. Vegetation appears green and rock and soil appear brown in the image.This natural color Landsat 5 image was collected on June 11, 2005. It was created using bands 3, 2 and 1. Mount Everest is found on Landsat WRS-2 Path 140 Row 41.

Nasa/Landsat


Mono Lake, CaliforniaNasa/Landsat

This Landsat 7 image of Mono Lake was acquired on July 27,

2000. This image is a false-color composite made from the

mid-infrared, near-infrared, and green spectral channels of the

Landsat 7 ETM+ sensor – it also includes the panchromatic

15-meter band for spatial sharpening purposes. In this image,

the waters of Mono Lake appear a bluish-black and

vegetation appears bright green. You will notice the

vegetation to the west of the lake and following the tributaries

that enter the lake.

Weather Observation, visible and infrared bands

G3E-P.37

Satellite image of Hurricane Katrina taken on

August 29, 2005.

Imag

es ta

ken fro

m G

onzale

z &

Woods,

Dig

ital Im

age P

rocessin

g (

2008)


TYPHOON MANGKHUT


Interpretation of aerial photography is a problem domain in both

computer vision and registration.

INTERPRETATION OF AERIAL PHOTOGRAPHY


SATELLITE IMAGERY


Volcanos in Russia and Alaska

REMOTE SENSING OF OUR COUNTRY

Tiangong 1

Tiangong 2

GF1


Imag

es ta

ken fro

m s

ina

.com

APPLICATIONS: GIS (CONT…)

Night-Time Lights of the World data set

(infra red)

Global inventory of human settlement

Not hard to imagine the kind of analysis that might be done using this data

Infrared satellite images of the Americas. The

small shaded map is provided for reference.

Infrared imaging

G3E-P.38Imag

es ta

ken fro

m G

onzale

z &

Woods,

Dig

ital Im

age P

rocessin

g (

2008)



Infrared satellite images of the remaining populated parts of the world. The small shaded map is provided for reference.

Imag

es ta

ken fro

m G

onzale

z &

Woods,

Dig

ital Im

age P

rocessin

g (

2008)

G3E-P.39G3C-P.9

ASTRONOMICAL IMAGES


APPLICATIONS: THE HUBBLE TELESCOPE

Launched in 1990 the Hubble telescope can take images of very distant objects

However, an incorrect mirror made many of Hubble’s images useless

Image processing techniques were used to fix this


http://en.wikipedia.org/wiki/Image:Hst_sts82.jpg

http://en.wikipedia.org/wiki/Image:Hst_sts82.jpg

INDUSTRIAL INSPECTION(INDUSTRIAL VISION SYSTEMS)


APPLICATIONS: INDUSTRIAL INSPECTIONHuman operators are expensive, slow andunreliable

Make machines do thejob instead

Industrial vision systems are used in all kinds of industries

Can we trust them?

Some examples of manufactured goods checked using digital image processing. (a) Circuit board controller. (b) Packaged pills. (c) Bottles. (d) Air bubbles in a clear plastic product. (e) Cereal. (f) Image of intraocular implant. G3E-P.40

Visible range:

automated inspection tasks

Automated visual inspection

Imag

es ta

ken fro

m G

onzale

z &

Woods,

Dig

ital Im

age P

rocessin

g (

2008)


APPLICATIONS: PCB INSPECTION

Printed Circuit Board (PCB) inspection

Machine inspection is used to determine that all components are present and that all solder joints are acceptable

Both conventional imaging and x-ray imaging are used



Some additional examples of imaging in the visible spectrum. (a) Thumb print. (b) Paper currency. (c) and (d) Automated license plate reading.

G3E-P.41Imag

es ta

ken fro

m G

onzale

z &

Woods,

Dig

ital Im

age P

rocessin

g (

2008)

G3C-P.10

IMAGING IN THE MICROWAVE BAND


G3E-P.42

Spaceborne radar image of mountainous region in southeast

Tibet.

Imag

es ta

ken fro

m G

onzale

z &

Woods,

Dig

ital Im

age P

rocessin

g (

2008)

G3C-P.10

RADIO BAND

MRI - imaging

(Nobel prizes: Bloch 1952,

… , 2003)

A strong magnet passes radio waves

though short pulses which causes

a response pulse (echo)


IMAGING IN THE RADIO BANDMRI

G3E-P.43

MRI images of a human (a) knee, and (b) spine.

Imag

es ta

ken fro

m G

onzale

z &

Woods,

Dig

ital Im

age P

rocessin

g (

2008)


MRI

3/4/2019 DIGITAL IMAGE PROCESSING 128MRI of normal brain

http://www.med.harvard.edu/AANLIB/cases/caseM/mr1_t/024.gif

http://www.med.harvard.edu/AANLIB/cases/caseM/mr1_t/024.gif

MRI

Take slice from MRI scan of canine heart, and find boundaries between types of tissue

Image with gray levels representing tissue density

Use a suitable filter to highlight edges

Original MRI Image of a Dog Heart Edge Detection Image


Figure Images of the Crab Pulsar (in the center of each image)

covering the electromagnetic spectrum.

G3E-P.43Imag

es ta

ken fro

m G

onzale

z &

Woods,

Dig

ital Im

age P

rocessin

g (

2008)


EXAMPLES IN WHICH OTHER IMAGING MODALITIES ARE USED

Cross-sectional image of a seismic model. The arrow points to a hydrocarbon (oil and/or gas) trap.

Sound

G3E-P.44

Other sources of energy

beside electromagnetic waves:

- acoustic waves

(seismic, marine/atmospheric,

sonar/radar, ultrasound)

- electron microscopy

- synthetic images

Imag

es ta

ken fro

m G

onzale

z &

Woods,

Dig

ital Im

age P

rocessin

g (

2008)


APPLICATIONS: MEDICINE (CONT...)

Figure Examples of ultrasound imaging. (a) A fetus. (b) Another view of the fetus. (c) Thyroids. (d) Muscle layers showing lesion.

Ultrasound

G3E-P.45Imag

es ta

ken fro

m G

onzale

z &

Woods,

Dig

ital Im

age P

rocessin

g (

2008)



ULTRASOUND IMAGEProfiles of a fetus at 4 months, the face is about 4cm long

Ultra sound image is another imaging modality

The fetal arm with the major arteries (radial and ulnar) clearly delineated.

http://www.parenthood.com/us.html

3/4/2019 133

MEDICAL IMAGES


Fetal ultrasound

Figure (a)250X SEM image of a tungsten filament following thermal failure(note the shattered pieces on the lower left).(b)2500XSEM image of a damaged integrated circuit. The white fibers are oxides resulting from thermal destruction.

Electron Microscope

G3E-P.46Imag

es ta

ken fro

m G

onzale

z &

Woods,

Dig

ital Im

age P

rocessin

g (

2008)

3/4/2019


G3C-P.13

Figure (a) and (b) Fractal images. (c) and (d) Images generated from 3-D computer models of the objects shown.

Images generated by computers

G3E-P.47Imag

es ta

ken fro

m G

onzale

z &

Woods,

Dig

ital Im

age P

rocessin

g (

2008)


APPLICATIONS: ARTISTIC EFFECTS

Artistic effects are used to make images more visually appealing, to add special effects and to make composite images


MORPHING



THE END OF LECTURE 1


DIGITAL IMAGE PROCESSING - SCUT · 2019-03-04 · Digital image processing –perform digital signal processing operations on digital images (by means of digital computers.) MAPPING

Documents