2 views

Uploaded by Rameshkumar Jayaraman

Image Processing Transformation is used to change or enhance the picture with Spatial domain

Image Processing Transformation is used to change or enhance the picture with Spatial domain

© All Rights Reserved

- Notes ch # 1
- Edge Detection in Digital Images Using Fuzzy Logic Technique
- SKRIPSI TANPA BAB PEMBAHASAN(1).pdf
- CSE Sixth Sense Technology Report
- Robotics
- IMVIP_Tabirca
- 2011 Homomorphic Filtering
- Lecture 03,04,05 - Intensity transformation and Spatial Filtering.pdf
- Histrogram Processing
- Robust Digital Image Watermarking Technique Based on Histogram Analysis
- DIGITAL IMAGE PROCESSING
- New Paper for Journal
- Multi Scale Morphological Segmentation of Gray-scale Images
- Geo Location and Information Retrieval for on Premise Signs
- v42-5
- 18-avl
- LBP
- Comparative Analysis of Filters
- 8. Article Azojete Vol 10 85-93 Alkali
- 1Introduction to Research1.pptx

You are on page 1of 50

Spatial Domain II

Review: gray level transformations

what transform

should we apply?

Histogram Processing

Histogram equalization

Histogram matching

Local enhancement

Use of histogram statistics

Histogram

Statistics of the pixel gray-levels of an image

h(rk)=nk : histogram

no. of

occurrence

gray level

Obtain contrast information

from histogram

Histogram: implementation issue

Divide the range of gray levels (ex. 0~255)

Number of bins

Position of bins specified in a vector

10 bins

5 bins

Histogram: normalization

=prob.

occurrence total pixels

Histogram equalization 均化

Goal: produce an uniform histogram

Find a transformation: s=T(r)

uniform

0 1 0 1

Histogram equalization(cont.)

Cumulative function of

1 histogram

Prob. 0.5

0.5

0 1 0 0.5 1

Ideal uniform histogram

Histogram equalization:

discrete solution

Probability (normalized histogram) of gray

level rk

p(rk)=nk/n, k=0,1,2,…, L-1

Discrete version of CDF (cumulative

distribution function)

k k nj

sk T (rk ) pr (rj ) <1

j 0 j 0 n

Example: histogram equalization

Histogram Processing

Histogram equalization

Histogram matching

Local enhancement

Use of histogram statistics

Histogram matching: original

image

Histogram equalization result

Histogram

Equalization

function

Equalized

histogram

After equalization

Histogram matching

The desired shape of histogram is specified

(not necessarily uniform)

Derivation of histogram matching function:

z=G-1(T(r))

z s r

desired uniform input

z=G-1(s) s=T(r)

histogram

equalization

histogram

equalization

s=G(z)

Original -> uniform desire -> uniform

(equalization) (equalization)

Inverse

function

of G

Histogram matching result

Desired histogram

After histogram

matching

G-1

Histogram Processing

Histogram equalization

Histogram matching

Local enhancement

Use of histogram statistics

Local enhancement

Global: entire image

Local: neighborhood of each pixel

local equalization

Histogram statistics

Take pixel value r as a random variable

Normalized histogram of an image

=> probability distribution function of r

L 1

m ri p ( ri ) mean

i 0

L 1

2 (r ) (ri m) 2 p (ri ) variance

i 0

variance => average contrast

Histogram statistics (cont.)

Local measurement: Sxy neighborhood

mS xy r

( s ,t )S xy

s ,t p(rs ,t ) mean in Sxy

(r )

2

S xy (r

( s ,t )S xy

s ,t mS xy ) p(rs ,t )

2

variance in Sxy

Application of histogram statistics:

example

Globally, this image is light

background object is

unseen

鎢絲及其支柱的放大影像

Histogram statistics: example

Calculate local statistics in 3x3 region

local mean local standard deviation

Histogram statistics: example

Local enhancement 像素平均值小 但是標準差大

E f ( x, y )k1 if mS xy k0 M G and DG S xy k1 DG

g ( x, y )

f ( x, y ) otherwise

enhanced

pixels

Histogram statistics: example

original enhanced

Outline: spatial domain

Histogram processing

Spatial filtering

Smoothing filter

Ordered statistics filter

Sharpening filter

Basics of spatial filtering

g(x,y)=T[ f(x,y) ]

T operates on a

neighborhood

mask coefficients

X (product) output

underlying neighborhood

Basics of spatial filtering

Mathematical formula

a b

g ( x, y ) w(s, t ) f ( x s, y t )

s at b

convolution

Border issues

Operate inside only

Discard the mask at border

Padding at image boundaries

zero padding

extension

Smoothing spatial filtering

Used for blurring and for noise reduction

Smoothing linear filters

Average filters, low-pass filters

因為3x3太小

original 3x3

noise

reduced

5x5 9x9

small area

blended into

background

15x15 35x35

border

effects

Smoothing: example

Order-statistics filters

Pixel neighborhood

f1 f2 f3

f4 f5 f6

f7 f8 f9

sort

f4 f3 f7 f6 f8 f2 f1 f9 f5

increasing order

filter filter filter

remove isolated

high(low) pixels

Median filter: example

salt-and-pepper noise

Outline: spatial domain

Histogram processing

Spatial filtering 空間濾波

Smoothing filter

Ordered statistics filter

Sharpening filter

Sharpening

filtering:

example

original Edge detection

scaled sharpened

Sharpening spatial filters

Goal

highlight fine detail in an image

Spatial differentiation 微分

Digital implementation => difference 差分

de-emphasize regions with slowly varying gray

levels

smooth

1 ( 1) '

2 ( 1)2 ''

Sharpening: foundation

First and second-order derivatives in digital

form => difference

f

f ( x 1) f ( x) 一次微分

x

2 f

[ f ( x 1) f ( x)] [ f ( x) f ( x 1)] 二次微分

x 2

f ( x 1) f ( x 1) 2 f ( x)

2nd derivatives for image

2-D 2nd derivatives => Laplacian

2

f 2

f

f 2 2

2

x y

=>discrete formulation

2 f [ f ( x 1, y ) f ( x 1, y ) 2 f ( x, y )]

[ f ( x, y 1) f ( x, y 1) 2 f ( x, y )]

[ f ( x 1, y ) f ( x 1, y ) f ( x, y 1) f ( x, y 1)] 4 f ( x, y )

Definition of 2nd derivatives in

filter mask

450 rotation

900 rotation invariant

invariant (include

Diagonals)

- - - -

- 4 - - 8 -

- - - -

Laplacian filtering: example

Sharpened result = original +

Laplacian filtered image

f ( x, y) 2 f ( x, y) if center coeff. of the mask is negative

g ( x, y)

f ( x, y ) 2

f ( x, y) if center coeff. of the mask is positive

Laplacian

filtering:

example

original Laplacian

scaled sharpened

original

right

left

mask

mask

Use of 1st derivative: Gradient

Gradient f

Gx x

f f

G y

y

Magnitude of gradient

2 1/ 2

f f

2

f mag (f )

x y

Definition of 1st derivative in

mask filters

Sobel operators

Gradient: example

*enhance defects and eliminate slowly changing background

defects

- Notes ch # 1Uploaded byZeeshanMahdi
- Edge Detection in Digital Images Using Fuzzy Logic TechniqueUploaded byMuhammad Iqbal Ramadhani
- SKRIPSI TANPA BAB PEMBAHASAN(1).pdfUploaded byFariz Al Hafiz
- CSE Sixth Sense Technology ReportUploaded bymunna
- RoboticsUploaded byJohnMichaelAniscol
- IMVIP_TabircaUploaded byAnonymous 0U9j6BLllB
- 2011 Homomorphic FilteringUploaded byArif Fadllullah Ayip
- Lecture 03,04,05 - Intensity transformation and Spatial Filtering.pdfUploaded byVu Quang Pham
- Histrogram ProcessingUploaded byfizajessica
- Robust Digital Image Watermarking Technique Based on Histogram AnalysisUploaded byWorld of Computer Science and Information Technology Journal
- DIGITAL IMAGE PROCESSINGUploaded byRakesh Srirangam
- New Paper for JournalUploaded byanubala vp
- Multi Scale Morphological Segmentation of Gray-scale ImagesUploaded bykatebao
- Geo Location and Information Retrieval for on Premise SignsUploaded byijteee
- v42-5Uploaded byrahas123
- 18-avlUploaded byEliud Noguera
- LBPUploaded bySaime Illtutmish
- Comparative Analysis of FiltersUploaded byCS & IT
- 8. Article Azojete Vol 10 85-93 AlkaliUploaded byOyeniyi Samuel Kehinde
- 1Introduction to Research1.pptxUploaded byReza Hakim
- 219cd5f3b5071a5c951718299aa61fbf the Need for Wind EnergyUploaded byEhsan Ur Rehman
- rubericUploaded byapi-231581936
- Experiment 3Uploaded byZyra Camille Giron Hachero
- Line Detection in Digital Images: A Modification to Randomized Line Detection AlgorithmUploaded byseventhsensegroup
- Photoshop Quick Reference GuideUploaded byKuwabara Tsusha
- Add on PruevaUploaded byCarlosIvanFerreiraMeneses
- Photoshop CS4 Questions and AnswersUploaded byCaljer Caldo
- MolinaUploaded bysandra
- Team BuildingUploaded byEthan Zachary
- Guide 2Uploaded bymrsukurac11

- Medical ElectronicsUploaded byRameshkumar Jayaraman
- CIRCUITS AND SIGNALSUploaded byRameshkumar Jayaraman
- Vector Quantization in Image Processing.pdfUploaded byRameshkumar Jayaraman
- ADSPUploaded byRameshkumar Jayaraman
- DCS Comprehension QuestionsUploaded byRameshkumar Jayaraman
- Descendant Protocols: A SurveUploaded byRameshkumar Jayaraman
- Echo CancellationUploaded byRameshkumar Jayaraman
- Simulation EnvironmentUploaded byRameshkumar Jayaraman
- ieee488Uploaded byKenan Kuzulugil
- computer networks question papersUploaded byAanitha Ravindran
- vcdUploaded byRameshkumar Jayaraman
- Nr320402-Digital Signal ProcessingUploaded bySRINIVASA RAO GANTA

- Quiz, Answers and Solutions in 1st Quiz in Mathematics in Preparation for UPCATUploaded byAna Marie
- Unigraphics NX8 - SketchingUploaded byBoy Doland
- Chapter 09Uploaded bymapasabc
- Catálogo TécnicoUploaded byJulio Razeck
- AN-C240Uploaded bykymk21
- my workUploaded byjagadeesh sura
- 31817873-28025913-93ZJ-in-IntroductionUploaded byArm L Harvey
- Stock Update ListUploaded byricky
- SL13A DatasheetUploaded byali
- Basics of PipingUploaded byDawood Akram
- Types of Pipe Fittings in Plumbing SystemUploaded byJoanne Dawang
- SSC Mains Maths 19Uploaded bypiyush13ju
- Thermodynamic Systems and ProcessesUploaded byAlpesh Panchal
- MikroPul High Efficiency Cyclones 200511Uploaded byZoran Danilov
- Designofwaveguide-fedseriesslotarraysUploaded byjoojoooo2011
- 1362909498_Dami et al (1)Uploaded bymusaveer
- Rielly E.conrad. SMP93 - Standard Ship Motion Program User ManualUploaded byYuriyAK
- asl hand drawing rubric sheetUploaded byapi-278922030
- Nelson Stud Welding - Standard FerruleUploaded byStefan Ionita
- UntitledUploaded bySamaksh Verma
- Isight Optimization of Material Parameters used in the Abaqus Worldwide Side Impact Dummy 2012Uploaded bySIMULIACorp
- WIRE-ROPE-HOIST drh donati.pdfUploaded byJavier Vasquez
- parte III cinetica.pdfUploaded bypablobalado
- Aiits 1416 Pt III Jeem Jeea Advanced Paper 2 Questions PaperUploaded byRavi Kumar Varma
- BibliographyUploaded byRyan
- 14PHDIT003 (1)Uploaded byPraveen D Jadhav
- As Java Stack Most Common LOG Files2Uploaded bybuddy261
- Configuracion y O&M BTS NokiaUploaded byjcardenas55
- ECT193Uploaded byMohammed Madi
- LM_Chapter 01.pdfUploaded bymnahas84