SlideShare a Scribd company logo
Ali abdul-zahraa
We will discuss shape-based representations
(external), features based on texture and
statistical moments (internal) .
look at principal component analysis (PCA), a
statistical method which has been widely
applied to image processing problems.
We are assume that an image has undergone
segmentation.
The common goal of feature extraction and
representation techniques is to convert the
segmented objects into representations that
better describe their main features and
attributes.
The type and complexity of the resulting
representation depend on many factors, such
as the type of image (e.g., binary, grayscale, or
color), the level of granularity (entire image or
individual regions) desired.
Feature extraction is the process by which
certain features of interest within an image are
detected and represented for further
processing.
It is a critical step in most computer vision and
image processing solutions because it marks
the transition from pictorial to nonpictorial
(alphanumerical, usually quantitative) data
representation.
The aim is to process the image in such a way
that the image, or properties of it, can be
adequately represented and extracted in a
compact form amenable to subsequent
recognition and classification.
Representations are typically of two basic
kinds:
 internal (which relates to the pixels comprising
a region)
 or external (which relates to the boundary of a
region).
A feature vector is a n × 1 array that encodes
the n features (or measurements) of an image
or object.
The array contents may be:
 symbolic (e.g., a string containing the name of
the predominant color in the image)
 numerical (e.g., an integer expressing the area
of an object, in pixels) I’ll interested in.
 or both
A very basic representation of a shape simply
requires the identification of a number N of
points along the boundary of the features. In
two dimensions, this is simply.
A common requirement for feature extraction
and representation techniques is that the
features used to represent an image be
invariant to rotation, scaling, and translation,
collectively known as RST.
RST invariance ensures that a machine vision
system will still be able to recognize objects
even when they appear at different size,
position within the image, and angle (relative to
a horizontal reference).
A binary object, in this case, is a connected
region within a binary image f (x, y), which will
be denoted as Oi, i > 0. Mathematically, we can
define a function Oi(x, y) as follows:
Oi(x, y) =
1 if f (x, y) ∈ Oi
0 otherwise
The matlab function bwlabel, pixels labeled 0
correspond to the background; pixels labeled 1
and higher correspond to the connected
components in the image.
we mean that the selected coordinates constituting
the boundary/shape must be chosen in such a way
as to ensure close agreement across a group of
observers.
If this were not satisfied, then different observers
would define completely different shape vectors for
what is actually the same shape.
achieved by defining criteria for identifying
appropriate and well-defined key points along the
boundaries , Such key points are called
landmarks
Landmarks essentially divide into three
categories:
Mathematical landmarks
Anatomical or true landmarks
Pseudo-landmarks
These correspond to points located on an
object according to some mathematical or
geometric property (e.g. according to local
gradient, curvature or some extremum value).
These are points assigned by an expert which
are identifiable in (and correspond between)
different members of a class of objects.
Examples of anatomical landmarks are the
corners of the mouth and eyes in human faces.
These are points which are neither
mathematically nor anatomically completely
well defined, though they may certainly be
intuitively meaningful and/or require some
skilled judgment on the part of an operator.
An example of a pseudo landmark might be
the ‘ centre of the cheek bones’ in a human
face, because the visual information is not
definite enough to allow unerring placement.
• Anatomical landmarks
(indicated in red) are located
at points which can be easily
identified visually.
• Mathematical landmarks
(black crosses) are identified
at points of zero gradient and
maximum corner content.
• The pseudo-landmarks are
indicated by green circles
In certain applications, we do not require a
shape analysis/recognition technique to
provide a precise, regenerative representation
of the shape. The aim is simply to characterize
a shape as succinctly as possible in order that
it can be differentiated from other shapes and
classified accordingly.
a small number of descriptors or even a single
parameter can be sufficient to achieve this
task.
Note that many of these measures can be
derived from knowledge of the perimeter
length.
The following Table gives a number of
common, single-parameter measures of
approximate shape
which can be employed as shape features in
basic tasks of discrimination and classification.
Note that many of these measures can be
derived from knowledge of the perimeter
length,
the extreme x and y values and the total area
enclosed by the boundary – quantities which
can be calculated easily in practice.
1. Area
The area of the ith object Oi, measured in
pixels, is given by:
2. Centroid
The coordinates of the centroid (also known as
center of area) of object Oi, denoted (x¯i, y¯i),
are given by: or
3. Projections
The horizontal and vertical projections of a
binary object—hi(x) and vi(y), respectively—are
obtained by equations:
and
Projections are very useful and compact shape
descriptors. For example, the height and width
of an object without holes can be computed as
the maximum value of the object’s vertical and
horizontal projections, respectively, as
illustrated in Figure:
4. Thinness Ratio
The thinness ratio Ti of a binary object Oi is a
figure of merit that relates the object’s area and
its perimeter by equation
Ti = (4πAi)/(Pi^2)
where Ai is the area and Pi is the perimeter
The thinness ratio is often used as a measure
of roundness.
Since the maximum value for Ti is 1 (which
corresponds to a perfect circle), for a generic
object the higher its thinness ratio, the more
round it is.
This figure of merit can also be used as a
measure of regularity and its inverse, 1/Ti is
sometimes called irregularity or compactness
ratio.
A=imread('coins_and_keys.png'); subplot(1,2,1), imshow(A);
%Read in image and display
bw=~im2bw(rgb2gray(A),0.35); bw=imfill(bw,'holes');
%Threshold and fill in holes
bw=imopen(bw,ones(5)); subplot(1,2,2), imshow(bw,[0 1]);
%Morphological opening
[L,num]=bwlabel(bw);
%Create labelled image
s=regionprops(L,'area','perimeter');
%Calculate region properties
for i=1:num
%object’s area and perimeter
x(i)=s(i).Area;
y(i)=s(i).Perimeter;
form(i)=4.*pi.*x(i)./(y(i).^2);
%Calculate form factor
end
figure; plot(x./max(x),form,'ro');
%Plot area against form factor
% regionprops Measure properties of image regions
The key and drill bit are easily distinguished
from the coins by their form-factor values.
However, the imperfect result from thresholding
means that the form factor is unable to
distinguish between the heptagonal coins and
circular coins. These are, however, easily
separated by area.
1. Chain Code, Freeman Code, and Shape
Number:
A chain code : is a boundary representation
technique by which a contour is represented as
a sequence of straight line segments of
specified length (usually 1) and direction.
Once the chain code for a boundary has been
computed, it is possible to convert the resulting array
into a rotation-invariant equivalent, known as the first
difference
Fourier Descriptor
Fourier descriptor: view a coordinate (x,y) as a complex number
(x = real part and y = imaginary part) then apply the Fourier
transform to a sequence of boundary points.
)()()( kjykxks 





1
0
/2
)(
1
)(
K
k
Kuk
eks
K
ua 
Fourier descriptor :




1
0
/2
)(
1
)(
K
k
Kuk
eua
K
ks 
Let s(k) be a coordinate
of a boundary point k :
Reconstruction formula
Boundary
points
Example: Fourier Descriptor
Examples of reconstruction from Fourier descriptors




1
0
/2
)(
1
)(ˆ
P
k
Kuk
eua
K
ks 
P is the number of
Fourier coefficients
used to reconstruct
the boundary
Fourier Descriptor Properties
Some properties of Fourier descriptors

More Related Content

What's hot

Image segmentation ppt
Image segmentation pptImage segmentation ppt
Image segmentation pptGichelle Amon
 
Histogram Processing
Histogram ProcessingHistogram Processing
Histogram ProcessingAmnaakhaan
 
Chapter 6 color image processing
Chapter 6 color image processingChapter 6 color image processing
Chapter 6 color image processingasodariyabhavesh
 
Image Enhancement in Spatial Domain
Image Enhancement in Spatial DomainImage Enhancement in Spatial Domain
Image Enhancement in Spatial DomainA B Shinde
 
Color Image Processing
Color Image ProcessingColor Image Processing
Color Image Processingkiruthiammu
 
Image Enhancement in Spatial Domain
Image Enhancement in Spatial DomainImage Enhancement in Spatial Domain
Image Enhancement in Spatial DomainDEEPASHRI HK
 
Image Restoration (Digital Image Processing)
Image Restoration (Digital Image Processing)Image Restoration (Digital Image Processing)
Image Restoration (Digital Image Processing)Kalyan Acharjya
 
Digital Image Fundamentals
Digital Image FundamentalsDigital Image Fundamentals
Digital Image FundamentalsA B Shinde
 
Image Segmentation (Digital Image Processing)
Image Segmentation (Digital Image Processing)Image Segmentation (Digital Image Processing)
Image Segmentation (Digital Image Processing)VARUN KUMAR
 
DIGITAL IMAGE PROCESSING - LECTURE NOTES
DIGITAL IMAGE PROCESSING - LECTURE NOTESDIGITAL IMAGE PROCESSING - LECTURE NOTES
DIGITAL IMAGE PROCESSING - LECTURE NOTESEzhilya venkat
 
Image enhancement techniques
Image enhancement techniques Image enhancement techniques
Image enhancement techniques Arshad khan
 
Image Enhancement using Frequency Domain Filters
Image Enhancement using Frequency Domain FiltersImage Enhancement using Frequency Domain Filters
Image Enhancement using Frequency Domain FiltersKarthika Ramachandran
 
Digital Image Processing: Digital Image Fundamentals
Digital Image Processing: Digital Image FundamentalsDigital Image Processing: Digital Image Fundamentals
Digital Image Processing: Digital Image FundamentalsMostafa G. M. Mostafa
 
1.arithmetic & logical operations
1.arithmetic & logical operations1.arithmetic & logical operations
1.arithmetic & logical operationsmukesh bhardwaj
 
Image Filtering in the Frequency Domain
Image Filtering in the Frequency DomainImage Filtering in the Frequency Domain
Image Filtering in the Frequency DomainAmnaakhaan
 
Image sampling and quantization
Image sampling and quantizationImage sampling and quantization
Image sampling and quantizationBCET, Balasore
 

What's hot (20)

Image segmentation ppt
Image segmentation pptImage segmentation ppt
Image segmentation ppt
 
Histogram Processing
Histogram ProcessingHistogram Processing
Histogram Processing
 
Chapter 6 color image processing
Chapter 6 color image processingChapter 6 color image processing
Chapter 6 color image processing
 
Image Enhancement in Spatial Domain
Image Enhancement in Spatial DomainImage Enhancement in Spatial Domain
Image Enhancement in Spatial Domain
 
Color Image Processing
Color Image ProcessingColor Image Processing
Color Image Processing
 
Image Enhancement in Spatial Domain
Image Enhancement in Spatial DomainImage Enhancement in Spatial Domain
Image Enhancement in Spatial Domain
 
Image Restoration (Digital Image Processing)
Image Restoration (Digital Image Processing)Image Restoration (Digital Image Processing)
Image Restoration (Digital Image Processing)
 
Digital Image Fundamentals
Digital Image FundamentalsDigital Image Fundamentals
Digital Image Fundamentals
 
Image processing ppt
Image processing pptImage processing ppt
Image processing ppt
 
Image Segmentation (Digital Image Processing)
Image Segmentation (Digital Image Processing)Image Segmentation (Digital Image Processing)
Image Segmentation (Digital Image Processing)
 
Cse image processing ppt
Cse image processing pptCse image processing ppt
Cse image processing ppt
 
DIGITAL IMAGE PROCESSING - LECTURE NOTES
DIGITAL IMAGE PROCESSING - LECTURE NOTESDIGITAL IMAGE PROCESSING - LECTURE NOTES
DIGITAL IMAGE PROCESSING - LECTURE NOTES
 
Image enhancement techniques
Image enhancement techniques Image enhancement techniques
Image enhancement techniques
 
Image Enhancement using Frequency Domain Filters
Image Enhancement using Frequency Domain FiltersImage Enhancement using Frequency Domain Filters
Image Enhancement using Frequency Domain Filters
 
Image enhancement
Image enhancementImage enhancement
Image enhancement
 
Digital Image Processing: Digital Image Fundamentals
Digital Image Processing: Digital Image FundamentalsDigital Image Processing: Digital Image Fundamentals
Digital Image Processing: Digital Image Fundamentals
 
IMAGE SEGMENTATION.
IMAGE SEGMENTATION.IMAGE SEGMENTATION.
IMAGE SEGMENTATION.
 
1.arithmetic & logical operations
1.arithmetic & logical operations1.arithmetic & logical operations
1.arithmetic & logical operations
 
Image Filtering in the Frequency Domain
Image Filtering in the Frequency DomainImage Filtering in the Frequency Domain
Image Filtering in the Frequency Domain
 
Image sampling and quantization
Image sampling and quantizationImage sampling and quantization
Image sampling and quantization
 

Viewers also liked

Neural networks
Neural networksNeural networks
Neural networksSlideshare
 
Feature Extraction
Feature ExtractionFeature Extraction
Feature Extractionskylian
 
ARTIFICIAL INTELLIGENCE & NEURAL NETWORKS
ARTIFICIAL INTELLIGENCE & NEURAL NETWORKSARTIFICIAL INTELLIGENCE & NEURAL NETWORKS
ARTIFICIAL INTELLIGENCE & NEURAL NETWORKSEr Kaushal
 
Artificial neural networks
Artificial neural networksArtificial neural networks
Artificial neural networksstellajoseph
 
Artificial intelligence NEURAL NETWORKS
Artificial intelligence NEURAL NETWORKSArtificial intelligence NEURAL NETWORKS
Artificial intelligence NEURAL NETWORKSREHMAT ULLAH
 
Chapter 5 - Fuzzy Logic
Chapter 5 - Fuzzy LogicChapter 5 - Fuzzy Logic
Chapter 5 - Fuzzy LogicAshique Rasool
 
Neural network & its applications
Neural network & its applications Neural network & its applications
Neural network & its applications Ahmed_hashmi
 
Speech recognition
Speech recognitionSpeech recognition
Speech recognitionCharu Joshi
 
Artificial neural network
Artificial neural networkArtificial neural network
Artificial neural networkDEEPASHRI HK
 

Viewers also liked (15)

LISP: Introduction to lisp
LISP: Introduction to lispLISP: Introduction to lisp
LISP: Introduction to lisp
 
Neural networks
Neural networksNeural networks
Neural networks
 
Feature Extraction
Feature ExtractionFeature Extraction
Feature Extraction
 
ARTIFICIAL INTELLIGENCE & NEURAL NETWORKS
ARTIFICIAL INTELLIGENCE & NEURAL NETWORKSARTIFICIAL INTELLIGENCE & NEURAL NETWORKS
ARTIFICIAL INTELLIGENCE & NEURAL NETWORKS
 
Artificial neural networks
Artificial neural networksArtificial neural networks
Artificial neural networks
 
Artificial intelligence NEURAL NETWORKS
Artificial intelligence NEURAL NETWORKSArtificial intelligence NEURAL NETWORKS
Artificial intelligence NEURAL NETWORKS
 
Fuzzy logic ppt
Fuzzy logic pptFuzzy logic ppt
Fuzzy logic ppt
 
Chapter 5 - Fuzzy Logic
Chapter 5 - Fuzzy LogicChapter 5 - Fuzzy Logic
Chapter 5 - Fuzzy Logic
 
Fuzzy logic
Fuzzy logicFuzzy logic
Fuzzy logic
 
Neural network & its applications
Neural network & its applications Neural network & its applications
Neural network & its applications
 
Pattern Recognition
Pattern RecognitionPattern Recognition
Pattern Recognition
 
Pattern recognition
Pattern recognitionPattern recognition
Pattern recognition
 
Introduction to pattern recognition
Introduction to pattern recognitionIntroduction to pattern recognition
Introduction to pattern recognition
 
Speech recognition
Speech recognitionSpeech recognition
Speech recognition
 
Artificial neural network
Artificial neural networkArtificial neural network
Artificial neural network
 

Similar to Features image processing and Extaction

Image Information Retrieval From Incomplete Queries Using Color and Shape Fea...
Image Information Retrieval From Incomplete Queries Using Color and Shape Fea...Image Information Retrieval From Incomplete Queries Using Color and Shape Fea...
Image Information Retrieval From Incomplete Queries Using Color and Shape Fea...sipij
 
DIP-LECTURE_NOTES.pdf
DIP-LECTURE_NOTES.pdfDIP-LECTURE_NOTES.pdf
DIP-LECTURE_NOTES.pdfVaideshSiva1
 
image segmentation by ppres.pptx
image segmentation by ppres.pptximage segmentation by ppres.pptx
image segmentation by ppres.pptxmohan134666
 
Presentation on Face Recognition Based on 3D Shape Estimation
Presentation on Face Recognition Based on 3D Shape EstimationPresentation on Face Recognition Based on 3D Shape Estimation
Presentation on Face Recognition Based on 3D Shape EstimationRapidAcademy
 
Image features detection description
Image features detection  descriptionImage features detection  description
Image features detection descriptionmomen saboor
 
An application of morphological
An application of morphologicalAn application of morphological
An application of morphologicalNaresh Chilamakuri
 
7.traffic sign detection and recognition
7.traffic sign detection and recognition7.traffic sign detection and recognition
7.traffic sign detection and recognitionEditorJST
 
"FingerPrint Recognition Using Principle Component Analysis(PCA)”
"FingerPrint Recognition Using Principle Component Analysis(PCA)”"FingerPrint Recognition Using Principle Component Analysis(PCA)”
"FingerPrint Recognition Using Principle Component Analysis(PCA)”Er. Arpit Sharma
 
A COMPARATIVE ANALYSIS OF RETRIEVAL TECHNIQUES IN CONTENT BASED IMAGE RETRIEVAL
A COMPARATIVE ANALYSIS OF RETRIEVAL TECHNIQUES IN CONTENT BASED IMAGE RETRIEVALA COMPARATIVE ANALYSIS OF RETRIEVAL TECHNIQUES IN CONTENT BASED IMAGE RETRIEVAL
A COMPARATIVE ANALYSIS OF RETRIEVAL TECHNIQUES IN CONTENT BASED IMAGE RETRIEVALcscpconf
 
A comparative analysis of retrieval techniques in content based image retrieval
A comparative analysis of retrieval techniques in content based image retrievalA comparative analysis of retrieval techniques in content based image retrieval
A comparative analysis of retrieval techniques in content based image retrievalcsandit
 
APPLYING R-SPATIOGRAM IN OBJECT TRACKING FOR OCCLUSION HANDLING
APPLYING R-SPATIOGRAM IN OBJECT TRACKING FOR OCCLUSION HANDLINGAPPLYING R-SPATIOGRAM IN OBJECT TRACKING FOR OCCLUSION HANDLING
APPLYING R-SPATIOGRAM IN OBJECT TRACKING FOR OCCLUSION HANDLINGsipij
 
Different Image Segmentation Techniques for Dental Image Extraction
Different Image Segmentation Techniques for Dental Image ExtractionDifferent Image Segmentation Techniques for Dental Image Extraction
Different Image Segmentation Techniques for Dental Image ExtractionIJERA Editor
 
computervision1.pdf it is about computer vision
computervision1.pdf it is about computer visioncomputervision1.pdf it is about computer vision
computervision1.pdf it is about computer visionshesnasuneer
 
Medical Image Retrieval Based On Edge Histogram Descriptor
Medical Image Retrieval Based On Edge Histogram DescriptorMedical Image Retrieval Based On Edge Histogram Descriptor
Medical Image Retrieval Based On Edge Histogram Descriptorinventionjournals
 
Signature recognition using clustering techniques dissertati
Signature recognition using clustering techniques dissertatiSignature recognition using clustering techniques dissertati
Signature recognition using clustering techniques dissertatiDr. Vinayak Bharadi
 

Similar to Features image processing and Extaction (20)

Image Information Retrieval From Incomplete Queries Using Color and Shape Fea...
Image Information Retrieval From Incomplete Queries Using Color and Shape Fea...Image Information Retrieval From Incomplete Queries Using Color and Shape Fea...
Image Information Retrieval From Incomplete Queries Using Color and Shape Fea...
 
Multimedia searching
Multimedia searchingMultimedia searching
Multimedia searching
 
mini prjt
mini prjtmini prjt
mini prjt
 
DIP-LECTURE_NOTES.pdf
DIP-LECTURE_NOTES.pdfDIP-LECTURE_NOTES.pdf
DIP-LECTURE_NOTES.pdf
 
image segmentation by ppres.pptx
image segmentation by ppres.pptximage segmentation by ppres.pptx
image segmentation by ppres.pptx
 
Presentation on Face Recognition Based on 3D Shape Estimation
Presentation on Face Recognition Based on 3D Shape EstimationPresentation on Face Recognition Based on 3D Shape Estimation
Presentation on Face Recognition Based on 3D Shape Estimation
 
Image features detection description
Image features detection  descriptionImage features detection  description
Image features detection description
 
ACMP340.pptx
ACMP340.pptxACMP340.pptx
ACMP340.pptx
 
An application of morphological
An application of morphologicalAn application of morphological
An application of morphological
 
7.traffic sign detection and recognition
7.traffic sign detection and recognition7.traffic sign detection and recognition
7.traffic sign detection and recognition
 
"FingerPrint Recognition Using Principle Component Analysis(PCA)”
"FingerPrint Recognition Using Principle Component Analysis(PCA)”"FingerPrint Recognition Using Principle Component Analysis(PCA)”
"FingerPrint Recognition Using Principle Component Analysis(PCA)”
 
A COMPARATIVE ANALYSIS OF RETRIEVAL TECHNIQUES IN CONTENT BASED IMAGE RETRIEVAL
A COMPARATIVE ANALYSIS OF RETRIEVAL TECHNIQUES IN CONTENT BASED IMAGE RETRIEVALA COMPARATIVE ANALYSIS OF RETRIEVAL TECHNIQUES IN CONTENT BASED IMAGE RETRIEVAL
A COMPARATIVE ANALYSIS OF RETRIEVAL TECHNIQUES IN CONTENT BASED IMAGE RETRIEVAL
 
A comparative analysis of retrieval techniques in content based image retrieval
A comparative analysis of retrieval techniques in content based image retrievalA comparative analysis of retrieval techniques in content based image retrieval
A comparative analysis of retrieval techniques in content based image retrieval
 
APPLYING R-SPATIOGRAM IN OBJECT TRACKING FOR OCCLUSION HANDLING
APPLYING R-SPATIOGRAM IN OBJECT TRACKING FOR OCCLUSION HANDLINGAPPLYING R-SPATIOGRAM IN OBJECT TRACKING FOR OCCLUSION HANDLING
APPLYING R-SPATIOGRAM IN OBJECT TRACKING FOR OCCLUSION HANDLING
 
Different Image Segmentation Techniques for Dental Image Extraction
Different Image Segmentation Techniques for Dental Image ExtractionDifferent Image Segmentation Techniques for Dental Image Extraction
Different Image Segmentation Techniques for Dental Image Extraction
 
Computer graphics
Computer graphicsComputer graphics
Computer graphics
 
computervision1.pdf it is about computer vision
computervision1.pdf it is about computer visioncomputervision1.pdf it is about computer vision
computervision1.pdf it is about computer vision
 
Medical Image Retrieval Based On Edge Histogram Descriptor
Medical Image Retrieval Based On Edge Histogram DescriptorMedical Image Retrieval Based On Edge Histogram Descriptor
Medical Image Retrieval Based On Edge Histogram Descriptor
 
E018212935
E018212935E018212935
E018212935
 
Signature recognition using clustering techniques dissertati
Signature recognition using clustering techniques dissertatiSignature recognition using clustering techniques dissertati
Signature recognition using clustering techniques dissertati
 

More from Ali A Jalil

Clean Code: Successive Refinement
Clean Code: Successive RefinementClean Code: Successive Refinement
Clean Code: Successive RefinementAli A Jalil
 
Image classification
Image classificationImage classification
Image classificationAli A Jalil
 
Photometric calibration
Photometric calibrationPhotometric calibration
Photometric calibrationAli A Jalil
 
Interconnection Network
Interconnection NetworkInterconnection Network
Interconnection NetworkAli A Jalil
 

More from Ali A Jalil (10)

Clean Code: Successive Refinement
Clean Code: Successive RefinementClean Code: Successive Refinement
Clean Code: Successive Refinement
 
And or graph
And or graphAnd or graph
And or graph
 
Markov model
Markov modelMarkov model
Markov model
 
Image classification
Image classificationImage classification
Image classification
 
HDR
HDRHDR
HDR
 
Photometric calibration
Photometric calibrationPhotometric calibration
Photometric calibration
 
Interconnection Network
Interconnection NetworkInterconnection Network
Interconnection Network
 
Polygon drawing
Polygon drawingPolygon drawing
Polygon drawing
 
Polygon drawing
Polygon drawingPolygon drawing
Polygon drawing
 
Text mining
Text miningText mining
Text mining
 

Recently uploaded

Designing Great Products: The Power of Design and Leadership by Chief Designe...
Designing Great Products: The Power of Design and Leadership by Chief Designe...Designing Great Products: The Power of Design and Leadership by Chief Designe...
Designing Great Products: The Power of Design and Leadership by Chief Designe...Product School
 
Measures in SQL (a talk at SF Distributed Systems meetup, 2024-05-22)
Measures in SQL (a talk at SF Distributed Systems meetup, 2024-05-22)Measures in SQL (a talk at SF Distributed Systems meetup, 2024-05-22)
Measures in SQL (a talk at SF Distributed Systems meetup, 2024-05-22)Julian Hyde
 
Introduction to Open Source RAG and RAG Evaluation
Introduction to Open Source RAG and RAG EvaluationIntroduction to Open Source RAG and RAG Evaluation
Introduction to Open Source RAG and RAG EvaluationZilliz
 
When stars align: studies in data quality, knowledge graphs, and machine lear...
When stars align: studies in data quality, knowledge graphs, and machine lear...When stars align: studies in data quality, knowledge graphs, and machine lear...
When stars align: studies in data quality, knowledge graphs, and machine lear...Elena Simperl
 
De-mystifying Zero to One: Design Informed Techniques for Greenfield Innovati...
De-mystifying Zero to One: Design Informed Techniques for Greenfield Innovati...De-mystifying Zero to One: Design Informed Techniques for Greenfield Innovati...
De-mystifying Zero to One: Design Informed Techniques for Greenfield Innovati...Product School
 
Empowering NextGen Mobility via Large Action Model Infrastructure (LAMI): pav...
Empowering NextGen Mobility via Large Action Model Infrastructure (LAMI): pav...Empowering NextGen Mobility via Large Action Model Infrastructure (LAMI): pav...
Empowering NextGen Mobility via Large Action Model Infrastructure (LAMI): pav...Thierry Lestable
 
Dev Dives: Train smarter, not harder – active learning and UiPath LLMs for do...
Dev Dives: Train smarter, not harder – active learning and UiPath LLMs for do...Dev Dives: Train smarter, not harder – active learning and UiPath LLMs for do...
Dev Dives: Train smarter, not harder – active learning and UiPath LLMs for do...UiPathCommunity
 
Kubernetes & AI - Beauty and the Beast !?! @KCD Istanbul 2024
Kubernetes & AI - Beauty and the Beast !?! @KCD Istanbul 2024Kubernetes & AI - Beauty and the Beast !?! @KCD Istanbul 2024
Kubernetes & AI - Beauty and the Beast !?! @KCD Istanbul 2024Tobias Schneck
 
From Siloed Products to Connected Ecosystem: Building a Sustainable and Scala...
From Siloed Products to Connected Ecosystem: Building a Sustainable and Scala...From Siloed Products to Connected Ecosystem: Building a Sustainable and Scala...
From Siloed Products to Connected Ecosystem: Building a Sustainable and Scala...Product School
 
JMeter webinar - integration with InfluxDB and Grafana
JMeter webinar - integration with InfluxDB and GrafanaJMeter webinar - integration with InfluxDB and Grafana
JMeter webinar - integration with InfluxDB and GrafanaRTTS
 
Search and Society: Reimagining Information Access for Radical Futures
Search and Society: Reimagining Information Access for Radical FuturesSearch and Society: Reimagining Information Access for Radical Futures
Search and Society: Reimagining Information Access for Radical FuturesBhaskar Mitra
 
Future Visions: Predictions to Guide and Time Tech Innovation, Peter Udo Diehl
Future Visions: Predictions to Guide and Time Tech Innovation, Peter Udo DiehlFuture Visions: Predictions to Guide and Time Tech Innovation, Peter Udo Diehl
Future Visions: Predictions to Guide and Time Tech Innovation, Peter Udo DiehlPeter Udo Diehl
 
Knowledge engineering: from people to machines and back
Knowledge engineering: from people to machines and backKnowledge engineering: from people to machines and back
Knowledge engineering: from people to machines and backElena Simperl
 
Free and Effective: Making Flows Publicly Accessible, Yumi Ibrahimzade
Free and Effective: Making Flows Publicly Accessible, Yumi IbrahimzadeFree and Effective: Making Flows Publicly Accessible, Yumi Ibrahimzade
Free and Effective: Making Flows Publicly Accessible, Yumi IbrahimzadeCzechDreamin
 
ODC, Data Fabric and Architecture User Group
ODC, Data Fabric and Architecture User GroupODC, Data Fabric and Architecture User Group
ODC, Data Fabric and Architecture User GroupCatarinaPereira64715
 
UiPath Test Automation using UiPath Test Suite series, part 2
UiPath Test Automation using UiPath Test Suite series, part 2UiPath Test Automation using UiPath Test Suite series, part 2
UiPath Test Automation using UiPath Test Suite series, part 2DianaGray10
 
Optimizing NoSQL Performance Through Observability
Optimizing NoSQL Performance Through ObservabilityOptimizing NoSQL Performance Through Observability
Optimizing NoSQL Performance Through ObservabilityScyllaDB
 
Software Delivery At the Speed of AI: Inflectra Invests In AI-Powered Quality
Software Delivery At the Speed of AI: Inflectra Invests In AI-Powered QualitySoftware Delivery At the Speed of AI: Inflectra Invests In AI-Powered Quality
Software Delivery At the Speed of AI: Inflectra Invests In AI-Powered QualityInflectra
 
How world-class product teams are winning in the AI era by CEO and Founder, P...
How world-class product teams are winning in the AI era by CEO and Founder, P...How world-class product teams are winning in the AI era by CEO and Founder, P...
How world-class product teams are winning in the AI era by CEO and Founder, P...Product School
 
IOS-PENTESTING-BEGINNERS-PRACTICAL-GUIDE-.pptx
IOS-PENTESTING-BEGINNERS-PRACTICAL-GUIDE-.pptxIOS-PENTESTING-BEGINNERS-PRACTICAL-GUIDE-.pptx
IOS-PENTESTING-BEGINNERS-PRACTICAL-GUIDE-.pptxAbida Shariff
 

Recently uploaded (20)

Designing Great Products: The Power of Design and Leadership by Chief Designe...
Designing Great Products: The Power of Design and Leadership by Chief Designe...Designing Great Products: The Power of Design and Leadership by Chief Designe...
Designing Great Products: The Power of Design and Leadership by Chief Designe...
 
Measures in SQL (a talk at SF Distributed Systems meetup, 2024-05-22)
Measures in SQL (a talk at SF Distributed Systems meetup, 2024-05-22)Measures in SQL (a talk at SF Distributed Systems meetup, 2024-05-22)
Measures in SQL (a talk at SF Distributed Systems meetup, 2024-05-22)
 
Introduction to Open Source RAG and RAG Evaluation
Introduction to Open Source RAG and RAG EvaluationIntroduction to Open Source RAG and RAG Evaluation
Introduction to Open Source RAG and RAG Evaluation
 
When stars align: studies in data quality, knowledge graphs, and machine lear...
When stars align: studies in data quality, knowledge graphs, and machine lear...When stars align: studies in data quality, knowledge graphs, and machine lear...
When stars align: studies in data quality, knowledge graphs, and machine lear...
 
De-mystifying Zero to One: Design Informed Techniques for Greenfield Innovati...
De-mystifying Zero to One: Design Informed Techniques for Greenfield Innovati...De-mystifying Zero to One: Design Informed Techniques for Greenfield Innovati...
De-mystifying Zero to One: Design Informed Techniques for Greenfield Innovati...
 
Empowering NextGen Mobility via Large Action Model Infrastructure (LAMI): pav...
Empowering NextGen Mobility via Large Action Model Infrastructure (LAMI): pav...Empowering NextGen Mobility via Large Action Model Infrastructure (LAMI): pav...
Empowering NextGen Mobility via Large Action Model Infrastructure (LAMI): pav...
 
Dev Dives: Train smarter, not harder – active learning and UiPath LLMs for do...
Dev Dives: Train smarter, not harder – active learning and UiPath LLMs for do...Dev Dives: Train smarter, not harder – active learning and UiPath LLMs for do...
Dev Dives: Train smarter, not harder – active learning and UiPath LLMs for do...
 
Kubernetes & AI - Beauty and the Beast !?! @KCD Istanbul 2024
Kubernetes & AI - Beauty and the Beast !?! @KCD Istanbul 2024Kubernetes & AI - Beauty and the Beast !?! @KCD Istanbul 2024
Kubernetes & AI - Beauty and the Beast !?! @KCD Istanbul 2024
 
From Siloed Products to Connected Ecosystem: Building a Sustainable and Scala...
From Siloed Products to Connected Ecosystem: Building a Sustainable and Scala...From Siloed Products to Connected Ecosystem: Building a Sustainable and Scala...
From Siloed Products to Connected Ecosystem: Building a Sustainable and Scala...
 
JMeter webinar - integration with InfluxDB and Grafana
JMeter webinar - integration with InfluxDB and GrafanaJMeter webinar - integration with InfluxDB and Grafana
JMeter webinar - integration with InfluxDB and Grafana
 
Search and Society: Reimagining Information Access for Radical Futures
Search and Society: Reimagining Information Access for Radical FuturesSearch and Society: Reimagining Information Access for Radical Futures
Search and Society: Reimagining Information Access for Radical Futures
 
Future Visions: Predictions to Guide and Time Tech Innovation, Peter Udo Diehl
Future Visions: Predictions to Guide and Time Tech Innovation, Peter Udo DiehlFuture Visions: Predictions to Guide and Time Tech Innovation, Peter Udo Diehl
Future Visions: Predictions to Guide and Time Tech Innovation, Peter Udo Diehl
 
Knowledge engineering: from people to machines and back
Knowledge engineering: from people to machines and backKnowledge engineering: from people to machines and back
Knowledge engineering: from people to machines and back
 
Free and Effective: Making Flows Publicly Accessible, Yumi Ibrahimzade
Free and Effective: Making Flows Publicly Accessible, Yumi IbrahimzadeFree and Effective: Making Flows Publicly Accessible, Yumi Ibrahimzade
Free and Effective: Making Flows Publicly Accessible, Yumi Ibrahimzade
 
ODC, Data Fabric and Architecture User Group
ODC, Data Fabric and Architecture User GroupODC, Data Fabric and Architecture User Group
ODC, Data Fabric and Architecture User Group
 
UiPath Test Automation using UiPath Test Suite series, part 2
UiPath Test Automation using UiPath Test Suite series, part 2UiPath Test Automation using UiPath Test Suite series, part 2
UiPath Test Automation using UiPath Test Suite series, part 2
 
Optimizing NoSQL Performance Through Observability
Optimizing NoSQL Performance Through ObservabilityOptimizing NoSQL Performance Through Observability
Optimizing NoSQL Performance Through Observability
 
Software Delivery At the Speed of AI: Inflectra Invests In AI-Powered Quality
Software Delivery At the Speed of AI: Inflectra Invests In AI-Powered QualitySoftware Delivery At the Speed of AI: Inflectra Invests In AI-Powered Quality
Software Delivery At the Speed of AI: Inflectra Invests In AI-Powered Quality
 
How world-class product teams are winning in the AI era by CEO and Founder, P...
How world-class product teams are winning in the AI era by CEO and Founder, P...How world-class product teams are winning in the AI era by CEO and Founder, P...
How world-class product teams are winning in the AI era by CEO and Founder, P...
 
IOS-PENTESTING-BEGINNERS-PRACTICAL-GUIDE-.pptx
IOS-PENTESTING-BEGINNERS-PRACTICAL-GUIDE-.pptxIOS-PENTESTING-BEGINNERS-PRACTICAL-GUIDE-.pptx
IOS-PENTESTING-BEGINNERS-PRACTICAL-GUIDE-.pptx
 

Features image processing and Extaction

  • 2. We will discuss shape-based representations (external), features based on texture and statistical moments (internal) . look at principal component analysis (PCA), a statistical method which has been widely applied to image processing problems. We are assume that an image has undergone segmentation.
  • 3. The common goal of feature extraction and representation techniques is to convert the segmented objects into representations that better describe their main features and attributes. The type and complexity of the resulting representation depend on many factors, such as the type of image (e.g., binary, grayscale, or color), the level of granularity (entire image or individual regions) desired.
  • 4. Feature extraction is the process by which certain features of interest within an image are detected and represented for further processing. It is a critical step in most computer vision and image processing solutions because it marks the transition from pictorial to nonpictorial (alphanumerical, usually quantitative) data representation.
  • 5. The aim is to process the image in such a way that the image, or properties of it, can be adequately represented and extracted in a compact form amenable to subsequent recognition and classification. Representations are typically of two basic kinds:  internal (which relates to the pixels comprising a region)  or external (which relates to the boundary of a region).
  • 6. A feature vector is a n × 1 array that encodes the n features (or measurements) of an image or object. The array contents may be:  symbolic (e.g., a string containing the name of the predominant color in the image)  numerical (e.g., an integer expressing the area of an object, in pixels) I’ll interested in.  or both
  • 7. A very basic representation of a shape simply requires the identification of a number N of points along the boundary of the features. In two dimensions, this is simply.
  • 8. A common requirement for feature extraction and representation techniques is that the features used to represent an image be invariant to rotation, scaling, and translation, collectively known as RST. RST invariance ensures that a machine vision system will still be able to recognize objects even when they appear at different size, position within the image, and angle (relative to a horizontal reference).
  • 9. A binary object, in this case, is a connected region within a binary image f (x, y), which will be denoted as Oi, i > 0. Mathematically, we can define a function Oi(x, y) as follows: Oi(x, y) = 1 if f (x, y) ∈ Oi 0 otherwise The matlab function bwlabel, pixels labeled 0 correspond to the background; pixels labeled 1 and higher correspond to the connected components in the image.
  • 10. we mean that the selected coordinates constituting the boundary/shape must be chosen in such a way as to ensure close agreement across a group of observers. If this were not satisfied, then different observers would define completely different shape vectors for what is actually the same shape. achieved by defining criteria for identifying appropriate and well-defined key points along the boundaries , Such key points are called landmarks
  • 11. Landmarks essentially divide into three categories: Mathematical landmarks Anatomical or true landmarks Pseudo-landmarks
  • 12. These correspond to points located on an object according to some mathematical or geometric property (e.g. according to local gradient, curvature or some extremum value).
  • 13.
  • 14. These are points assigned by an expert which are identifiable in (and correspond between) different members of a class of objects. Examples of anatomical landmarks are the corners of the mouth and eyes in human faces.
  • 15. These are points which are neither mathematically nor anatomically completely well defined, though they may certainly be intuitively meaningful and/or require some skilled judgment on the part of an operator. An example of a pseudo landmark might be the ‘ centre of the cheek bones’ in a human face, because the visual information is not definite enough to allow unerring placement.
  • 16. • Anatomical landmarks (indicated in red) are located at points which can be easily identified visually. • Mathematical landmarks (black crosses) are identified at points of zero gradient and maximum corner content. • The pseudo-landmarks are indicated by green circles
  • 17. In certain applications, we do not require a shape analysis/recognition technique to provide a precise, regenerative representation of the shape. The aim is simply to characterize a shape as succinctly as possible in order that it can be differentiated from other shapes and classified accordingly.
  • 18. a small number of descriptors or even a single parameter can be sufficient to achieve this task. Note that many of these measures can be derived from knowledge of the perimeter length.
  • 19. The following Table gives a number of common, single-parameter measures of approximate shape which can be employed as shape features in basic tasks of discrimination and classification. Note that many of these measures can be derived from knowledge of the perimeter length, the extreme x and y values and the total area enclosed by the boundary – quantities which can be calculated easily in practice.
  • 20.
  • 21. 1. Area The area of the ith object Oi, measured in pixels, is given by: 2. Centroid The coordinates of the centroid (also known as center of area) of object Oi, denoted (x¯i, y¯i), are given by: or
  • 22. 3. Projections The horizontal and vertical projections of a binary object—hi(x) and vi(y), respectively—are obtained by equations: and
  • 23. Projections are very useful and compact shape descriptors. For example, the height and width of an object without holes can be computed as the maximum value of the object’s vertical and horizontal projections, respectively, as illustrated in Figure:
  • 24. 4. Thinness Ratio The thinness ratio Ti of a binary object Oi is a figure of merit that relates the object’s area and its perimeter by equation Ti = (4πAi)/(Pi^2) where Ai is the area and Pi is the perimeter
  • 25. The thinness ratio is often used as a measure of roundness. Since the maximum value for Ti is 1 (which corresponds to a perfect circle), for a generic object the higher its thinness ratio, the more round it is. This figure of merit can also be used as a measure of regularity and its inverse, 1/Ti is sometimes called irregularity or compactness ratio.
  • 26. A=imread('coins_and_keys.png'); subplot(1,2,1), imshow(A); %Read in image and display bw=~im2bw(rgb2gray(A),0.35); bw=imfill(bw,'holes'); %Threshold and fill in holes bw=imopen(bw,ones(5)); subplot(1,2,2), imshow(bw,[0 1]); %Morphological opening [L,num]=bwlabel(bw); %Create labelled image s=regionprops(L,'area','perimeter'); %Calculate region properties for i=1:num %object’s area and perimeter x(i)=s(i).Area; y(i)=s(i).Perimeter; form(i)=4.*pi.*x(i)./(y(i).^2); %Calculate form factor end figure; plot(x./max(x),form,'ro'); %Plot area against form factor % regionprops Measure properties of image regions
  • 27.
  • 28. The key and drill bit are easily distinguished from the coins by their form-factor values. However, the imperfect result from thresholding means that the form factor is unable to distinguish between the heptagonal coins and circular coins. These are, however, easily separated by area.
  • 29. 1. Chain Code, Freeman Code, and Shape Number: A chain code : is a boundary representation technique by which a contour is represented as a sequence of straight line segments of specified length (usually 1) and direction.
  • 30.
  • 31. Once the chain code for a boundary has been computed, it is possible to convert the resulting array into a rotation-invariant equivalent, known as the first difference
  • 32.
  • 33.
  • 34. Fourier Descriptor Fourier descriptor: view a coordinate (x,y) as a complex number (x = real part and y = imaginary part) then apply the Fourier transform to a sequence of boundary points. )()()( kjykxks       1 0 /2 )( 1 )( K k Kuk eks K ua  Fourier descriptor :     1 0 /2 )( 1 )( K k Kuk eua K ks  Let s(k) be a coordinate of a boundary point k : Reconstruction formula Boundary points
  • 35. Example: Fourier Descriptor Examples of reconstruction from Fourier descriptors     1 0 /2 )( 1 )(ˆ P k Kuk eua K ks  P is the number of Fourier coefficients used to reconstruct the boundary
  • 36. Fourier Descriptor Properties Some properties of Fourier descriptors