1 machine vision. 2 vision the most powerful sense
TRANSCRIPT
![Page 1: 1 Machine Vision. 2 VISION the most powerful sense](https://reader035.vdocument.in/reader035/viewer/2022062322/5697c00b1a28abf838cc8277/html5/thumbnails/1.jpg)
1
Machine Vision
![Page 2: 1 Machine Vision. 2 VISION the most powerful sense](https://reader035.vdocument.in/reader035/viewer/2022062322/5697c00b1a28abf838cc8277/html5/thumbnails/2.jpg)
2
VISION
the most powerful sense
![Page 3: 1 Machine Vision. 2 VISION the most powerful sense](https://reader035.vdocument.in/reader035/viewer/2022062322/5697c00b1a28abf838cc8277/html5/thumbnails/3.jpg)
3
OUTLINE
1. Properties of Machine Vision Systems
Methods in Machine Vision
2. Example: Fingerprint Recognition System
![Page 4: 1 Machine Vision. 2 VISION the most powerful sense](https://reader035.vdocument.in/reader035/viewer/2022062322/5697c00b1a28abf838cc8277/html5/thumbnails/4.jpg)
4
Machine Vision System
• creates a model of the real world from images
• recovers useful information about a scene from its two dimensional projections
![Page 5: 1 Machine Vision. 2 VISION the most powerful sense](https://reader035.vdocument.in/reader035/viewer/2022062322/5697c00b1a28abf838cc8277/html5/thumbnails/5.jpg)
5
A typical control system:
Scene Image Description
Application feedback
Imaging device
MACHINE VISION
Illumination
![Page 6: 1 Machine Vision. 2 VISION the most powerful sense](https://reader035.vdocument.in/reader035/viewer/2022062322/5697c00b1a28abf838cc8277/html5/thumbnails/6.jpg)
6
Components of a M.V. system
HARDWARESOFTWARE
• Optics (lenses, lighting)• Cameras • Interface (frame grabber)• Computer
![Page 7: 1 Machine Vision. 2 VISION the most powerful sense](https://reader035.vdocument.in/reader035/viewer/2022062322/5697c00b1a28abf838cc8277/html5/thumbnails/7.jpg)
7
Components of a M.V. system
HARDWARESOFTWARE
-There is no universal vision system-One system for each application
• Libraries with custom code developed using Visual C/C++, Visual Basic, or Java
• Graphical programming environments
![Page 8: 1 Machine Vision. 2 VISION the most powerful sense](https://reader035.vdocument.in/reader035/viewer/2022062322/5697c00b1a28abf838cc8277/html5/thumbnails/8.jpg)
8
Application Fields
• Medical imaging• Industrial automation • Robotics • Radar Imaging • Forensics • Remote Sensing • Cartography • Character recognition
![Page 9: 1 Machine Vision. 2 VISION the most powerful sense](https://reader035.vdocument.in/reader035/viewer/2022062322/5697c00b1a28abf838cc8277/html5/thumbnails/9.jpg)
9
Machine Vision StagesImage Acquisition
Image Processing
Image Segmentation
Image Analysis
Pattern Recognition
Analog to digital conversion
Remove noise,improve contrast…
Find regions (objects) in the image
Take measurements of objects/relationships
Match the description withsimilar description of known objects (models)
![Page 10: 1 Machine Vision. 2 VISION the most powerful sense](https://reader035.vdocument.in/reader035/viewer/2022062322/5697c00b1a28abf838cc8277/html5/thumbnails/10.jpg)
10
Image Formation
• Perspective projection
• Orthographic projection
3D 2DProjection
![Page 11: 1 Machine Vision. 2 VISION the most powerful sense](https://reader035.vdocument.in/reader035/viewer/2022062322/5697c00b1a28abf838cc8277/html5/thumbnails/11.jpg)
11
Digital Image Representation
Image: 2D array of gray level or color values
Pixel: Array element Picture Element
•It`s 2D•It`s a square•It has one color•It may be any color
Pixel value: Arithmetic value of gray level or color intensity
Gray level image: f = f(x,y) Color image: f = {Rred(x,y), Ggreen(x,y), Bblue(x,y)}
![Page 12: 1 Machine Vision. 2 VISION the most powerful sense](https://reader035.vdocument.in/reader035/viewer/2022062322/5697c00b1a28abf838cc8277/html5/thumbnails/12.jpg)
12
Digital Image Formation
• Sampling rate (resolution)
• Quantization level
Sampling Quantization
![Page 13: 1 Machine Vision. 2 VISION the most powerful sense](https://reader035.vdocument.in/reader035/viewer/2022062322/5697c00b1a28abf838cc8277/html5/thumbnails/13.jpg)
13
Different Sampling Rates
![Page 14: 1 Machine Vision. 2 VISION the most powerful sense](https://reader035.vdocument.in/reader035/viewer/2022062322/5697c00b1a28abf838cc8277/html5/thumbnails/14.jpg)
14
Different Quantization Levels
![Page 15: 1 Machine Vision. 2 VISION the most powerful sense](https://reader035.vdocument.in/reader035/viewer/2022062322/5697c00b1a28abf838cc8277/html5/thumbnails/15.jpg)
15
Image Processing (IP)
Input Image Output Image
Image Processing
FilteringSmoothingThinning
ExpendingShrinking
Compressing…
![Page 16: 1 Machine Vision. 2 VISION the most powerful sense](https://reader035.vdocument.in/reader035/viewer/2022062322/5697c00b1a28abf838cc8277/html5/thumbnails/16.jpg)
16
Fundementals• Neigborhood
• Histogram: gray levels vs number of pixels
4-Neighbors 8-Neighbors
![Page 17: 1 Machine Vision. 2 VISION the most powerful sense](https://reader035.vdocument.in/reader035/viewer/2022062322/5697c00b1a28abf838cc8277/html5/thumbnails/17.jpg)
17
IP Examples
Removal of noise with median filter
![Page 18: 1 Machine Vision. 2 VISION the most powerful sense](https://reader035.vdocument.in/reader035/viewer/2022062322/5697c00b1a28abf838cc8277/html5/thumbnails/18.jpg)
18
IP Examples (2)
Improvement of contrast by histogram modification
![Page 19: 1 Machine Vision. 2 VISION the most powerful sense](https://reader035.vdocument.in/reader035/viewer/2022062322/5697c00b1a28abf838cc8277/html5/thumbnails/19.jpg)
19
Symethricalinversion of the image
IP Examples (3)
![Page 20: 1 Machine Vision. 2 VISION the most powerful sense](https://reader035.vdocument.in/reader035/viewer/2022062322/5697c00b1a28abf838cc8277/html5/thumbnails/20.jpg)
20
IP Examples (4)
Smoothing
Original Uniform Gaussian
![Page 21: 1 Machine Vision. 2 VISION the most powerful sense](https://reader035.vdocument.in/reader035/viewer/2022062322/5697c00b1a28abf838cc8277/html5/thumbnails/21.jpg)
21
Binary Image ProcessingWHY?
better efficiency in acquiring, storage,
processing and transmission
TRESHOLDING
![Page 22: 1 Machine Vision. 2 VISION the most powerful sense](https://reader035.vdocument.in/reader035/viewer/2022062322/5697c00b1a28abf838cc8277/html5/thumbnails/22.jpg)
22
Different tresholds
![Page 23: 1 Machine Vision. 2 VISION the most powerful sense](https://reader035.vdocument.in/reader035/viewer/2022062322/5697c00b1a28abf838cc8277/html5/thumbnails/23.jpg)
23
Image Segmentation
Input ImageRegionsObjects
Segmentation
-Clasify pixels into groups having similar characteristics
-Two techniques: Region segmentation
Edge detection
![Page 24: 1 Machine Vision. 2 VISION the most powerful sense](https://reader035.vdocument.in/reader035/viewer/2022062322/5697c00b1a28abf838cc8277/html5/thumbnails/24.jpg)
24
Region Segmentation
• Histogram Based
![Page 25: 1 Machine Vision. 2 VISION the most powerful sense](https://reader035.vdocument.in/reader035/viewer/2022062322/5697c00b1a28abf838cc8277/html5/thumbnails/25.jpg)
25
Region Segmentation (2)
• Split & Merge
![Page 26: 1 Machine Vision. 2 VISION the most powerful sense](https://reader035.vdocument.in/reader035/viewer/2022062322/5697c00b1a28abf838cc8277/html5/thumbnails/26.jpg)
26
Edge Detection
• Find the curves on the image where rapid changes occur
![Page 27: 1 Machine Vision. 2 VISION the most powerful sense](https://reader035.vdocument.in/reader035/viewer/2022062322/5697c00b1a28abf838cc8277/html5/thumbnails/27.jpg)
27
Image Analysis
Input ImageRegions, objects
Measurements
Image Analysis
Measurements:-Size -Position-Orientation-Spatial relationship-Gray scale or color intensity-Velocity
![Page 28: 1 Machine Vision. 2 VISION the most powerful sense](https://reader035.vdocument.in/reader035/viewer/2022062322/5697c00b1a28abf838cc8277/html5/thumbnails/28.jpg)
28
Pattern Recognition (PR)
- Measurements- Stuctural descriptions
Class identifier
PatternRecognition
feature vectorset of information data
![Page 29: 1 Machine Vision. 2 VISION the most powerful sense](https://reader035.vdocument.in/reader035/viewer/2022062322/5697c00b1a28abf838cc8277/html5/thumbnails/29.jpg)
29
Approaches to PR
Statistical
Structural
Neural
![Page 30: 1 Machine Vision. 2 VISION the most powerful sense](https://reader035.vdocument.in/reader035/viewer/2022062322/5697c00b1a28abf838cc8277/html5/thumbnails/30.jpg)
30
• 3D VISION
• Dynamic Vision
![Page 31: 1 Machine Vision. 2 VISION the most powerful sense](https://reader035.vdocument.in/reader035/viewer/2022062322/5697c00b1a28abf838cc8277/html5/thumbnails/31.jpg)
31
Fingerprint Recognition
- most precise identification biometric
- has many applications- has the largest database
![Page 32: 1 Machine Vision. 2 VISION the most powerful sense](https://reader035.vdocument.in/reader035/viewer/2022062322/5697c00b1a28abf838cc8277/html5/thumbnails/32.jpg)
32
![Page 33: 1 Machine Vision. 2 VISION the most powerful sense](https://reader035.vdocument.in/reader035/viewer/2022062322/5697c00b1a28abf838cc8277/html5/thumbnails/33.jpg)
33
Fingerprint recognition system
Fingerprintsensor
Fingerprintsensor
Feature Extractor
Feature Extractor
Feature Matcher
ID
Enrollment
Identification
Templatedatabase
![Page 34: 1 Machine Vision. 2 VISION the most powerful sense](https://reader035.vdocument.in/reader035/viewer/2022062322/5697c00b1a28abf838cc8277/html5/thumbnails/34.jpg)
34
Fingerprint Representation
Local Ridge Characteristics
•Ridge Ending•Ridge Bifurcation•Enclosure•Ridge Dot
![Page 35: 1 Machine Vision. 2 VISION the most powerful sense](https://reader035.vdocument.in/reader035/viewer/2022062322/5697c00b1a28abf838cc8277/html5/thumbnails/35.jpg)
35
Fingerprint Representation (2)
Singular PointsCoreDelta
Major Central Pattern
Arch Loop Whorl
![Page 36: 1 Machine Vision. 2 VISION the most powerful sense](https://reader035.vdocument.in/reader035/viewer/2022062322/5697c00b1a28abf838cc8277/html5/thumbnails/36.jpg)
36
Image Processing & Analysis for Fingerprint Recognition
Pre-processing Minutiae Extraction
Post-processing
Input Image
•Binarization
•Noise Removal
•Smoothing
•Thinning
•Ridge break removal
•Bridge removal
•Spike removal
Processed Image
+Minutiae
Description
Outputs
![Page 37: 1 Machine Vision. 2 VISION the most powerful sense](https://reader035.vdocument.in/reader035/viewer/2022062322/5697c00b1a28abf838cc8277/html5/thumbnails/37.jpg)
37
Pre-Processing• Binarization
search through array pixel by pixel;
if current byte colour value is above threshold then
change value to white;
else
change colour to black
• Noise Removal if the pixel is white and all immediate surrounding pixels are
black
then
change pixel to black;
else if the pixel is black and all immediate surrounding pixels are white then
change pixel to white;
![Page 38: 1 Machine Vision. 2 VISION the most powerful sense](https://reader035.vdocument.in/reader035/viewer/2022062322/5697c00b1a28abf838cc8277/html5/thumbnails/38.jpg)
38
Pre-Processing(2)
• Smoothingfor each pixel do
add the values of surrounding pixels;
divide by the number of surrounding pixels (usually 8 unless
at the edge);
assign current pixel the calculated result;
• Thinning
![Page 39: 1 Machine Vision. 2 VISION the most powerful sense](https://reader035.vdocument.in/reader035/viewer/2022062322/5697c00b1a28abf838cc8277/html5/thumbnails/39.jpg)
39
Extractionif pixel has exactly one neighbour then
pixel is a ridge ending;calculate x value of pixel;calculate y value of pixel;
calculate angle of ridge ending;write data to database;
else if pixel has exactly three neighbours thenpixel is a bifurcation;
calculate x value of pixel;calculate y value of pixel;
calculate angle of bifurcation;write data to database;
![Page 40: 1 Machine Vision. 2 VISION the most powerful sense](https://reader035.vdocument.in/reader035/viewer/2022062322/5697c00b1a28abf838cc8277/html5/thumbnails/40.jpg)
40
Post-Processing• Ridge break removalIf A and B are facing each other and are less then a minimum
distance (D) then
A and B are false minutia points;
remove A and B from ridge end point set;
update database;
Bridge removal
• Spike removalFor each ridge ending point (A)
For each bifurcation point (B)
If A and B are less than minimum distance (D)apart and they are connected then
A and B are false minutia points;
remove A and B from their sets;
![Page 41: 1 Machine Vision. 2 VISION the most powerful sense](https://reader035.vdocument.in/reader035/viewer/2022062322/5697c00b1a28abf838cc8277/html5/thumbnails/41.jpg)
41
Matching
![Page 42: 1 Machine Vision. 2 VISION the most powerful sense](https://reader035.vdocument.in/reader035/viewer/2022062322/5697c00b1a28abf838cc8277/html5/thumbnails/42.jpg)
42
References[1] MACHINE VISION
Jain-Kasturi-Schunck[2] EE 701 Robot Vision Lecture Notes
A. Aydin Alatan – METU[3] Tutorial on Machine Vision
Petrakis[4] Multimodel User Interfaces
Anil Jain[5] Automatic Fingerprint Recognition System
Tony Walsh
![Page 43: 1 Machine Vision. 2 VISION the most powerful sense](https://reader035.vdocument.in/reader035/viewer/2022062322/5697c00b1a28abf838cc8277/html5/thumbnails/43.jpg)
43
THANK YOU!