Image Processing and Pattern Recognition Jouko Lampinen.
-
date post
20-Dec-2015 -
Category
Documents
-
view
230 -
download
5
Transcript of Image Processing and Pattern Recognition Jouko Lampinen.
![Page 1: Image Processing and Pattern Recognition Jouko Lampinen.](https://reader036.fdocuments.net/reader036/viewer/2022062516/56649d445503460f94a213e4/html5/thumbnails/1.jpg)
Image Processing and Pattern Recognition
Jouko Lampinen
![Page 2: Image Processing and Pattern Recognition Jouko Lampinen.](https://reader036.fdocuments.net/reader036/viewer/2022062516/56649d445503460f94a213e4/html5/thumbnails/2.jpg)
About this presentation
• In this set of slides we illustrate a bigger problem which uses both morphological operations and other operations that will be introduced soon.
• In most cases we use morphological operations together with other operations.
• The most important reason of using them is speed and non-linear processing.
![Page 3: Image Processing and Pattern Recognition Jouko Lampinen.](https://reader036.fdocuments.net/reader036/viewer/2022062516/56649d445503460f94a213e4/html5/thumbnails/3.jpg)
Image analysis of grain material in concrete production
• Images captured by standard
1200 dpi color scanner • Grain shape inputs
• angularity, flakiness• Grain texture inputs
• Boundary & surface texture• FFT based texture features
• Image Analysis Tool:
Matlab standalone application• Quality Control Tool:
Excel macro package for running
and analyzing the Bayesian
models (to be discussed)
![Page 4: Image Processing and Pattern Recognition Jouko Lampinen.](https://reader036.fdocuments.net/reader036/viewer/2022062516/56649d445503460f94a213e4/html5/thumbnails/4.jpg)
Example of grains (1.6-2.0 mm sieve fraction)
![Page 5: Image Processing and Pattern Recognition Jouko Lampinen.](https://reader036.fdocuments.net/reader036/viewer/2022062516/56649d445503460f94a213e4/html5/thumbnails/5.jpg)
Grain FeaturesGrain Features Measured from the Image
• Area• Major Axis • Minor Axis• Eccentricity• Convex Area• Equivalent Diameter• Solidity• Perimeter• Compactness• Borderline FFT (5 features related to roughness)• Texture 2D FFT (5 features related to surface structure) • Morphological Spectrum (roundness)
Most of these parameters will be presented in next lectures
![Page 6: Image Processing and Pattern Recognition Jouko Lampinen.](https://reader036.fdocuments.net/reader036/viewer/2022062516/56649d445503460f94a213e4/html5/thumbnails/6.jpg)
Object size and shape characterization
• Bounding box (rotated along principal axes)• Ellipsoid determined by the principal axes • Convex hull
![Page 7: Image Processing and Pattern Recognition Jouko Lampinen.](https://reader036.fdocuments.net/reader036/viewer/2022062516/56649d445503460f94a213e4/html5/thumbnails/7.jpg)
Original sand grain image (natural sand)
![Page 8: Image Processing and Pattern Recognition Jouko Lampinen.](https://reader036.fdocuments.net/reader036/viewer/2022062516/56649d445503460f94a213e4/html5/thumbnails/8.jpg)
Thresholded image (natural grains)
![Page 9: Image Processing and Pattern Recognition Jouko Lampinen.](https://reader036.fdocuments.net/reader036/viewer/2022062516/56649d445503460f94a213e4/html5/thumbnails/9.jpg)
Objects filled
![Page 10: Image Processing and Pattern Recognition Jouko Lampinen.](https://reader036.fdocuments.net/reader036/viewer/2022062516/56649d445503460f94a213e4/html5/thumbnails/10.jpg)
Morphological opening (yellow pixels removed)
![Page 11: Image Processing and Pattern Recognition Jouko Lampinen.](https://reader036.fdocuments.net/reader036/viewer/2022062516/56649d445503460f94a213e4/html5/thumbnails/11.jpg)
Labelled objects
![Page 12: Image Processing and Pattern Recognition Jouko Lampinen.](https://reader036.fdocuments.net/reader036/viewer/2022062516/56649d445503460f94a213e4/html5/thumbnails/12.jpg)
Bounding boxes and minor/major axes
![Page 13: Image Processing and Pattern Recognition Jouko Lampinen.](https://reader036.fdocuments.net/reader036/viewer/2022062516/56649d445503460f94a213e4/html5/thumbnails/13.jpg)
Original sand grain image (crushed)
![Page 14: Image Processing and Pattern Recognition Jouko Lampinen.](https://reader036.fdocuments.net/reader036/viewer/2022062516/56649d445503460f94a213e4/html5/thumbnails/14.jpg)
Thresholded image (crushed)
![Page 15: Image Processing and Pattern Recognition Jouko Lampinen.](https://reader036.fdocuments.net/reader036/viewer/2022062516/56649d445503460f94a213e4/html5/thumbnails/15.jpg)
Objects filled
![Page 16: Image Processing and Pattern Recognition Jouko Lampinen.](https://reader036.fdocuments.net/reader036/viewer/2022062516/56649d445503460f94a213e4/html5/thumbnails/16.jpg)
Morphological opening (yellow pixels removed)
![Page 17: Image Processing and Pattern Recognition Jouko Lampinen.](https://reader036.fdocuments.net/reader036/viewer/2022062516/56649d445503460f94a213e4/html5/thumbnails/17.jpg)
Labelled objects
![Page 18: Image Processing and Pattern Recognition Jouko Lampinen.](https://reader036.fdocuments.net/reader036/viewer/2022062516/56649d445503460f94a213e4/html5/thumbnails/18.jpg)
Bounding boxes and minor/major axes
![Page 19: Image Processing and Pattern Recognition Jouko Lampinen.](https://reader036.fdocuments.net/reader036/viewer/2022062516/56649d445503460f94a213e4/html5/thumbnails/19.jpg)
Grain shape analysis: angularity
Sharp angles in grains break under compression
Measurement: simulate the erosion due to Ice Age by morphological erosion
Morphological spectrum:
S(r)
Amount of material removed by circular structure element of radius r
Feature space!!
![Page 20: Image Processing and Pattern Recognition Jouko Lampinen.](https://reader036.fdocuments.net/reader036/viewer/2022062516/56649d445503460f94a213e4/html5/thumbnails/20.jpg)
Example of Morphological Spectra and Angularity
Crushed gravel Natural gravel (manufactured by Ice Age)
Morphological spectrumWe can scientifically
compare various gravels