Presentation is loading. Please wait.

Presentation is loading. Please wait.

Image Processing and Pattern Recognition

Similar presentations


Presentation on theme: "Image Processing and Pattern Recognition"— Presentation transcript:

1 Image Processing and Pattern Recognition
Jouko Lampinen

2 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.

3 Problem Various types of grain materials are used in concrete production We want to characterize features of grains We want to characterize sets of grains and classify them We want to look to similarities and dissimilarities We use morphological, other shape based methods and spectral methods as well as Machine Learning software

4 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)

5 Example of grains (1.6-2.0 mm sieve fraction)

6 Most of these parameters will be presented in next lectures
Grain 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

7 Object size and shape characterization
Bounding box (rotated along principal axes) Ellipsoid determined by the principal axes Convex hull

8 Original sand grain image (natural sand)

9 Thresholded image (natural grains)

10 Objects filled

11 Morphological opening (yellow pixels removed)

12 Labelled objects

13 Bounding boxes and minor/major axes

14 Original sand grain image (crushed)

15 Thresholded image (crushed)

16 Objects filled

17 Morphological opening (yellow pixels removed)

18 Labelled objects

19 Bounding boxes and minor/major axes

20 Grain shape analysis: angularity
Feature space!! 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

21 Example of Morphological Spectra and Angularity
Natural gravel (manufactured by Ice Age) Crushed gravel We can scientifically compare various gravels Morphological spectrum


Download ppt "Image Processing and Pattern Recognition"

Similar presentations


Ads by Google