# Mathematical Morphology

a non exhaustive overview

Mathematical Morphology
• Shape oriented operations, that “ simplify image data, preserving their essential shape characteristics and eliminating irrelevancies” [Haralick87]

Mathematical Morphology

2

Overview
• Basic morphological operators • More complex operations • Conclusion and References

Mathematical Morphology

3

Overview
• Basic morphological operators
– Binary – Grayscale – Color – Structuring element

• More complex operations • Conclusion and References

Mathematical Morphology

4

Basic operators: binary • Dilation . erosion  by a structuring element Mathematical Morphology 5 .

Basic operators: binary • Opening ° : remove capes. isthmus and islands smaller than the structuring element   Mathematical Morphology 6 .

channels and lakes smaller than the structuring element   Mathematical Morphology 7 .Basic operators: binary • Closing ° : fill gulfs.

Basic operators: binary • Sequencial filter: open-close or close-open Mathematical Morphology 8 .

Overview • Basic morphological operators – Binary – Grayscale – Color – Structuring element • More complex operations • Conclusion and References Mathematical Morphology 9 .

Basic operator: grayscale • Dilation : max over the structuring element Mathematical Morphology 10 .

Basic operator: grayscale • Erosion : min over the structuring element Mathematical Morphology 11 .

Basic operator: grayscale • Opening ° : remove light features smaller than the structuring element Mathematical Morphology 12 .

Basic operator: grayscale • Closing ° : remove dark features smaller than the structuring element Mathematical Morphology 13 .

Basic operator: grayscale • Sequential filter (open-close or close-open): remove both light and dark features Mathematical Morphology 14 .

Overview • Basic morphological operators – Binary – Grayscale – Color – Structuring element • More complex operations • Conclusion and References Mathematical Morphology 15 .

Color images • Process each channel separately: color ghosting with basic operators  Mathematical Morphology 16 .

Color images • Process each channel separately: color ghosting unnoticeable with sequential operators opening Mathematical Morphology 17 .

Color images • Several ordering strategy Mathematical Morphology 18 .

Overview • Basic morphological operators – Binary – Grayscale – Color – Structuring element • More complex operations • Conclusion and References Mathematical Morphology 19 .

flat element (binary) • Grayscale element: fuzzy morphology Mathematical Morphology 20 .Structuring element • Usually.

Structuring element • Shape has an impact! Mathematical Morphology 21 .

Structuring element • Choose the structuring element according to the image structure  Mathematical Morphology 22 .

Structuring element • Choose the structuring element according to the image structure Mathematical Morphology 23 .

Overview • Basic morphological operators • More complex operations – Reconstruction operators – Top hat. thinning. sharpening.. segmentation. distance.. • Conclusion and References Mathematical Morphology 24 .

Reconstruction operators • Remove features smaller than the structuring element. without altering the shape • Reconstruct connected components from the preserved features Mathematical Morphology 25 .

I) until stability Mathematical Morphology 26 .Reconstruction operators: binary • Opening by reconstruction: – Erosion: f'(0) = f – Iterative reconstruction: f'(t+1) = min(f'(t).

I) until stability Mathematical Morphology 27 .Reconstruction operators: binary • Closing by reconstruction: – Dilation: f'(0) = f – Iterative reconstruction: f'(t+1) = max(f'(t).

Reconstruction operators: grayscale • Opening by reconstruction: remove unconnected light features Mathematical Morphology 28 .

Reconstruction operators: grayscale • Closing by reconstruction: remove unconnected dark features Mathematical Morphology 29 .

Reconstruction operators: grayscale • Sequential filter by reconstruction: open-close Mathematical Morphology 30 .

• Conclusion and References Mathematical Morphology 31 .Overview • Basic morphological operators • More complex operations – Reconstruction operators – Top hat. segmentation. distance.. sharpening.. thinning.

Top Hat • White top-hat: f-opening(f) Extract light features Mathematical Morphology 32 .

Top Hat • Black top-hat: closing(f)-f Extract dark features Mathematical Morphology 33 .

Edge sharpening • Toggle mapping f f f (f+f)/2 Mathematical Morphology 34 .

Edge sharpening • Toggle mapping Mathematical Morphology 35 .

Distance function • Distance from binary elements Mathematical Morphology 36 .

Thinning • Binary (or grayscale ?) skeleton Mathematical Morphology 37 .

Segmentation • Watershed: – Image = heightfield – Flood the image from its minima – Lake junctions give the segmentation Mathematical Morphology 38 .

Segmentation • Watershed: hierarchical results Mathematical Morphology 39 .

Overview • Basic morphological operators • More complex operations • Conclusion and References Mathematical Morphology 40 .

Conclusion • Powerful toolbox for many image analysis tasks • Not famous because not useful? • Not used because not famous? • Based on a whole mathematical theory • But can be very practical (maybe too much?) • French! Mathematical Morphology 41 .

(Practical approach) • Jean Serra and Luc Vincent. 2003: Morphological Image Analysis. 1992: An Overview of Morphological Filtering.References • Pierre Soille. (Mathematical approach) Mathematical Morphology 42 . Principles and Applications.