9 Morphological Image Processing.ppt [相容模式]

Post on 10-Feb-2022

11 views 1 download

transcript

9 MORPHOLOGICAL IMAGE PROCESSING

Chih-Wei TangDepartment of Communication Engineering

National Central UniversityJhongLi, Taiwan

Outline• Preliminaries• Dilation and erosion• Opening and closing• Some basic morphological algorithms• Extensions to gray-scale images

C.E., NCU, Taiwan 2

Basic Concepts from Set Theory

C.E., NCU, Taiwan 3

• Sets: objects in an image• Set theory: the language of mathematical

morphology

C.E., NCU, Taiwan 4

C.E., NCU, Taiwan 5

C.E., NCU, Taiwan 6

C.E., NCU, Taiwan 7

C.E., NCU, Taiwan 8

Translation and Reflection

C.E., NCU, Taiwan 9

• They are extended from morphology but not found in basic texts on set theory.

C.E., NCU, Taiwan 10

Outline

Preliminaries Dilation and erosion Opening and closing Some basic morphological algorithms Extensions to gray-scale images

C.E., NCU, Taiwan 11Reflection

Translation

Use of Morphological Dilation for Bridging Gaps

C.E., NCU, Taiwan 12

C.E., NCU, Taiwan 13

Use of Morphological Erosion for Removing Image Components

C.E., NCU, Taiwan 14

C.E., NCU, Taiwan 15

Outline

Preliminaries Dilation and erosion Opening and closing Some basic morphological algorithms Extensions to gray-scale images

Opening and Closing• Opening

• smooth the contour of an object• breaks narrow isthmuses• eliminates thin protrusions

• Closing• smooth sections of contours• generally fuses narrow breaks and long thin gulfs• eliminates small holes• fills gaps in the contour

C.E., NCU, Taiwan 16

Opening

C.E., NCU, Taiwan 17

Closing

C.E., NCU, Taiwan 18

Opening

Closing

C.E., NCU, Taiwan 19

Use of Opening and Closing for Morphological Filtering

C.E., NCU, Taiwan 20

C.E., NCU, Taiwan 21

Outline

Preliminaries Dilation and erosion Opening and closing Some basic morphological algorithms Extensions to gray-scale images

Boundary Extraction

C.E., NCU, Taiwan 22

StructureElement

Erosion

Example – Boundary Extraction

C.E., NCU, Taiwan 23

Region Filling

C.E., NCU, Taiwan 24

Dilation

Complement

Example – Region Filling

C.E., NCU, Taiwan 25

Extraction of Connected Components

C.E., NCU, Taiwan 26

Converge!!!1 If kk XX

kXY Let

C.E., NCU, Taiwan 27

Outline

Preliminaries Dilation and erosion Opening and closing Some basic morphological algorithms Extensions to gray-scale images

2-D Dilation

C.E., NCU, Taiwan 28

• General effects• If all the values of the structuring element

are positive, the output image tends to be brighter than the input.

• Dark details either are reduced or eliminated, depending on how their values and shapes relate to the structuring element used for dilation.

1-D Dilation

C.E., NCU, Taiwan 29

Correct?

2-D Erosion

• General effects• If all the elements of the structuring element

are positive, the output image tends to be darker than the input image.

• The effect of bright details in the input image that are smaller in area than the structuring element is reduced.

C.E., NCU, Taiwan 30

1-D Erosion

C.E., NCU, Taiwan 31

Correct?

Dilation and Erosion on A Gray-Scale Image

C.E., NCU, Taiwan 32

Gray-Scale Opening and Closing

C.E., NCU, Taiwan 33

Gray-Scale Opening and Closing –Example

C.E., NCU, Taiwan 34