What is Image Segmentation? Image Segmentation Methods Thresholding Boundary-based
Digital Image Processing CSC331 Image Segmentation 1.
-
Upload
warren-morton -
Category
Documents
-
view
234 -
download
5
Transcript of Digital Image Processing CSC331 Image Segmentation 1.
![Page 1: Digital Image Processing CSC331 Image Segmentation 1.](https://reader036.fdocuments.in/reader036/viewer/2022062301/56649e935503460f94b98d29/html5/thumbnails/1.jpg)
1
Digital Image ProcessingCSC331
Image Segmentation
![Page 2: Digital Image Processing CSC331 Image Segmentation 1.](https://reader036.fdocuments.in/reader036/viewer/2022062301/56649e935503460f94b98d29/html5/thumbnails/2.jpg)
2
Summery of previous lecture
• Similarity base Image Segmentation • Image Segmentation by thresholding– Global threshold– Adaptive/Dynamic threshold – Local threshold
![Page 3: Digital Image Processing CSC331 Image Segmentation 1.](https://reader036.fdocuments.in/reader036/viewer/2022062301/56649e935503460f94b98d29/html5/thumbnails/3.jpg)
3
Todays lecture
• There are two main approaches to region-based segmentation:
• Region growing • Region splitting and merging • Texture based segmentation • Color based
![Page 4: Digital Image Processing CSC331 Image Segmentation 1.](https://reader036.fdocuments.in/reader036/viewer/2022062301/56649e935503460f94b98d29/html5/thumbnails/4.jpg)
Region-Based Segmentation
• Edges and thresholds sometimes do not give good results for segmentation.
• Region-based segmentation is based on the connectivity of similar pixels in a region.– Each region must be uniform. – Connectivity of the pixels within the region is very
important.
• There are two main approaches to region-based segmentation: region growing and region splitting.
![Page 5: Digital Image Processing CSC331 Image Segmentation 1.](https://reader036.fdocuments.in/reader036/viewer/2022062301/56649e935503460f94b98d29/html5/thumbnails/5.jpg)
5
Working of Region growing • Start from a set of seed points and from these points grow the regions by
appending to each seed those neighbouring pixels that have similar properties
• The selection of the seed points depends on the problem. When a priory information is not available, clustering techniques can be used: compute the above mentioned properties at every pixel and use the centroids of clusters
• The selection of similarity criteria depends on the problem under consideration and the type of image data that is available
• Descriptors must be used in conjunction with connectivity (adjacency) information
• Formulation of a “stopping rule”. Growing a region should stop when no more pixels satisfy the criteria for inclusion in that region.
• When a model of the expected results is partially available, the consideration of additional criteria like the size of the region, the likeliness between a candidate pixel and the pixels grown so far, and the shape of the region can improve the performance of the algorithm.
![Page 6: Digital Image Processing CSC331 Image Segmentation 1.](https://reader036.fdocuments.in/reader036/viewer/2022062301/56649e935503460f94b98d29/html5/thumbnails/6.jpg)
6
To conclude
![Page 7: Digital Image Processing CSC331 Image Segmentation 1.](https://reader036.fdocuments.in/reader036/viewer/2022062301/56649e935503460f94b98d29/html5/thumbnails/7.jpg)
7
![Page 8: Digital Image Processing CSC331 Image Segmentation 1.](https://reader036.fdocuments.in/reader036/viewer/2022062301/56649e935503460f94b98d29/html5/thumbnails/8.jpg)
8
![Page 9: Digital Image Processing CSC331 Image Segmentation 1.](https://reader036.fdocuments.in/reader036/viewer/2022062301/56649e935503460f94b98d29/html5/thumbnails/9.jpg)
9
![Page 10: Digital Image Processing CSC331 Image Segmentation 1.](https://reader036.fdocuments.in/reader036/viewer/2022062301/56649e935503460f94b98d29/html5/thumbnails/10.jpg)
10
![Page 11: Digital Image Processing CSC331 Image Segmentation 1.](https://reader036.fdocuments.in/reader036/viewer/2022062301/56649e935503460f94b98d29/html5/thumbnails/11.jpg)
11
![Page 12: Digital Image Processing CSC331 Image Segmentation 1.](https://reader036.fdocuments.in/reader036/viewer/2022062301/56649e935503460f94b98d29/html5/thumbnails/12.jpg)
Region-Based SegmentationRegion Growing
![Page 13: Digital Image Processing CSC331 Image Segmentation 1.](https://reader036.fdocuments.in/reader036/viewer/2022062301/56649e935503460f94b98d29/html5/thumbnails/13.jpg)
Region-Based SegmentationRegion Growing
• Fig. 10.41 shows the histogram of Fig. 10.40 (a). It is difficult to segment the defects by thresholding methods. (Applying region growing methods are better in this case.)
Figure 10.41Figure 10.40(a)
![Page 14: Digital Image Processing CSC331 Image Segmentation 1.](https://reader036.fdocuments.in/reader036/viewer/2022062301/56649e935503460f94b98d29/html5/thumbnails/14.jpg)
Region splitting and merging
• I Iterative subdivision of the image in homogeneous regions (splitting).
• I Joining of the adjacent homogeneous regions (merging).
![Page 15: Digital Image Processing CSC331 Image Segmentation 1.](https://reader036.fdocuments.in/reader036/viewer/2022062301/56649e935503460f94b98d29/html5/thumbnails/15.jpg)
Region-Based SegmentationRegion Splitting and Merging
• Region splitting is the opposite of region growing.– First there is a large region (possible the entire image).– Then a predicate (measurement) is used to determine if
the region is uniform. – If not, then the method requires that the region be split
into two regions. – Then each of these two regions is independently tested by
the predicate (measurement). – This procedure continues until all resulting regions are
uniform.
![Page 16: Digital Image Processing CSC331 Image Segmentation 1.](https://reader036.fdocuments.in/reader036/viewer/2022062301/56649e935503460f94b98d29/html5/thumbnails/16.jpg)
16
![Page 17: Digital Image Processing CSC331 Image Segmentation 1.](https://reader036.fdocuments.in/reader036/viewer/2022062301/56649e935503460f94b98d29/html5/thumbnails/17.jpg)
17
![Page 18: Digital Image Processing CSC331 Image Segmentation 1.](https://reader036.fdocuments.in/reader036/viewer/2022062301/56649e935503460f94b98d29/html5/thumbnails/18.jpg)
18
![Page 19: Digital Image Processing CSC331 Image Segmentation 1.](https://reader036.fdocuments.in/reader036/viewer/2022062301/56649e935503460f94b98d29/html5/thumbnails/19.jpg)
19
![Page 20: Digital Image Processing CSC331 Image Segmentation 1.](https://reader036.fdocuments.in/reader036/viewer/2022062301/56649e935503460f94b98d29/html5/thumbnails/20.jpg)
20
Working of S and M
![Page 21: Digital Image Processing CSC331 Image Segmentation 1.](https://reader036.fdocuments.in/reader036/viewer/2022062301/56649e935503460f94b98d29/html5/thumbnails/21.jpg)
21
![Page 22: Digital Image Processing CSC331 Image Segmentation 1.](https://reader036.fdocuments.in/reader036/viewer/2022062301/56649e935503460f94b98d29/html5/thumbnails/22.jpg)
22
Original, 8x8, 16x16, 32x32
![Page 23: Digital Image Processing CSC331 Image Segmentation 1.](https://reader036.fdocuments.in/reader036/viewer/2022062301/56649e935503460f94b98d29/html5/thumbnails/23.jpg)
23
![Page 24: Digital Image Processing CSC331 Image Segmentation 1.](https://reader036.fdocuments.in/reader036/viewer/2022062301/56649e935503460f94b98d29/html5/thumbnails/24.jpg)
24
S and M compression with thresholding
![Page 25: Digital Image Processing CSC331 Image Segmentation 1.](https://reader036.fdocuments.in/reader036/viewer/2022062301/56649e935503460f94b98d29/html5/thumbnails/25.jpg)
25
• Different other segmentation methods,– Graph-Cut Segmentation– Watershed– Watershed with marker– Texture based segmentation – Color based etc.
![Page 26: Digital Image Processing CSC331 Image Segmentation 1.](https://reader036.fdocuments.in/reader036/viewer/2022062301/56649e935503460f94b98d29/html5/thumbnails/26.jpg)
26
![Page 27: Digital Image Processing CSC331 Image Segmentation 1.](https://reader036.fdocuments.in/reader036/viewer/2022062301/56649e935503460f94b98d29/html5/thumbnails/27.jpg)
27
![Page 28: Digital Image Processing CSC331 Image Segmentation 1.](https://reader036.fdocuments.in/reader036/viewer/2022062301/56649e935503460f94b98d29/html5/thumbnails/28.jpg)
28
![Page 29: Digital Image Processing CSC331 Image Segmentation 1.](https://reader036.fdocuments.in/reader036/viewer/2022062301/56649e935503460f94b98d29/html5/thumbnails/29.jpg)
29
![Page 30: Digital Image Processing CSC331 Image Segmentation 1.](https://reader036.fdocuments.in/reader036/viewer/2022062301/56649e935503460f94b98d29/html5/thumbnails/30.jpg)
30
![Page 31: Digital Image Processing CSC331 Image Segmentation 1.](https://reader036.fdocuments.in/reader036/viewer/2022062301/56649e935503460f94b98d29/html5/thumbnails/31.jpg)
31
Summery of the lecture
• There are two main approaches to region-based segmentation:
• Region growing • Region splitting and merging • Texture based segmentation • Color based
![Page 32: Digital Image Processing CSC331 Image Segmentation 1.](https://reader036.fdocuments.in/reader036/viewer/2022062301/56649e935503460f94b98d29/html5/thumbnails/32.jpg)
32
References • Prof .P. K. Biswas
Department of Electronics and Electrical Communication Engineering Indian Institute of Technology, Kharagpur
• Gonzalez R. C. & Woods R.E. (2008). Digital Image Processing. Prentice Hall.
• Forsyth, D. A. & Ponce, J. (2011).Computer Vision: A Modern Approach. Pearson Education.