Graph Cut Segmentation - ele.puc-rio.brraul/ImageAnalysis/GRAPH CUT SEGMENTATIO… · Shi, J. and...

14
Graph Cut Segmentation Raul Queiroz Feitosa

Transcript of Graph Cut Segmentation - ele.puc-rio.brraul/ImageAnalysis/GRAPH CUT SEGMENTATIO… · Shi, J. and...

Page 1: Graph Cut Segmentation - ele.puc-rio.brraul/ImageAnalysis/GRAPH CUT SEGMENTATIO… · Shi, J. and Malik, J., (1998), Motion Segmentation and Tracking Using Normalized Cuts, Proc.

Graph Cut Segmentation

Raul Queiroz Feitosa

Page 2: Graph Cut Segmentation - ele.puc-rio.brraul/ImageAnalysis/GRAPH CUT SEGMENTATIO… · Shi, J. and Malik, J., (1998), Motion Segmentation and Tracking Using Normalized Cuts, Proc.

2

Basic Idea

Images are represented by weighted graphs, whereby

pixels are tokens.

Cut up this graph to get sub graphs with strong

interior links and weaker exterior links

11/28/2019 Graph Cut Segmentation

Page 3: Graph Cut Segmentation - ele.puc-rio.brraul/ImageAnalysis/GRAPH CUT SEGMENTATIO… · Shi, J. and Malik, J., (1998), Motion Segmentation and Tracking Using Normalized Cuts, Proc.

Weighted Graphs

The set of points in an arbitrary feature space are represented as a weighted undirected graph G (V,E)

where V is the set of points in the feature space, and

E is the set of edges formed between every pair of nodes.

The weight on each edge, w(i,j) is a function of the similarity between nodes i and j.

3

1720

1600

7643

2041

0031

Weight Matrix: W

a

e

d

c

b

11/28/2019 Graph Cut Segmentation

Page 4: Graph Cut Segmentation - ele.puc-rio.brraul/ImageAnalysis/GRAPH CUT SEGMENTATIO… · Shi, J. and Malik, J., (1998), Motion Segmentation and Tracking Using Normalized Cuts, Proc.

4

A graph G can be

partitioned into two disjoint

sets of points A and B such

that:

• A B =

• A B =V

The degree of dissimilarity

(~affinity) between A and B

can be computed as the

total weight of the edges

that have been removed.

* From Khurram Hassan-Shafique CAP5415 Computer Vision 2003

Minimum Cut

11/28/2019 Graph Cut Segmentation

Page 5: Graph Cut Segmentation - ele.puc-rio.brraul/ImageAnalysis/GRAPH CUT SEGMENTATIO… · Shi, J. and Malik, J., (1998), Motion Segmentation and Tracking Using Normalized Cuts, Proc.

5

Minimum Cut and Clustering

From Khurram Hassan-Shafique CAP5415 Computer Vision 2003

The optimal bi-partitioning of a

graph is the one that minimizes this

cut value.

11/28/2019 Graph Cut Segmentation

Page 6: Graph Cut Segmentation - ele.puc-rio.brraul/ImageAnalysis/GRAPH CUT SEGMENTATIO… · Shi, J. and Malik, J., (1998), Motion Segmentation and Tracking Using Normalized Cuts, Proc.

𝐶1𝐶2

Image Segmentation & Minimum Cut

11/28/2019 SLIC 6

...

...

...

...

...

...

...

...

...

...

...

...

...

...

An image is modeled as an undirected graph 𝐺 =𝑉, 𝐸 ,

where:

𝑉 = {𝑣𝑖}: vertex ( )

𝐸 = { 𝑣𝑖 , 𝑣𝑗 }: Edge ( )

𝑤 𝑣𝑖 , 𝑣𝑗 : weight associated to an edge (affinity

measure).

...

...

...

...

...

...

...

...

...

...

...

...

...

...

𝐶3𝑆: Segmentation

𝐶1, 𝐶2, …: Segments

high 𝒘

l𝒐𝒘 𝒘

Page 7: Graph Cut Segmentation - ele.puc-rio.brraul/ImageAnalysis/GRAPH CUT SEGMENTATIO… · Shi, J. and Malik, J., (1998), Motion Segmentation and Tracking Using Normalized Cuts, Proc.

7

Measuring Affinity

Spectral

Texture

Distance

aff x, y exp 12 i

2

I x I y

2

aff x, y exp 12 d

2

x y

2

aff x, y exp 12 t

2

c x c y

2

Maximum affinity = 1.

11/28/2019 Graph Cut Segmentation

Page 8: Graph Cut Segmentation - ele.puc-rio.brraul/ImageAnalysis/GRAPH CUT SEGMENTATIO… · Shi, J. and Malik, J., (1998), Motion Segmentation and Tracking Using Normalized Cuts, Proc.

8

Drawbacks of Minimum Cut

Weight of cut is directly proportional to the number

of edges in the cut.

Ideal Cut

Cuts with

lesser weight

than the

ideal cut

From Saksoy 2018

11/28/2019 Graph Cut Segmentation

Page 9: Graph Cut Segmentation - ele.puc-rio.brraul/ImageAnalysis/GRAPH CUT SEGMENTATIO… · Shi, J. and Malik, J., (1998), Motion Segmentation and Tracking Using Normalized Cuts, Proc.

9

Normalized Cut

Instead of looking at the value of total edge weight

connecting the two partitions, compute the cut cost as

a fraction of the total edge.

where

is the total connection from nodes in A to all nodes in

the graph. Similarly for assoc(B,V).

11/28/2019 Graph Cut Segmentation

Page 10: Graph Cut Segmentation - ele.puc-rio.brraul/ImageAnalysis/GRAPH CUT SEGMENTATIO… · Shi, J. and Malik, J., (1998), Motion Segmentation and Tracking Using Normalized Cuts, Proc.

10

Finding Minimum Normalized-Cut

“Although there are an exponential number of such

partitions, finding the minimum cut of a graph is a

well-studied problem and there exist efficient

algorithms for solving it”.

Shi & Malik, 2000

11/28/2019 Graph Cut Segmentation

Page 11: Graph Cut Segmentation - ele.puc-rio.brraul/ImageAnalysis/GRAPH CUT SEGMENTATIO… · Shi, J. and Malik, J., (1998), Motion Segmentation and Tracking Using Normalized Cuts, Proc.

Finding Minimum Normalized-Cut

Example: Color Images

11

From Derek Hoiem

11/28/2019 Graph Cut Segmentation

Page 12: Graph Cut Segmentation - ele.puc-rio.brraul/ImageAnalysis/GRAPH CUT SEGMENTATIO… · Shi, J. and Malik, J., (1998), Motion Segmentation and Tracking Using Normalized Cuts, Proc.

Pros & ConsPros

– Generic framework, can be used with many

different features and affinity formulations

– Provides regular segments

Cons– Need to chose number of segments

– High storage requirement and time complexity

– Bias towards partitioning into equal sized

segments

Usage– Use for oversegmentation when you want

regular segments

From Derek Hoiem

11/28/2019 Graph Cut Segmentation

Page 13: Graph Cut Segmentation - ele.puc-rio.brraul/ImageAnalysis/GRAPH CUT SEGMENTATIO… · Shi, J. and Malik, J., (1998), Motion Segmentation and Tracking Using Normalized Cuts, Proc.

References

Shi, J. and Malik, J., (2000) Normalized Cuts and Image Segmentation,

IEEE Transactions on Pattern Analysis and Machine Intelligence, Vol. 22

(8), pp.888-905 .

Shi, J. and Malik, J., (1998), Motion Segmentation and Tracking Using

Normalized Cuts, Proc. Int'l Conf. Computer Vision, pp. 154-160.

1311/28/2019 Graph Cut Segmentation

Page 14: Graph Cut Segmentation - ele.puc-rio.brraul/ImageAnalysis/GRAPH CUT SEGMENTATIO… · Shi, J. and Malik, J., (1998), Motion Segmentation and Tracking Using Normalized Cuts, Proc.

11/28/2019 Morphological Image Processing 14

Next Topic

Representation and

Description