Presentation is loading. Please wait.

Presentation is loading. Please wait.

Outline Perceptual organization, grouping, and segmentation

Similar presentations


Presentation on theme: "Outline Perceptual organization, grouping, and segmentation"— Presentation transcript:

1 Outline Perceptual organization, grouping, and segmentation
Introduction Region growing Split-and-merge File: week13-f.ppt

2 Visual Perception Modeling
Introduction Segmentation Roughly speaking, segmentation is to partition the images into meaningful parts that are relatively homogenous in certain sense 11/13/2018 Visual Perception Modeling

3 Visual Perception Modeling
Introduction – cont. Why is segmentation important Classification algorithms in general assume that the features are extracted only from the objects/regions that we are interested in 11/13/2018 Visual Perception Modeling

4 Visual Perception Modeling
Introduction – cont. Why is segmentation difficult The first difficulty is a representation issue There are many different kinds of objects, textures Is there a representation that will apply to all the images 11/13/2018 Visual Perception Modeling

5 Introduction - continued
How can we characterize all these images perceptually? 11/13/2018 Visual Perception Modeling

6 Visual Perception Modeling
Introduction – cont. Why is segmentation difficult The first difficulty is a representation issue There are many different kinds of objects, textures Is there a representation that will apply to all the images The second difficulty is to identify first what types of objects are present in the given input image The third difficulty is to localize the boundaries between regions 11/13/2018 Visual Perception Modeling

7 Visual Perception Modeling
Introduction – cont. But we can do the task effortless How have we done so? 11/13/2018 Visual Perception Modeling

8 Visual Perception Modeling
Introduction – cont. Perceptual organization Try to understand the principles behind perception by observing and building models for perceptual phenomena 11/13/2018 Visual Perception Modeling

9 Visual Perception Modeling
Introduction – cont. 11/13/2018 Visual Perception Modeling

10 Visual Perception Modeling
Introduction – cont. Gestalt grouping principles Proximity Objects that are close to each other tend to be grouped together Similarity Objects that are more similar to one another tend to be grouped together Closure Objects that form closed units tend to be grouped together 11/13/2018 Visual Perception Modeling

11 Visual Perception Modeling
Introduction – cont. Gestalt grouping principles – continued Good continuation Common fate Figure and ground Subjective contour 11/13/2018 Visual Perception Modeling

12 Visual Perception Modeling
Introduction – cont. Problems with Gestalt principles They are NOT computational models In addition, those factors interfere each other in a given image 11/13/2018 Visual Perception Modeling

13 Visual Perception Modeling
Introduction – cont. Computational models/implementations There are generally two kinds of computational models/implementations for segmentation Based on homogeneity measure to group pixels with similar attributes together Region growing/split-and-merge Based on discontinuity of attributes to detect boundaries/contours of regions Active contours 11/13/2018 Visual Perception Modeling

14 Visual Perception Modeling
Region Growing Region growing Is a set of algorithms to group pixels with similar attributes together The basic idea is to grow from a seed pixel At a labeled pixel, check its neighbors If the attributes of its neighbor is similar to the attributes of the labeled pixel, label the neighbor Repeat until there is no pixel that can be labeled 11/13/2018 Visual Perception Modeling

15 Visual Perception Modeling
Region Growing – cont. A simple case The attribute of a pixel is its pixel value The similarity is given by the difference between the two pixel values If the difference is smaller than a threshold, we say they are similar Otherwise they are not 11/13/2018 Visual Perception Modeling

16 Visual Perception Modeling
Region Growing – cont. Recursive implementation Given a seed point, call the following recursive function void RegionGrowing(IMAGE animage, LABEL labelmap, int x, int y, int label) if (labelmap[x][y] != 0) return; labelmap[x][y] = label; for each neighbor nx, ny of pixel x,y if labelmap[nx][ny]==0 if diff(animage[x][y]-animage[nx][ny]) < threhold, RegionGrowing(animage, labelmap, nx, ny, label) end if end for return 11/13/2018 Visual Perception Modeling

17 Visual Perception Modeling
Region Growing – cont. Efficient implementation Based on scan-line algorithm in graphics Each time we label a line instead of a pixel This procedure is much more efficient than the recursive version 11/13/2018 Visual Perception Modeling

18 Visual Perception Modeling
Split and Merge There is also a different implementation to partition an input image into homogenous regions Start with the entire image as one region Then split a region into sub-regions if the variance is larger than a threshold and merge neighboring regions if they are similar 11/13/2018 Visual Perception Modeling

19 Visual Perception Modeling
Split and Merge – cont. 1. Start with the entire image as a single region 2. Pick a region R. If H(R) is false, then split the region into four sub-regions 3. Consider any two or more neighboring sub-regions, R1,R2,...,Rn, in the image. If H(R1 U R2 U ... U Rn ) is true, merge the n regions into a single region. 4. Repeat these steps until no further splits or merges take place 11/13/2018 Visual Perception Modeling

20 Visual Perception Modeling
Split and Merge – cont. 11/13/2018 Visual Perception Modeling

21 Visual Perception Modeling
Split and Merge – cont. 11/13/2018 Visual Perception Modeling

22 Visual Perception Modeling
Split and Merge – cont. 11/13/2018 Visual Perception Modeling


Download ppt "Outline Perceptual organization, grouping, and segmentation"

Similar presentations


Ads by Google