SlideShare a Scribd company logo
1 of 63
Download to read offline
Superpixel algorithms
Shima Foolad
shimafoolad@gmail.com
sh.foolad@Semnan.ac.ir
3 Dec. 2017
1
SUPERPIXEL ALGORITHMS
2
OUTLINE
Introduction1
2 Superpixel algorithms
1 Watershed
2
3 Visual Comparison of algorithms
Mean-shift
3 SLIC
3
WHAT IS A SUPERPIXEL?
A superpixel can be defined as a group of pixels which have similar
characteristics.
4
ADVANTAGES OF SUPERPIXEL
1. Good adherence to object boundaries
2. reduce the computational complexity from thousands of pixels to a few
hundred superpixels
5
APPLICATION OF SUPERPIXEL
segmentation
6
SUPERPIXEL ALGORITHMS
7
There are many algorithms to segment superpixels:
• Whatershed
• Mean-Shift
• Normalized-Cuts
• Graph-based
• QuichShift
• TurboPixels
• SLIC
WATERSHED ALGORITHM
8
WATERSHED ALGORITHM
9
• Any grey image can be considered as a topographic surface.
• flood this surface from its minima
• prevent the merging of the waters coming from different sources
Watershed algorithm was proposed by Vincent and Soille in 1991 Watershed lines
WATERSHED ALGORITHM
10
Watershed algorithm might be used on the gradient image instead of the original image.
Gradient imageOriginal image
Watershed of the original imageWatershed of the gradient image
WATERSHED ALGORITHM
11
in practice, this algorithm produces an over-segmentation due to noise or local irregularities in
the gradient image.
MEAN-SHIFT ALGORITHM
12
MEAN-SHIFT ALGORITHM
13
1. Choose a search window size.
2. Choose the initial location of the search window.
3. Compute the mean location (centroid of the data) in the search window.
4. Center the search window at the mean location computed in Step 3.
5. Repeat Steps 3 and 4 until convergence.
Mean-shift algorithm was proposed by Comaniciu and Meer in 2002
MEAN-SHIFT ALGORITHM
14
MEAN-SHIFT ALGORITHM
15
MEAN-SHIFT ALGORITHM
16
MEAN-SHIFT ALGORITHM
17
MEAN-SHIFT ALGORITHM
18
finding peaks in the high-dimensional data distribution
MEAN-SHIFT ALGORITHM
19
finding peaks in the high-dimensional data distribution in color image
MEAN-SHIFT ALGORITHM
20
MEAN-SHIFT ALGORITHM
22
SLIC ALGORITHM
23
SLIC ALGORITHM
Simple Linear Iterative Clustering (SLIC) algorithm
24
The Simple Linear Iterative Clustering (SLIC) algorithm was proposed by Radhakrishna Achanta in 2010
SLIC ALGORITHM
Sample segmentation output
25
SLIC WEB SITE
http://ivrl.epfl.ch/research/superpixels
26
SLIC
27
For color images, SLIC algorithm works in the LAB color space.
COVERT RGB TO LAB COLOR SPACE
28
𝐿 = 116. ℎ
𝑌
𝑌𝑤
− 16
𝐴 = 500 ℎ
𝑋
𝑋 𝑤
− ℎ
𝑌
𝑌𝑤
𝐵 = 200 ℎ
𝑌
𝑌𝑤
− ℎ
𝑍
𝑍 𝑤
ℎ 𝑞 = ቐ
3
𝑞 𝑞 > 0.008856
7.787𝑞 +
16
116
𝑞 ≤ 0.008856
𝑋
𝑌
𝑍
=
0.412453 0.357580 0.180423
0.212671 0.715160 0.072169
0.019334 0.119193 0.950227
𝑅
𝐺
𝐵
𝑋 𝑤=0.950450 𝑌𝑤=1.000000 𝑍 𝑤=0.088754
COVERT RGB TO LAB COLOR SPACE
B channel
Blue-yellow
A channel
Red-green
L channel
29
RGB
SLIC EXAMPLE
30
• Each pixel is assigned a 5-valued vector
(𝑋, 𝑌, 𝐿, 𝑎, 𝑏) for position and color
• Number of pixels: 𝑁 = 1600
• Image size: 40×40
• Number of superpixels: 𝐾 = 16
THE MAIN STEPS OF THE SLIC ALGORITHM
1. Initialize 𝐾 cluster centers 𝑪 𝒌 = 𝒍 𝒌, 𝒂 𝒌, 𝒃 𝒌, 𝒙 𝒌, 𝒚 𝒌
𝑻
on a regular grid spaced 𝑆
=
𝑁
𝐾
pixels apart.
31
• each superpixel has approximately
𝑁
𝐾
pixels
NUMBER OF SUPERPIXELS (K)
32
THE MAIN STEPS OF THE SLIC ALGORITHM
1. Initialize 𝐾 cluster centers 𝑪 𝒌 = 𝒍 𝒌, 𝒂 𝒌, 𝒃 𝒌, 𝒙 𝒌, 𝒚 𝒌
𝑻
on a regular grid spaced 𝑆
=
𝑁
𝐾
pixels apart.
33
• each superpixel has approximately
𝑁
𝐾
pixels
𝑁
𝐾
=
1600
16
= 100
. . . .
.
.
.
.
.
.
.
.
.
.
.
.
𝑪1
𝑆
𝑆
𝑆 =
𝑁
𝐾
= 100 = 10
𝑪5
𝑪9
𝑪13
𝑪2
𝑪6
𝑪10
𝑪14
𝑪3
𝑪7
𝑪11
𝑪15
𝑪4
𝑪8
𝑪12
𝑪16
THE MAIN STEPS OF THE SLIC ALGORITHM
2. move these cluster centers to the positions with the lowest gradients in a 3 × 3
neighborhood;
This is done to avoid centering a superpixel on an edge, and to reduce to chance
of seeding superpixel with a noisy pixel.
34
𝐺 𝑥, 𝑦 = 𝐼 𝑥, 𝑦 − 1 − 𝐼(𝑥, 𝑦 + 1) 2 + 𝐼 𝑥 − 1, 𝑦 − 𝐼(𝑥 + 1, 𝑦) 2
. . . .
.
.
.
.
.
.
.
.
.
.
.
.
𝑪1
𝑪5
𝑪9
𝑪13
𝑪2
𝑪6
𝑪10
𝑪14
𝑪3
𝑪7
𝑪11
𝑪15
𝑪4
𝑪8
𝑪12
𝑪16
THE MAIN STEPS OF THE SLIC ALGORITHM
2. move these cluster centers to the positions with the lowest gradients in a 3 × 3
neighborhood;
This is done to avoid centering a superpixel on an edge, and to reduce to chance
of seeding superpixel with a noisy pixel.
35
𝐺 𝑥, 𝑦 = 𝐼 𝑥, 𝑦 − 1 − 𝐼(𝑥, 𝑦 + 1) 2 + 𝐼 𝑥 − 1, 𝑦 − 𝐼(𝑥 + 1, 𝑦) 2
. . . .
.
.
.
.
.
.
.
.
.
.
.
.
𝑪1
𝑪5
𝑪9
𝑪13
𝑪2
𝑪6
𝑪10
𝑪14
𝑪3
𝑪7
𝑪11
𝑪15
𝑪4
𝑪8
𝑪12
𝑪16
.
THE MAIN STEPS OF THE SLIC ALGORITHM
3. Assign pixels. Designate each pixel to a closest cluster center in a local search
space;
36
K-means algorithm SLIC algorithm
THE MAIN STEPS OF THE SLIC ALGORITHM
3. Assign pixels. Designate each pixel to a closest cluster center in a local search
space;
37
for each cluster center 𝑪 𝒌
Assign the best matching pixels from a 𝟐𝑺 × 𝟐𝑺 around the cluster center according to the distance measure.
end for
. . . .
.
.
.
.
.
.
.
.
.
.
.
.
𝑪1
𝑪5
𝑪9
𝑪13
𝑪2
𝑪6
𝑪10
𝑪14
𝑪3
𝑪7
𝑪11
𝑪15
𝑪4
𝑪8
𝑪12
𝑪16
THE MAIN STEPS OF THE SLIC ALGORITHM
3. Assign pixels. Designate each pixel to a closest cluster center in a local search
space;
38
     
2 2 2
c j i j i j id l l a a b b     
   
2 2
s j i j id x x y y   
/S N K
2
2 2s
c
d
D d m
S
 
   
 
Distance measure
Color distance:
position distance:
𝐷′ =
𝑑 𝑐
𝑁𝑐
2
+
𝑑 𝑠
𝑁𝑠
2
𝐷′ =
𝑑 𝑐
𝑚
2
+
𝑑 𝑠
𝑆
2
m= Compactness of superpixel
COMPACTNESS OF SUPERPIXELS (m)
m = 1 m = 20 m = 40
39
THE MAIN STEPS OF THE SLIC ALGORITHM
3. Assign pixels. Designate each pixel to a closest cluster center in a local search
space by local KMC;
4. Update cluster centers. Set each cluster center as the mean of all pixels in the
corresponding cluster;
5. Repeat steps (3)–(4) until the clusters do not change or error (difference between
previous cluster and new cluster) is converge.
40
initialization iteration 1 iteration 2 iteration 3 iteration 4
THE MAIN STEPS OF THE SLIC ALGORITHM
6. Post-processing. The connected components algorithm is used to reassign
isolated regions to nearby superpixels if the size of the isolated regions is smaller
than a minimum size 𝑆 𝑚𝑖𝑛.
41
post-processing
SUPERVOXEL
42
2
SLICO
SLIC
SLICO
SLIC uses the same compactness parameter (chosen by user) for all superpixels in the image.
SLICO adaptively chooses the compactness parameter for each superpixel differently.
43
VISUAL COMPARISON OF ALGORITHMS
44
Watershed
1991
SLIC
2010
Mean-Shift
2002
VISUAL COMPARISON OF ALGORITHMS
45
ADVANTAGES OF SLIC
46
• low complexity
• generate superpixels with compact , regular size and shape
• SLIC is simple to use and understand
DISADVANTAGE OF SLIC
47
Turbopixels algorithmSLIC algorithmSuperPB algorithmSEEDS algorithm
BSLIC
48
BSLIC
49
BSLIC
50
DIFFERENCE BETWEEN SLIC AND BSLIC
51
• initializing cluster centers in hexagon rather than square
distribution
• choosing some specific edge pixels as cluster centers
• incorporating boundary term into the distance measurement during
k-means clustering
DISTRIBUTION OF CLUSTER CENTERS
52
DISTRIBUTION OF CLUSTER CENTERS
53
INITIALIZATION OF EDGE CENTERS
54
Edge-across superpixels. (a) Original image with slender rod; (b) Edge image with canny filter operator; (c) Partial
enlarged superpixels with only plane centers initialized in hexagon distribution; (d) Partial enlarged superpixels
with only plane centers initialized in square distribution.
hexagon distribution square distribution
PLANE CENTER AND EDGE CENTER
55
Plane center and edge center. Dots in solid black Ci0, Ci1, Ci2, Ci3, Ci4, Ci5 and Ci6 are “plane center”;
Square in solid red Ei1 is “edge center”.
hexagon distribution square distribution
Segmentation without
edge cluster center
Segmentation with
edge cluster center
56
DISTANCE MEASUREMENT
57
DISTANCE MEASUREMENT
58
Superpixel segmentation results
With edge cluster center
Segmentation without
edge cluster center
Segmentation with
edge cluster center
59
BSLIC ITERATING PROCESS
60
(a) Superpixels with only plane centers; (b) Superpixels with both plane and edge centers; (c)
First iterating result of BSLIC; (d) Final segmentation result of BSLIC.
BSLIC SUPERPIXELS SEGMENTATION RESULTS
61
m=5 m=15 m=30
k=100
k=500
k=1000
PART OF BSLIC EXPERIMENTAL RESULTS
62TurbopixelsSLICSuperPBSEEDSBSLIC
REFERENCES
[1] Luc Vincent and Pierre Soille. Watersheds in digital spaces: An efficient algorithm based on immersion
simulations. IEEE Transactions on Pattern Analalysis and Machine Intelligence, 13(6):583–598, 1991.
[2] D. Comaniciu and P. Meer. Mean shift: a robust approach toward feature space analysis. IEEE
Transactions on Pattern Analysis and Machine Intelligence, 24(5):603–619, May 2002.
[3] Radhakrishna Achanta, Appu Shaji, Kevin Smith, Aurelien Lucchi, Pascal Fua, and Sabine
Süsstrunk, SLIC Superpixels Compared to State-of-the-art Superpixel Methods, IEEE Transactions on
Pattern Analysis and Machine Intelligence, vol. 34, num. 11, p. 2274 - 2282, May 2012.
[4] Radhakrishna Achanta, Appu Shaji, Kevin Smith, Aurelien Lucchi, Pascal Fua, and Sabine
Süsstrunk, SLIC Superpixels, EPFL Technical Report no. 149300, June 2010.
[5] Hai Wang, Xiongyou Peng, Xue Xiao, and Yan Liu, BSLIC: SLIC Superpixels Based on Boundary Term,
Symmetry 2017, 9(3), Feb 2017.
63
Thanks
64

More Related Content

What's hot

Machine Learning With Logistic Regression
Machine Learning  With Logistic RegressionMachine Learning  With Logistic Regression
Machine Learning With Logistic RegressionKnoldus Inc.
 
Lect 03 - first portion
Lect 03 - first portionLect 03 - first portion
Lect 03 - first portionMoe Moe Myint
 
Introduction to deep learning
Introduction to deep learningIntroduction to deep learning
Introduction to deep learningAmr Rashed
 
Introduction to CNN
Introduction to CNNIntroduction to CNN
Introduction to CNNShuai Zhang
 
Edge Detection algorithm and code
Edge Detection algorithm and codeEdge Detection algorithm and code
Edge Detection algorithm and codeVaddi Manikanta
 
Image Filtering in the Frequency Domain
Image Filtering in the Frequency DomainImage Filtering in the Frequency Domain
Image Filtering in the Frequency DomainAmnaakhaan
 
Faster R-CNN: Towards real-time object detection with region proposal network...
Faster R-CNN: Towards real-time object detection with region proposal network...Faster R-CNN: Towards real-time object detection with region proposal network...
Faster R-CNN: Towards real-time object detection with region proposal network...Universitat Politècnica de Catalunya
 
CNN and its applications by ketaki
CNN and its applications by ketakiCNN and its applications by ketaki
CNN and its applications by ketakiKetaki Patwari
 
Multi Layer Perceptron & Back Propagation
Multi Layer Perceptron & Back PropagationMulti Layer Perceptron & Back Propagation
Multi Layer Perceptron & Back PropagationSung-ju Kim
 
Convolutional Neural Network Models - Deep Learning
Convolutional Neural Network Models - Deep LearningConvolutional Neural Network Models - Deep Learning
Convolutional Neural Network Models - Deep LearningMohamed Loey
 
Backpropagation in Convolutional Neural Network
Backpropagation in Convolutional Neural NetworkBackpropagation in Convolutional Neural Network
Backpropagation in Convolutional Neural NetworkHiroshi Kuwajima
 
Feature detection and matching
Feature detection and matchingFeature detection and matching
Feature detection and matchingKuppusamy P
 
Semantic Segmentation Methods using Deep Learning
Semantic Segmentation Methods using Deep LearningSemantic Segmentation Methods using Deep Learning
Semantic Segmentation Methods using Deep LearningSungjoon Choi
 
Chapter 3 image enhancement (spatial domain)
Chapter 3 image enhancement (spatial domain)Chapter 3 image enhancement (spatial domain)
Chapter 3 image enhancement (spatial domain)asodariyabhavesh
 
fusion of Camera and lidar for autonomous driving I
fusion of Camera and lidar for autonomous driving Ifusion of Camera and lidar for autonomous driving I
fusion of Camera and lidar for autonomous driving IYu Huang
 
Convolutional Neural Network (CNN) presentation from theory to code in Theano
Convolutional Neural Network (CNN) presentation from theory to code in TheanoConvolutional Neural Network (CNN) presentation from theory to code in Theano
Convolutional Neural Network (CNN) presentation from theory to code in TheanoSeongwon Hwang
 
Lec14: Evaluation Framework for Medical Image Segmentation
Lec14: Evaluation Framework for Medical Image SegmentationLec14: Evaluation Framework for Medical Image Segmentation
Lec14: Evaluation Framework for Medical Image SegmentationUlaş Bağcı
 

What's hot (20)

Machine Learning With Logistic Regression
Machine Learning  With Logistic RegressionMachine Learning  With Logistic Regression
Machine Learning With Logistic Regression
 
Lect 03 - first portion
Lect 03 - first portionLect 03 - first portion
Lect 03 - first portion
 
Introduction to deep learning
Introduction to deep learningIntroduction to deep learning
Introduction to deep learning
 
Introduction to CNN
Introduction to CNNIntroduction to CNN
Introduction to CNN
 
Edge Detection algorithm and code
Edge Detection algorithm and codeEdge Detection algorithm and code
Edge Detection algorithm and code
 
Image Filtering in the Frequency Domain
Image Filtering in the Frequency DomainImage Filtering in the Frequency Domain
Image Filtering in the Frequency Domain
 
Faster R-CNN: Towards real-time object detection with region proposal network...
Faster R-CNN: Towards real-time object detection with region proposal network...Faster R-CNN: Towards real-time object detection with region proposal network...
Faster R-CNN: Towards real-time object detection with region proposal network...
 
Chapter 5
Chapter 5Chapter 5
Chapter 5
 
CNN and its applications by ketaki
CNN and its applications by ketakiCNN and its applications by ketaki
CNN and its applications by ketaki
 
Multi Layer Perceptron & Back Propagation
Multi Layer Perceptron & Back PropagationMulti Layer Perceptron & Back Propagation
Multi Layer Perceptron & Back Propagation
 
Convolutional Neural Network Models - Deep Learning
Convolutional Neural Network Models - Deep LearningConvolutional Neural Network Models - Deep Learning
Convolutional Neural Network Models - Deep Learning
 
Mask R-CNN
Mask R-CNNMask R-CNN
Mask R-CNN
 
Backpropagation in Convolutional Neural Network
Backpropagation in Convolutional Neural NetworkBackpropagation in Convolutional Neural Network
Backpropagation in Convolutional Neural Network
 
Feature detection and matching
Feature detection and matchingFeature detection and matching
Feature detection and matching
 
Semantic Segmentation Methods using Deep Learning
Semantic Segmentation Methods using Deep LearningSemantic Segmentation Methods using Deep Learning
Semantic Segmentation Methods using Deep Learning
 
Chapter 3 image enhancement (spatial domain)
Chapter 3 image enhancement (spatial domain)Chapter 3 image enhancement (spatial domain)
Chapter 3 image enhancement (spatial domain)
 
Deep learning
Deep learningDeep learning
Deep learning
 
fusion of Camera and lidar for autonomous driving I
fusion of Camera and lidar for autonomous driving Ifusion of Camera and lidar for autonomous driving I
fusion of Camera and lidar for autonomous driving I
 
Convolutional Neural Network (CNN) presentation from theory to code in Theano
Convolutional Neural Network (CNN) presentation from theory to code in TheanoConvolutional Neural Network (CNN) presentation from theory to code in Theano
Convolutional Neural Network (CNN) presentation from theory to code in Theano
 
Lec14: Evaluation Framework for Medical Image Segmentation
Lec14: Evaluation Framework for Medical Image SegmentationLec14: Evaluation Framework for Medical Image Segmentation
Lec14: Evaluation Framework for Medical Image Segmentation
 

Similar to Superpixel algorithms (whatershed, mean-shift, SLIC, BSLIC), Foolad

ImageNet classification with deep convolutional neural networks(2012)
ImageNet classification with deep convolutional neural networks(2012)ImageNet classification with deep convolutional neural networks(2012)
ImageNet classification with deep convolutional neural networks(2012)WoochulShin10
 
Convolution Neural Network Lecture Slides
Convolution Neural Network Lecture SlidesConvolution Neural Network Lecture Slides
Convolution Neural Network Lecture SlidesAdnanHaider234505
 
Learning Convolutional Neural Networks for Graphs
Learning Convolutional Neural Networks for GraphsLearning Convolutional Neural Networks for Graphs
Learning Convolutional Neural Networks for Graphspione30
 
Introduction to Neural Networks and Deep Learning
Introduction to Neural Networks and Deep LearningIntroduction to Neural Networks and Deep Learning
Introduction to Neural Networks and Deep LearningVahid Mirjalili
 
Mask-RCNN for Instance Segmentation
Mask-RCNN for Instance SegmentationMask-RCNN for Instance Segmentation
Mask-RCNN for Instance SegmentationDat Nguyen
 
Chaotic substitution box design for block ciphers
Chaotic substitution box design for block  ciphersChaotic substitution box design for block  ciphers
Chaotic substitution box design for block ciphersHammad Haleem
 
MAtrix Multiplication Parallel.ppsx
MAtrix Multiplication Parallel.ppsxMAtrix Multiplication Parallel.ppsx
MAtrix Multiplication Parallel.ppsxBharathiLakshmiAAssi
 
Lecture 6: Convolutional Neural Networks
Lecture 6: Convolutional Neural NetworksLecture 6: Convolutional Neural Networks
Lecture 6: Convolutional Neural NetworksSang Jun Lee
 
PR-305: Exploring Simple Siamese Representation Learning
PR-305: Exploring Simple Siamese Representation LearningPR-305: Exploring Simple Siamese Representation Learning
PR-305: Exploring Simple Siamese Representation LearningSungchul Kim
 
Enhancing the performance of kmeans algorithm
Enhancing the performance of kmeans algorithmEnhancing the performance of kmeans algorithm
Enhancing the performance of kmeans algorithmHadi Fadlallah
 
Contour-Constrained Superpixels for Image and Video Processing
Contour-Constrained Superpixels for Image and Video ProcessingContour-Constrained Superpixels for Image and Video Processing
Contour-Constrained Superpixels for Image and Video ProcessingNAVER Engineering
 
EXTENDED K-MAP FOR MINIMIZING MULTIPLE OUTPUT LOGIC CIRCUITS
EXTENDED K-MAP FOR MINIMIZING MULTIPLE OUTPUT LOGIC CIRCUITSEXTENDED K-MAP FOR MINIMIZING MULTIPLE OUTPUT LOGIC CIRCUITS
EXTENDED K-MAP FOR MINIMIZING MULTIPLE OUTPUT LOGIC CIRCUITSVLSICS Design
 
K-means Clustering Algorithm with Matlab Source code
K-means Clustering Algorithm with Matlab Source codeK-means Clustering Algorithm with Matlab Source code
K-means Clustering Algorithm with Matlab Source codegokulprasath06
 
Machine Learning - Convolutional Neural Network
Machine Learning - Convolutional Neural NetworkMachine Learning - Convolutional Neural Network
Machine Learning - Convolutional Neural NetworkRichard Kuo
 
Scratch to Supercomputers: Bottoms-up Build of Large-scale Computational Lens...
Scratch to Supercomputers: Bottoms-up Build of Large-scale Computational Lens...Scratch to Supercomputers: Bottoms-up Build of Large-scale Computational Lens...
Scratch to Supercomputers: Bottoms-up Build of Large-scale Computational Lens...inside-BigData.com
 

Similar to Superpixel algorithms (whatershed, mean-shift, SLIC, BSLIC), Foolad (20)

ImageNet classification with deep convolutional neural networks(2012)
ImageNet classification with deep convolutional neural networks(2012)ImageNet classification with deep convolutional neural networks(2012)
ImageNet classification with deep convolutional neural networks(2012)
 
Reyes
ReyesReyes
Reyes
 
Convolution Neural Network Lecture Slides
Convolution Neural Network Lecture SlidesConvolution Neural Network Lecture Slides
Convolution Neural Network Lecture Slides
 
Learning Convolutional Neural Networks for Graphs
Learning Convolutional Neural Networks for GraphsLearning Convolutional Neural Networks for Graphs
Learning Convolutional Neural Networks for Graphs
 
Introduction to Neural Networks and Deep Learning
Introduction to Neural Networks and Deep LearningIntroduction to Neural Networks and Deep Learning
Introduction to Neural Networks and Deep Learning
 
Mask-RCNN for Instance Segmentation
Mask-RCNN for Instance SegmentationMask-RCNN for Instance Segmentation
Mask-RCNN for Instance Segmentation
 
Chaotic substitution box design for block ciphers
Chaotic substitution box design for block  ciphersChaotic substitution box design for block  ciphers
Chaotic substitution box design for block ciphers
 
MAtrix Multiplication Parallel.ppsx
MAtrix Multiplication Parallel.ppsxMAtrix Multiplication Parallel.ppsx
MAtrix Multiplication Parallel.ppsx
 
matrixmultiplicationparallel.ppsx
matrixmultiplicationparallel.ppsxmatrixmultiplicationparallel.ppsx
matrixmultiplicationparallel.ppsx
 
Densebox
DenseboxDensebox
Densebox
 
Lecture 6: Convolutional Neural Networks
Lecture 6: Convolutional Neural NetworksLecture 6: Convolutional Neural Networks
Lecture 6: Convolutional Neural Networks
 
MUMS: Transition & SPUQ Workshop - Gradient-Free Construction of Active Subsp...
MUMS: Transition & SPUQ Workshop - Gradient-Free Construction of Active Subsp...MUMS: Transition & SPUQ Workshop - Gradient-Free Construction of Active Subsp...
MUMS: Transition & SPUQ Workshop - Gradient-Free Construction of Active Subsp...
 
PR-305: Exploring Simple Siamese Representation Learning
PR-305: Exploring Simple Siamese Representation LearningPR-305: Exploring Simple Siamese Representation Learning
PR-305: Exploring Simple Siamese Representation Learning
 
MNIST 10-class Classifiers
MNIST 10-class ClassifiersMNIST 10-class Classifiers
MNIST 10-class Classifiers
 
Enhancing the performance of kmeans algorithm
Enhancing the performance of kmeans algorithmEnhancing the performance of kmeans algorithm
Enhancing the performance of kmeans algorithm
 
Contour-Constrained Superpixels for Image and Video Processing
Contour-Constrained Superpixels for Image and Video ProcessingContour-Constrained Superpixels for Image and Video Processing
Contour-Constrained Superpixels for Image and Video Processing
 
EXTENDED K-MAP FOR MINIMIZING MULTIPLE OUTPUT LOGIC CIRCUITS
EXTENDED K-MAP FOR MINIMIZING MULTIPLE OUTPUT LOGIC CIRCUITSEXTENDED K-MAP FOR MINIMIZING MULTIPLE OUTPUT LOGIC CIRCUITS
EXTENDED K-MAP FOR MINIMIZING MULTIPLE OUTPUT LOGIC CIRCUITS
 
K-means Clustering Algorithm with Matlab Source code
K-means Clustering Algorithm with Matlab Source codeK-means Clustering Algorithm with Matlab Source code
K-means Clustering Algorithm with Matlab Source code
 
Machine Learning - Convolutional Neural Network
Machine Learning - Convolutional Neural NetworkMachine Learning - Convolutional Neural Network
Machine Learning - Convolutional Neural Network
 
Scratch to Supercomputers: Bottoms-up Build of Large-scale Computational Lens...
Scratch to Supercomputers: Bottoms-up Build of Large-scale Computational Lens...Scratch to Supercomputers: Bottoms-up Build of Large-scale Computational Lens...
Scratch to Supercomputers: Bottoms-up Build of Large-scale Computational Lens...
 

Recently uploaded

From idea to production in a day – Leveraging Azure ML and Streamlit to build...
From idea to production in a day – Leveraging Azure ML and Streamlit to build...From idea to production in a day – Leveraging Azure ML and Streamlit to build...
From idea to production in a day – Leveraging Azure ML and Streamlit to build...Florian Roscheck
 
1:1定制(UQ毕业证)昆士兰大学毕业证成绩单修改留信学历认证原版一模一样
1:1定制(UQ毕业证)昆士兰大学毕业证成绩单修改留信学历认证原版一模一样1:1定制(UQ毕业证)昆士兰大学毕业证成绩单修改留信学历认证原版一模一样
1:1定制(UQ毕业证)昆士兰大学毕业证成绩单修改留信学历认证原版一模一样vhwb25kk
 
Dubai Call Girls Wifey O52&786472 Call Girls Dubai
Dubai Call Girls Wifey O52&786472 Call Girls DubaiDubai Call Girls Wifey O52&786472 Call Girls Dubai
Dubai Call Girls Wifey O52&786472 Call Girls Dubaihf8803863
 
Beautiful Sapna Vip Call Girls Hauz Khas 9711199012 Call /Whatsapps
Beautiful Sapna Vip  Call Girls Hauz Khas 9711199012 Call /WhatsappsBeautiful Sapna Vip  Call Girls Hauz Khas 9711199012 Call /Whatsapps
Beautiful Sapna Vip Call Girls Hauz Khas 9711199012 Call /Whatsappssapnasaifi408
 
Building on a FAIRly Strong Foundation to Connect Academic Research to Transl...
Building on a FAIRly Strong Foundation to Connect Academic Research to Transl...Building on a FAIRly Strong Foundation to Connect Academic Research to Transl...
Building on a FAIRly Strong Foundation to Connect Academic Research to Transl...Jack DiGiovanna
 
RS 9000 Call In girls Dwarka Mor (DELHI)⇛9711147426🔝Delhi
RS 9000 Call In girls Dwarka Mor (DELHI)⇛9711147426🔝DelhiRS 9000 Call In girls Dwarka Mor (DELHI)⇛9711147426🔝Delhi
RS 9000 Call In girls Dwarka Mor (DELHI)⇛9711147426🔝Delhijennyeacort
 
ASML's Taxonomy Adventure by Daniel Canter
ASML's Taxonomy Adventure by Daniel CanterASML's Taxonomy Adventure by Daniel Canter
ASML's Taxonomy Adventure by Daniel Cantervoginip
 
How we prevented account sharing with MFA
How we prevented account sharing with MFAHow we prevented account sharing with MFA
How we prevented account sharing with MFAAndrei Kaleshka
 
Call Girls In Mahipalpur O9654467111 Escorts Service
Call Girls In Mahipalpur O9654467111  Escorts ServiceCall Girls In Mahipalpur O9654467111  Escorts Service
Call Girls In Mahipalpur O9654467111 Escorts ServiceSapana Sha
 
Customer Service Analytics - Make Sense of All Your Data.pptx
Customer Service Analytics - Make Sense of All Your Data.pptxCustomer Service Analytics - Make Sense of All Your Data.pptx
Customer Service Analytics - Make Sense of All Your Data.pptxEmmanuel Dauda
 
Call Girls In Dwarka 9654467111 Escorts Service
Call Girls In Dwarka 9654467111 Escorts ServiceCall Girls In Dwarka 9654467111 Escorts Service
Call Girls In Dwarka 9654467111 Escorts ServiceSapana Sha
 
B2 Creative Industry Response Evaluation.docx
B2 Creative Industry Response Evaluation.docxB2 Creative Industry Response Evaluation.docx
B2 Creative Industry Response Evaluation.docxStephen266013
 
꧁❤ Greater Noida Call Girls Delhi ❤꧂ 9711199171 ☎️ Hard And Sexy Vip Call
꧁❤ Greater Noida Call Girls Delhi ❤꧂ 9711199171 ☎️ Hard And Sexy Vip Call꧁❤ Greater Noida Call Girls Delhi ❤꧂ 9711199171 ☎️ Hard And Sexy Vip Call
꧁❤ Greater Noida Call Girls Delhi ❤꧂ 9711199171 ☎️ Hard And Sexy Vip Callshivangimorya083
 
INTERNSHIP ON PURBASHA COMPOSITE TEX LTD
INTERNSHIP ON PURBASHA COMPOSITE TEX LTDINTERNSHIP ON PURBASHA COMPOSITE TEX LTD
INTERNSHIP ON PURBASHA COMPOSITE TEX LTDRafezzaman
 
9711147426✨Call In girls Gurgaon Sector 31. SCO 25 escort service
9711147426✨Call In girls Gurgaon Sector 31. SCO 25 escort service9711147426✨Call In girls Gurgaon Sector 31. SCO 25 escort service
9711147426✨Call In girls Gurgaon Sector 31. SCO 25 escort servicejennyeacort
 
PKS-TGC-1084-630 - Stage 1 Proposal.pptx
PKS-TGC-1084-630 - Stage 1 Proposal.pptxPKS-TGC-1084-630 - Stage 1 Proposal.pptx
PKS-TGC-1084-630 - Stage 1 Proposal.pptxPramod Kumar Srivastava
 
Predictive Analysis - Using Insight-informed Data to Determine Factors Drivin...
Predictive Analysis - Using Insight-informed Data to Determine Factors Drivin...Predictive Analysis - Using Insight-informed Data to Determine Factors Drivin...
Predictive Analysis - Using Insight-informed Data to Determine Factors Drivin...ThinkInnovation
 
9654467111 Call Girls In Munirka Hotel And Home Service
9654467111 Call Girls In Munirka Hotel And Home Service9654467111 Call Girls In Munirka Hotel And Home Service
9654467111 Call Girls In Munirka Hotel And Home ServiceSapana Sha
 
EMERCE - 2024 - AMSTERDAM - CROSS-PLATFORM TRACKING WITH GOOGLE ANALYTICS.pptx
EMERCE - 2024 - AMSTERDAM - CROSS-PLATFORM  TRACKING WITH GOOGLE ANALYTICS.pptxEMERCE - 2024 - AMSTERDAM - CROSS-PLATFORM  TRACKING WITH GOOGLE ANALYTICS.pptx
EMERCE - 2024 - AMSTERDAM - CROSS-PLATFORM TRACKING WITH GOOGLE ANALYTICS.pptxthyngster
 

Recently uploaded (20)

From idea to production in a day – Leveraging Azure ML and Streamlit to build...
From idea to production in a day – Leveraging Azure ML and Streamlit to build...From idea to production in a day – Leveraging Azure ML and Streamlit to build...
From idea to production in a day – Leveraging Azure ML and Streamlit to build...
 
Deep Generative Learning for All - The Gen AI Hype (Spring 2024)
Deep Generative Learning for All - The Gen AI Hype (Spring 2024)Deep Generative Learning for All - The Gen AI Hype (Spring 2024)
Deep Generative Learning for All - The Gen AI Hype (Spring 2024)
 
1:1定制(UQ毕业证)昆士兰大学毕业证成绩单修改留信学历认证原版一模一样
1:1定制(UQ毕业证)昆士兰大学毕业证成绩单修改留信学历认证原版一模一样1:1定制(UQ毕业证)昆士兰大学毕业证成绩单修改留信学历认证原版一模一样
1:1定制(UQ毕业证)昆士兰大学毕业证成绩单修改留信学历认证原版一模一样
 
Dubai Call Girls Wifey O52&786472 Call Girls Dubai
Dubai Call Girls Wifey O52&786472 Call Girls DubaiDubai Call Girls Wifey O52&786472 Call Girls Dubai
Dubai Call Girls Wifey O52&786472 Call Girls Dubai
 
Beautiful Sapna Vip Call Girls Hauz Khas 9711199012 Call /Whatsapps
Beautiful Sapna Vip  Call Girls Hauz Khas 9711199012 Call /WhatsappsBeautiful Sapna Vip  Call Girls Hauz Khas 9711199012 Call /Whatsapps
Beautiful Sapna Vip Call Girls Hauz Khas 9711199012 Call /Whatsapps
 
Building on a FAIRly Strong Foundation to Connect Academic Research to Transl...
Building on a FAIRly Strong Foundation to Connect Academic Research to Transl...Building on a FAIRly Strong Foundation to Connect Academic Research to Transl...
Building on a FAIRly Strong Foundation to Connect Academic Research to Transl...
 
RS 9000 Call In girls Dwarka Mor (DELHI)⇛9711147426🔝Delhi
RS 9000 Call In girls Dwarka Mor (DELHI)⇛9711147426🔝DelhiRS 9000 Call In girls Dwarka Mor (DELHI)⇛9711147426🔝Delhi
RS 9000 Call In girls Dwarka Mor (DELHI)⇛9711147426🔝Delhi
 
ASML's Taxonomy Adventure by Daniel Canter
ASML's Taxonomy Adventure by Daniel CanterASML's Taxonomy Adventure by Daniel Canter
ASML's Taxonomy Adventure by Daniel Canter
 
How we prevented account sharing with MFA
How we prevented account sharing with MFAHow we prevented account sharing with MFA
How we prevented account sharing with MFA
 
Call Girls In Mahipalpur O9654467111 Escorts Service
Call Girls In Mahipalpur O9654467111  Escorts ServiceCall Girls In Mahipalpur O9654467111  Escorts Service
Call Girls In Mahipalpur O9654467111 Escorts Service
 
Customer Service Analytics - Make Sense of All Your Data.pptx
Customer Service Analytics - Make Sense of All Your Data.pptxCustomer Service Analytics - Make Sense of All Your Data.pptx
Customer Service Analytics - Make Sense of All Your Data.pptx
 
Call Girls In Dwarka 9654467111 Escorts Service
Call Girls In Dwarka 9654467111 Escorts ServiceCall Girls In Dwarka 9654467111 Escorts Service
Call Girls In Dwarka 9654467111 Escorts Service
 
B2 Creative Industry Response Evaluation.docx
B2 Creative Industry Response Evaluation.docxB2 Creative Industry Response Evaluation.docx
B2 Creative Industry Response Evaluation.docx
 
꧁❤ Greater Noida Call Girls Delhi ❤꧂ 9711199171 ☎️ Hard And Sexy Vip Call
꧁❤ Greater Noida Call Girls Delhi ❤꧂ 9711199171 ☎️ Hard And Sexy Vip Call꧁❤ Greater Noida Call Girls Delhi ❤꧂ 9711199171 ☎️ Hard And Sexy Vip Call
꧁❤ Greater Noida Call Girls Delhi ❤꧂ 9711199171 ☎️ Hard And Sexy Vip Call
 
INTERNSHIP ON PURBASHA COMPOSITE TEX LTD
INTERNSHIP ON PURBASHA COMPOSITE TEX LTDINTERNSHIP ON PURBASHA COMPOSITE TEX LTD
INTERNSHIP ON PURBASHA COMPOSITE TEX LTD
 
9711147426✨Call In girls Gurgaon Sector 31. SCO 25 escort service
9711147426✨Call In girls Gurgaon Sector 31. SCO 25 escort service9711147426✨Call In girls Gurgaon Sector 31. SCO 25 escort service
9711147426✨Call In girls Gurgaon Sector 31. SCO 25 escort service
 
PKS-TGC-1084-630 - Stage 1 Proposal.pptx
PKS-TGC-1084-630 - Stage 1 Proposal.pptxPKS-TGC-1084-630 - Stage 1 Proposal.pptx
PKS-TGC-1084-630 - Stage 1 Proposal.pptx
 
Predictive Analysis - Using Insight-informed Data to Determine Factors Drivin...
Predictive Analysis - Using Insight-informed Data to Determine Factors Drivin...Predictive Analysis - Using Insight-informed Data to Determine Factors Drivin...
Predictive Analysis - Using Insight-informed Data to Determine Factors Drivin...
 
9654467111 Call Girls In Munirka Hotel And Home Service
9654467111 Call Girls In Munirka Hotel And Home Service9654467111 Call Girls In Munirka Hotel And Home Service
9654467111 Call Girls In Munirka Hotel And Home Service
 
EMERCE - 2024 - AMSTERDAM - CROSS-PLATFORM TRACKING WITH GOOGLE ANALYTICS.pptx
EMERCE - 2024 - AMSTERDAM - CROSS-PLATFORM  TRACKING WITH GOOGLE ANALYTICS.pptxEMERCE - 2024 - AMSTERDAM - CROSS-PLATFORM  TRACKING WITH GOOGLE ANALYTICS.pptx
EMERCE - 2024 - AMSTERDAM - CROSS-PLATFORM TRACKING WITH GOOGLE ANALYTICS.pptx
 

Superpixel algorithms (whatershed, mean-shift, SLIC, BSLIC), Foolad

  • 3. OUTLINE Introduction1 2 Superpixel algorithms 1 Watershed 2 3 Visual Comparison of algorithms Mean-shift 3 SLIC 3
  • 4. WHAT IS A SUPERPIXEL? A superpixel can be defined as a group of pixels which have similar characteristics. 4
  • 5. ADVANTAGES OF SUPERPIXEL 1. Good adherence to object boundaries 2. reduce the computational complexity from thousands of pixels to a few hundred superpixels 5
  • 7. SUPERPIXEL ALGORITHMS 7 There are many algorithms to segment superpixels: • Whatershed • Mean-Shift • Normalized-Cuts • Graph-based • QuichShift • TurboPixels • SLIC
  • 9. WATERSHED ALGORITHM 9 • Any grey image can be considered as a topographic surface. • flood this surface from its minima • prevent the merging of the waters coming from different sources Watershed algorithm was proposed by Vincent and Soille in 1991 Watershed lines
  • 10. WATERSHED ALGORITHM 10 Watershed algorithm might be used on the gradient image instead of the original image. Gradient imageOriginal image Watershed of the original imageWatershed of the gradient image
  • 11. WATERSHED ALGORITHM 11 in practice, this algorithm produces an over-segmentation due to noise or local irregularities in the gradient image.
  • 13. MEAN-SHIFT ALGORITHM 13 1. Choose a search window size. 2. Choose the initial location of the search window. 3. Compute the mean location (centroid of the data) in the search window. 4. Center the search window at the mean location computed in Step 3. 5. Repeat Steps 3 and 4 until convergence. Mean-shift algorithm was proposed by Comaniciu and Meer in 2002
  • 18. MEAN-SHIFT ALGORITHM 18 finding peaks in the high-dimensional data distribution
  • 19. MEAN-SHIFT ALGORITHM 19 finding peaks in the high-dimensional data distribution in color image
  • 23. SLIC ALGORITHM Simple Linear Iterative Clustering (SLIC) algorithm 24 The Simple Linear Iterative Clustering (SLIC) algorithm was proposed by Radhakrishna Achanta in 2010
  • 26. SLIC 27 For color images, SLIC algorithm works in the LAB color space.
  • 27. COVERT RGB TO LAB COLOR SPACE 28 𝐿 = 116. ℎ 𝑌 𝑌𝑤 − 16 𝐴 = 500 ℎ 𝑋 𝑋 𝑤 − ℎ 𝑌 𝑌𝑤 𝐵 = 200 ℎ 𝑌 𝑌𝑤 − ℎ 𝑍 𝑍 𝑤 ℎ 𝑞 = ቐ 3 𝑞 𝑞 > 0.008856 7.787𝑞 + 16 116 𝑞 ≤ 0.008856 𝑋 𝑌 𝑍 = 0.412453 0.357580 0.180423 0.212671 0.715160 0.072169 0.019334 0.119193 0.950227 𝑅 𝐺 𝐵 𝑋 𝑤=0.950450 𝑌𝑤=1.000000 𝑍 𝑤=0.088754
  • 28. COVERT RGB TO LAB COLOR SPACE B channel Blue-yellow A channel Red-green L channel 29 RGB
  • 29. SLIC EXAMPLE 30 • Each pixel is assigned a 5-valued vector (𝑋, 𝑌, 𝐿, 𝑎, 𝑏) for position and color • Number of pixels: 𝑁 = 1600 • Image size: 40×40 • Number of superpixels: 𝐾 = 16
  • 30. THE MAIN STEPS OF THE SLIC ALGORITHM 1. Initialize 𝐾 cluster centers 𝑪 𝒌 = 𝒍 𝒌, 𝒂 𝒌, 𝒃 𝒌, 𝒙 𝒌, 𝒚 𝒌 𝑻 on a regular grid spaced 𝑆 = 𝑁 𝐾 pixels apart. 31 • each superpixel has approximately 𝑁 𝐾 pixels
  • 32. THE MAIN STEPS OF THE SLIC ALGORITHM 1. Initialize 𝐾 cluster centers 𝑪 𝒌 = 𝒍 𝒌, 𝒂 𝒌, 𝒃 𝒌, 𝒙 𝒌, 𝒚 𝒌 𝑻 on a regular grid spaced 𝑆 = 𝑁 𝐾 pixels apart. 33 • each superpixel has approximately 𝑁 𝐾 pixels 𝑁 𝐾 = 1600 16 = 100 . . . . . . . . . . . . . . . . 𝑪1 𝑆 𝑆 𝑆 = 𝑁 𝐾 = 100 = 10 𝑪5 𝑪9 𝑪13 𝑪2 𝑪6 𝑪10 𝑪14 𝑪3 𝑪7 𝑪11 𝑪15 𝑪4 𝑪8 𝑪12 𝑪16
  • 33. THE MAIN STEPS OF THE SLIC ALGORITHM 2. move these cluster centers to the positions with the lowest gradients in a 3 × 3 neighborhood; This is done to avoid centering a superpixel on an edge, and to reduce to chance of seeding superpixel with a noisy pixel. 34 𝐺 𝑥, 𝑦 = 𝐼 𝑥, 𝑦 − 1 − 𝐼(𝑥, 𝑦 + 1) 2 + 𝐼 𝑥 − 1, 𝑦 − 𝐼(𝑥 + 1, 𝑦) 2 . . . . . . . . . . . . . . . . 𝑪1 𝑪5 𝑪9 𝑪13 𝑪2 𝑪6 𝑪10 𝑪14 𝑪3 𝑪7 𝑪11 𝑪15 𝑪4 𝑪8 𝑪12 𝑪16
  • 34. THE MAIN STEPS OF THE SLIC ALGORITHM 2. move these cluster centers to the positions with the lowest gradients in a 3 × 3 neighborhood; This is done to avoid centering a superpixel on an edge, and to reduce to chance of seeding superpixel with a noisy pixel. 35 𝐺 𝑥, 𝑦 = 𝐼 𝑥, 𝑦 − 1 − 𝐼(𝑥, 𝑦 + 1) 2 + 𝐼 𝑥 − 1, 𝑦 − 𝐼(𝑥 + 1, 𝑦) 2 . . . . . . . . . . . . . . . . 𝑪1 𝑪5 𝑪9 𝑪13 𝑪2 𝑪6 𝑪10 𝑪14 𝑪3 𝑪7 𝑪11 𝑪15 𝑪4 𝑪8 𝑪12 𝑪16 .
  • 35. THE MAIN STEPS OF THE SLIC ALGORITHM 3. Assign pixels. Designate each pixel to a closest cluster center in a local search space; 36 K-means algorithm SLIC algorithm
  • 36. THE MAIN STEPS OF THE SLIC ALGORITHM 3. Assign pixels. Designate each pixel to a closest cluster center in a local search space; 37 for each cluster center 𝑪 𝒌 Assign the best matching pixels from a 𝟐𝑺 × 𝟐𝑺 around the cluster center according to the distance measure. end for . . . . . . . . . . . . . . . . 𝑪1 𝑪5 𝑪9 𝑪13 𝑪2 𝑪6 𝑪10 𝑪14 𝑪3 𝑪7 𝑪11 𝑪15 𝑪4 𝑪8 𝑪12 𝑪16
  • 37. THE MAIN STEPS OF THE SLIC ALGORITHM 3. Assign pixels. Designate each pixel to a closest cluster center in a local search space; 38       2 2 2 c j i j i j id l l a a b b          2 2 s j i j id x x y y    /S N K 2 2 2s c d D d m S         Distance measure Color distance: position distance: 𝐷′ = 𝑑 𝑐 𝑁𝑐 2 + 𝑑 𝑠 𝑁𝑠 2 𝐷′ = 𝑑 𝑐 𝑚 2 + 𝑑 𝑠 𝑆 2 m= Compactness of superpixel
  • 38. COMPACTNESS OF SUPERPIXELS (m) m = 1 m = 20 m = 40 39
  • 39. THE MAIN STEPS OF THE SLIC ALGORITHM 3. Assign pixels. Designate each pixel to a closest cluster center in a local search space by local KMC; 4. Update cluster centers. Set each cluster center as the mean of all pixels in the corresponding cluster; 5. Repeat steps (3)–(4) until the clusters do not change or error (difference between previous cluster and new cluster) is converge. 40 initialization iteration 1 iteration 2 iteration 3 iteration 4
  • 40. THE MAIN STEPS OF THE SLIC ALGORITHM 6. Post-processing. The connected components algorithm is used to reassign isolated regions to nearby superpixels if the size of the isolated regions is smaller than a minimum size 𝑆 𝑚𝑖𝑛. 41 post-processing
  • 42. SLICO SLIC SLICO SLIC uses the same compactness parameter (chosen by user) for all superpixels in the image. SLICO adaptively chooses the compactness parameter for each superpixel differently. 43
  • 43. VISUAL COMPARISON OF ALGORITHMS 44 Watershed 1991 SLIC 2010 Mean-Shift 2002
  • 44. VISUAL COMPARISON OF ALGORITHMS 45
  • 45. ADVANTAGES OF SLIC 46 • low complexity • generate superpixels with compact , regular size and shape • SLIC is simple to use and understand
  • 46. DISADVANTAGE OF SLIC 47 Turbopixels algorithmSLIC algorithmSuperPB algorithmSEEDS algorithm
  • 50. DIFFERENCE BETWEEN SLIC AND BSLIC 51 • initializing cluster centers in hexagon rather than square distribution • choosing some specific edge pixels as cluster centers • incorporating boundary term into the distance measurement during k-means clustering
  • 53. INITIALIZATION OF EDGE CENTERS 54 Edge-across superpixels. (a) Original image with slender rod; (b) Edge image with canny filter operator; (c) Partial enlarged superpixels with only plane centers initialized in hexagon distribution; (d) Partial enlarged superpixels with only plane centers initialized in square distribution. hexagon distribution square distribution
  • 54. PLANE CENTER AND EDGE CENTER 55 Plane center and edge center. Dots in solid black Ci0, Ci1, Ci2, Ci3, Ci4, Ci5 and Ci6 are “plane center”; Square in solid red Ei1 is “edge center”.
  • 55. hexagon distribution square distribution Segmentation without edge cluster center Segmentation with edge cluster center 56
  • 58. Superpixel segmentation results With edge cluster center Segmentation without edge cluster center Segmentation with edge cluster center 59
  • 59. BSLIC ITERATING PROCESS 60 (a) Superpixels with only plane centers; (b) Superpixels with both plane and edge centers; (c) First iterating result of BSLIC; (d) Final segmentation result of BSLIC.
  • 60. BSLIC SUPERPIXELS SEGMENTATION RESULTS 61 m=5 m=15 m=30 k=100 k=500 k=1000
  • 61. PART OF BSLIC EXPERIMENTAL RESULTS 62TurbopixelsSLICSuperPBSEEDSBSLIC
  • 62. REFERENCES [1] Luc Vincent and Pierre Soille. Watersheds in digital spaces: An efficient algorithm based on immersion simulations. IEEE Transactions on Pattern Analalysis and Machine Intelligence, 13(6):583–598, 1991. [2] D. Comaniciu and P. Meer. Mean shift: a robust approach toward feature space analysis. IEEE Transactions on Pattern Analysis and Machine Intelligence, 24(5):603–619, May 2002. [3] Radhakrishna Achanta, Appu Shaji, Kevin Smith, Aurelien Lucchi, Pascal Fua, and Sabine Süsstrunk, SLIC Superpixels Compared to State-of-the-art Superpixel Methods, IEEE Transactions on Pattern Analysis and Machine Intelligence, vol. 34, num. 11, p. 2274 - 2282, May 2012. [4] Radhakrishna Achanta, Appu Shaji, Kevin Smith, Aurelien Lucchi, Pascal Fua, and Sabine Süsstrunk, SLIC Superpixels, EPFL Technical Report no. 149300, June 2010. [5] Hai Wang, Xiongyou Peng, Xue Xiao, and Yan Liu, BSLIC: SLIC Superpixels Based on Boundary Term, Symmetry 2017, 9(3), Feb 2017. 63