New Segmentation Technique

Slides:



Advertisements
Similar presentations
People Counting and Human Detection in a Challenging Situation Ya-Li Hou and Grantham K. H. Pang IEEE TRANSACTIONS ON SYSTEMS, MAN, AND CYBERNETICS—PART.
Advertisements

A Graph based Geometric Approach to Contour Extraction from Noisy Binary Images Amal Dev Parakkat, Jiju Peethambaran, Philumon Joseph and Ramanathan Muthuganapathy.
SOFT SCISSORS: AN INTERACTIVE TOOL FOR REALTIME HIGH QUALITY MATTING International Conference on Computer Graphics and Interactive Techniques ACM SIGGRAPH.
Graph cut Chien-chi Chen.
Presenter : Kuang-Jui Hsu Date : 2011/5/12(Tues.).
I Images as graphs Fully-connected graph – node for every pixel – link between every pair of pixels, p,q – similarity w ij for each link j w ij c Source:
Lecture 07 Segmentation Lecture 07 Segmentation Mata kuliah: T Computer Vision Tahun: 2010.
Foreground Background detection from video Foreground Background detection from video מאת : אבישג אנגרמן.
GrabCut Interactive Image (and Stereo) Segmentation Carsten Rother Vladimir Kolmogorov Andrew Blake Antonio Criminisi Geoffrey Cross [based on Siggraph.
GrabCut Interactive Foreground Extraction using Iterated Graph Cuts Carsten Rother Vladimir Kolmogorov Andrew Blake Microsoft Research Cambridge-UK.
GrabCut Interactive Foreground Extraction using Iterated Graph Cuts Carsten Rother Vladimir Kolmogorov Andrew Blake Microsoft Research Cambridge-UK.
A Gimp Plugin that uses “GrabCut” to perform image segmentation
Interactive Image Segmentation using Graph Cuts Mayuresh Kulkarni and Fred Nicolls Digital Image Processing Group University of Cape Town PRASA 2009.
Stephen J. Guy 1. Photomontage Photomontage GrabCut – Interactive Foreground Extraction 1.
Texture Segmentation Based on Voting of Blocks, Bayesian Flooding and Region Merging C. Panagiotakis (1), I. Grinias (2) and G. Tziritas (3)
GrabCut Interactive Image (and Stereo) Segmentation Joon Jae Lee Keimyung University Welcome. I will present Grabcut – an Interactive tool for foreground.
Image Segmentation some examples Zhiqiang wang
Medical Imaging Mohammad Dawood Department of Computer Science University of Münster Germany.
Lecture 6 Image Segmentation
Learning to Detect A Salient Object Reporter: 鄭綱 (3/2)
Clustering… in General In vector space, clusters are vectors found within  of a cluster vector, with different techniques for determining the cluster.
Region Segmentation. Find sets of pixels, such that All pixels in region i satisfy some constraint of similarity.
Segmentation and Clustering. Segmentation: Divide image into regions of similar contentsSegmentation: Divide image into regions of similar contents Clustering:
Advanced Topics in Computer Vision Spring 2006 Video Segmentation Tal Kramer, Shai Bagon Video Segmentation April 30 th, 2006.
Perceptual Organization: Segmentation and Optical Flow.
IEEE TRANSACTIONS ON IMAGE PROCESSING, VOL. 20, NO. 11, NOVEMBER 2011 Qian Zhang, King Ngi Ngan Department of Electronic Engineering, the Chinese university.
Image Segmentation Rob Atlas Nick Bridle Evan Radkoff.
Proceedings of the 2004 IEEE Computer Society Conference on Computer Vision and Pattern Recognition (CVPR’04) /04 $20.00 c 2004 IEEE 1 Li Hong.
New Segmentation Methods Advisor : 丁建均 Jian-Jiun Ding Presenter : 蔡佳豪 Chia-Hao Tsai Date: Digital Image and Signal Processing Lab Graduate Institute.
FRIP: A Region-Based Image Retrieval Tool Using Automatic Image Segmentation and Stepwise Boolean AND Matching IEEE TRANSACTIONS ON MULTIMEDIA, VOL. 7,
Exploring the Parameter Space of Image Segmentation Algorithms Talk at NCHU p 1 TexPoint fonts used in EMF. Read the TexPoint manual before you.
Prakash Chockalingam Clemson University Non-Rigid Multi-Modal Object Tracking Using Gaussian Mixture Models Committee Members Dr Stan Birchfield (chair)
Graph-based Segmentation. Main Ideas Convert image into a graph Vertices for the pixels Vertices for the pixels Edges between the pixels Edges between.
1Ellen L. Walker Segmentation Separating “content” from background Separating image into parts corresponding to “real” objects Complete segmentation Each.
COMMON EVALUATION FINAL PROJECT Vira Oleksyuk ECE 8110: Introduction to machine Learning and Pattern Recognition.
Object Stereo- Joint Stereo Matching and Object Segmentation Computer Vision and Pattern Recognition (CVPR), 2011 IEEE Conference on Michael Bleyer Vienna.
CSE 185 Introduction to Computer Vision Pattern Recognition 2.
Color Image Segmentation Speaker: Deng Huipeng 25th Oct , 2007.
Data Extraction using Image Similarity CIS 601 Image Processing Ajay Kumar Yadav.
Digital Camera and Computer Vision Laboratory Department of Computer Science and Information Engineering National Taiwan University, Taipei, Taiwan, R.O.C.
Image Enhancement [DVT final project]
A Region Based Stereo Matching Algorithm Using Cooperative Optimization Zeng-Fu Wang, Zhi-Gang Zheng University of Science and Technology of China Computer.
Color Image Segmentation Advisor : 丁建均 Jian-Jiun Ding Presenter : 蔡佳豪 Chia-Hao Tsai Date: Digital Image and Signal Processing Lab Graduate Institute.
Gaussian Mixture Models and Expectation-Maximization Algorithm.
CSSE463: Image Recognition Day 23 Midterm behind us… Midterm behind us… Foundations of Image Recognition completed! Foundations of Image Recognition completed!
Journal of Visual Communication and Image Representation
CS654: Digital Image Analysis Lecture 28: Advanced topics in Image Segmentation Image courtesy: IEEE, IJCV.
Clustering Algorithms Sunida Ratanothayanon. What is Clustering?
Digital Camera and Computer Vision Laboratory Department of Computer Science and Information Engineering National Taiwan University, Taipei, Taiwan, R.O.C.
Implementing the By: Matthew Marsh Supervisors: Prof Shaun Bangay Mrs Adele Lobb segmentation technique as a plugin for the GIMP.
Color Image Segmentation Mentor : Dr. Rajeev Srivastava Students: Achit Kumar Ojha Aseem Kumar Akshay Tyagi.
Cutting Images: Graphs and Boundary Finding Computational Photography Derek Hoiem, University of Illinois 09/20/12 “The Double Secret”, Magritte.
May 2003 SUT Color image segmentation – an innovative approach Amin Fazel May 2003 Sharif University of Technology Course Presentation base on a paper.
Graph-based Segmentation
Course : T Computer Vision
IMAGE PROCESSING RECOGNITION AND CLASSIFICATION
GrabCut Interactive Foreground Extraction using Iterated Graph Cuts Carsten Rother Vladimir Kolmogorov Andrew Blake Microsoft Research Cambridge-UK.
CSSE463: Image Recognition Day 21
Project Progress and Future Plans By: Matthew Marsh
Image Segmentation Techniques
Dingding Liu* Yingen Xiong† Linda Shapiro* Kari Pulli†
CSSE463: Image Recognition Day 23
Presented by: Yang Yu Spatiotemporal GMM for Background Subtraction with Superpixel Hierarchy Mingliang Chen, Xing Wei, Qingxiong.
Pattern Classification All materials in these slides were taken from Pattern Classification (2nd ed) by R. O. Duda, P. E. Hart and D. G. Stork, John.
“grabcut”- Interactive Foreground Extraction using Iterated Graph Cuts
CSSE463: Image Recognition Day 23
A Block Based MAP Segmentation for Image Compression
CSSE463: Image Recognition Day 23
EM Algorithm and its Applications
Presentation transcript:

New Segmentation Technique Speaker: Yu-Hsiang Wang Advisor: Prof. Jian-Jung Ding Digital Image and Signal Processing Lab Graduate Institute of Communication Engineering National Taiwan University DISP Lab, Graduate Institute of Communication Engineering, NTU

Outline Introduction JSEG GrabCut Conclusion Criterion for Segmentation Seed Determination Seed Growing Region Merge GrabCut Iterative minimization User editing Conclusion DISP Lab, Graduate Institute of Communication Engineering, NTU

Introduction We introduce two segmentation methods in this report: JSEG and GrabCut. JSEG is based on the concept of region growing. GrabCut is an interactive foreground/background segmentation in image. DISP Lab, Graduate Institute of Communication Engineering, NTU

JSEG[1] [1] DISP Lab, Graduate Institute of Communication Engineering, NTU

JSEG(Criterion for Segmentation) A color quantization algorithm is applied to image. [2] Each pixel is assigned its corresponding color class label. Estimate region by J value: ST and SW are an variance. DISP Lab, Graduate Institute of Communication Engineering, NTU

JSEG(Criterion for Segmentation) Total variance where z is coordinate and m is mean of coordinate. Mean of variance of each class where mi is the mean coordinate of class Zi. DISP Lab, Graduate Institute of Communication Engineering, NTU

JSEG(Criterion for Segmentation) An example of different class-maps and their corresponding J values. DISP Lab, Graduate Institute of Communication Engineering, NTU

JSEG(Criterion for Segmentation) Segmented class-map and value number of points in region k DISP Lab, Graduate Institute of Communication Engineering, NTU

JSEG(Criterion for Segmentation) Use local J value to implement region growing, where local J compute by windows: Scale 1 Scale 2 DISP Lab, Graduate Institute of Communication Engineering, NTU

JSEG [1] DISP Lab, Graduate Institute of Communication Engineering, NTU

JSEG(Seed Determination) Step 1: Compute the average and the standard deviation of the local J values. Step 2: Set threshold Step 3: Pixels with local J values less than TJ are set as candidate seed points. DISP Lab, Graduate Institute of Communication Engineering, NTU

JSEG(Seed Determination) Step 4: Associate candidate seed points as seed area if its size larger than minimum size. DISP Lab, Graduate Institute of Communication Engineering, NTU

JSEG [1] DISP Lab, Graduate Institute of Communication Engineering, NTU

JSEG(Seed Growing) Step 1: Remove “holes” in the seed areas. Step 2: Compute the average of the local J values in the remaining unsegmented part of the region. Seed area hole Seed area DISP Lab, Graduate Institute of Communication Engineering, NTU

JSEG(Seed Growing) Step 3: Connect pixels below the average to compose growing areas. Step 4: If a growing area is adjacent to one and only one seed, we merge it into that seed. Seed area DISP Lab, Graduate Institute of Communication Engineering, NTU

JSEG(Seed Growing) Step 5: Compute local J values of the remaining unsegmented pixels at the next smaller scale and repeat region growing. Step 6: At the smallest scale, the remaining pixels are grown one by one. Seed area DISP Lab, Graduate Institute of Communication Engineering, NTU

JSEG [1] DISP Lab, Graduate Institute of Communication Engineering, NTU

JSEG(Region Merge) Use color histogram to determine if two regions can be merged or not. The Euclidean distance between two color histograms i and j : This method is based on the agglomerative method. [3] DISP Lab, Graduate Institute of Communication Engineering, NTU

JSEG(Region Merge) Hierarchical agglomerative algorithm: [3] DISP Lab, Graduate Institute of Communication Engineering, NTU

JSEG(Segmentation Results) [1] DISP Lab, Graduate Institute of Communication Engineering, NTU

JSEG(Segmentation Results) [1] DISP Lab, Graduate Institute of Communication Engineering, NTU

GrabCut [5] Interactive tool for segmentation. Several method: DISP Lab, Graduate Institute of Communication Engineering, NTU

GrabCut Color data modeling Iterative energy minimization Gaussian Mixture Model (GMM) Background GMM and foreground GMM full-covariance Gaussian mixture with K components (typically K = 5). Iterative energy minimization DISP Lab, Graduate Institute of Communication Engineering, NTU

GrabCut(Gaussian Mixture Model) Why do not use one Gaussian distribution to model foreground(or back) Posit RG distribution of data foreground Use one Gaussian distribution model Use Gaussian mixture model DISP Lab, Graduate Institute of Communication Engineering, NTU

GrabCut(Gaussian Mixture Model) Compute the probability of assigning component j to data i, i is the no. of data and j is the no. of component. j=1 j=3 j=4 j=2 和K mean 不同之處在於,K mean每一個pixel只對一群有影響,而GMM每一個pixel對每個component都有影響力(因為是算被歸類成每一個的機率) DISP Lab, Graduate Institute of Communication Engineering, NTU

GrabCut(Initialization) User initializes trimap T, the background is set TB, foreground TF is empty and for and for . Initialize background and foreground GMMs from sets and . TB TU DISP Lab, Graduate Institute of Communication Engineering, NTU

GrabCut(Iterative minimization) Step 1: Assign GMM components to pixels, for each n in TU. where data 這一步會根據前景與背景的GMM,來決定每個data是算前景or背景,下一步則是重新學習GMM的model參數 mixture weighting coefficients Gaussian probability distribution DISP Lab, Graduate Institute of Communication Engineering, NTU

GrabCut(Iterative minimization) Step 2: Learn GMM parameters from data z. where Account of color GMM models 根據前一步重新分類的前景與背景點,來修正前景與背景的GMM model參數 DISP Lab, Graduate Institute of Communication Engineering, NTU

GrabCut(Iterative minimization) Step 3: Estimate segmentation by using min cut. where Repeat from Step 1 until convergence. color GMM model Smoothness term 猜測這一步是根據前兩步得到的結果,重新估計TU的範圍 (TB的補數) DISP Lab, Graduate Institute of Communication Engineering, NTU

GrabCut(Iterative minimization) Smoothness term ensures the appropriate high and low contrast, depending on zm and zn. 50 set of pairs of neighboring Smooth term 猜測可能是為了影響color GMM model 作一些可能類似是前景又是背景的pixel做微調動作,方式是考慮其鄰居點的顏色與他的關係 DISP Lab, Graduate Institute of Communication Engineering, NTU

GrabCut(Border matting) To smooth the boundary. Begin with a closed contour C. Apply dynamic programming algorithm for estimating throughout TU. 經過前面Iterative minimization的處理後已經得到前景與背景,因此可以畫出Contour C,根據C可以畫出一條封閉線(黃),在圈出寬度為2w的TU區域對此處重新做分配這部份的點為前景或背景。主要是運用DP對這些點作運算,因為DP可以去設定說顏色比較相近的點連續的話,weight比較重(ex: 我是皮膚色,下一點也是皮膚色的可能性上升,因把不是皮膚色的點設為背景),這樣重新分配的前景就會比較smooth DISP Lab, Graduate Institute of Communication Engineering, NTU

GrabCut(Border matting) Border matting result: DISP Lab, Graduate Institute of Communication Engineering, NTU

GrabCut(User editing) DISP Lab, Graduate Institute of Communication Engineering, NTU

GrabCut(Segmentation Results) DISP Lab, Graduate Institute of Communication Engineering, NTU

Conculsion JSEG GrabCut It both considers the similarity of colors and their distributions. Performance is better than Region growing and its time cost also small. GrabCut It can be applied for some image processing software, e.g. Photoshop. Also for some interactive entertainment systems, e.g. Smartphone and video game. DISP Lab, Graduate Institute of Communication Engineering, NTU

Reference [1] Y. Deng, and B.S. Manjunath, “Unsupervised segmentation of color-texture re-gions in images and video,” IEEE Trans. Pattern Anal. Machine Intell., vol. 23, no. 8, pp. 800-810, Aug. 2001. [2] Y. Deng, C. Kenney, M.S. Moore, and B.S. Manjunath, “Peer group filtering and perceptual color image quantization,” Proc. IEEE Int'l Symp. Circuits and Systems, vol. 4, pp. 21-24, Jul. 1999. [3] R.O. Duda and P.E. Hart, Pattern Classification and Scene Analysis. New York: John Wiley&Sons, 1970. [4] A. K. Jain, M. N. Murty, and P. J. Flynn, “Data clustering: a review,” ACM Computing Surveys, vol. 31, issue 3, pp. 264-323, Sep. 1999. [5] C. Rother, V. Kolmogorov, and A. Blake, “Grabcut: Interactive foreground extraction using iterated graph cuts,” ACM Transactions on Graphics, vol. 23, issue 3, pp. 309-314, Aug. 2004. DISP Lab, Graduate Institute of Communication Engineering, NTU