Background Estimation Mehdi Ghayoumi, MD Iftakharul Islam, Muslem Al-Saidi Department of Computer Science Kent State University, Kent, OH 44242.

Slides:



Advertisements
Similar presentations
Wang Tiles for Image and Texture Generation
Advertisements

Object Removal by Exemplar-Based Inpainting Ye Hong CS766 Fall 2004.
Image Repairing: Robust Image Synthesis by Adaptive ND Tensor Voting IEEE Computer Society Conference on Computer Vision and Pattern Recognition Jiaya.
SOFT SCISSORS: AN INTERACTIVE TOOL FOR REALTIME HIGH QUALITY MATTING International Conference on Computer Graphics and Interactive Techniques ACM SIGGRAPH.
Analysis of Contour Motions Ce Liu William T. Freeman Edward H. Adelson Computer Science and Artificial Intelligence Laboratory Massachusetts Institute.
1 Building a Dictionary of Image Fragments Zicheng Liao Ali Farhadi Yang Wang Ian Endres David Forsyth Department of Computer Science, University of Illinois.
GrabCut Interactive Image (and Stereo) Segmentation Carsten Rother Vladimir Kolmogorov Andrew Blake Antonio Criminisi Geoffrey Cross [based on Siggraph.
Jue Wang Michael F. Cohen IEEE CVPR Outline 1. Introduction 2. Failure Modes For Previous Approaches 3. Robust Matting 3.1 Optimized Color Sampling.
Video Inpainting Under Constrained Camera Motion Kedar A. Patwardhan, Student Member, IEEE, Guillermo Sapiro, Senior Member, IEEE, and Marcelo Bertalm.
Texture Segmentation Based on Voting of Blocks, Bayesian Flooding and Region Merging C. Panagiotakis (1), I. Grinias (2) and G. Tziritas (3)
Hierarchical Saliency Detection School of Electronic Information Engineering Tianjin University 1 Wang Bingren.
1 25 Years of Computer Graphics: Back to the Future? John PATTERSON Computer Vision and Graphics Group Dept of Computing Science University of GLASGOW.
AAM based Face Tracking with Temporal Matching and Face Segmentation Dalong Du.
Active Contour Models (Snakes)
蔡秉宸 IEEE Transactions on Image Processing Sch. of Sci., Xi'an Jiaotong Univ., Xi'an, China.
Video Coding with Spatio-temporal Texture Synthesis and Edge-based inpainting Chunbo Zhu, Xiaoyan Sun, Feng Wu, and Houqiang Li ICME 2008.
Maryia Kazakevich “Texture Synthesis by Patch-Based Sampling” Texture Synthesis by Patch-Based Sampling Real-Time Texture Synthesis By Patch-Based Sampling,
1 Image Completion using Global Optimization Presented by Tingfan Wu.
Announcements Project 4 questions? Guest lectures Thursday: Richard Ladner “tactile graphics” Next Tuesday: Jenny Yuen and Jeff Bigham.
Efficient Moving Object Segmentation Algorithm Using Background Registration Technique Shao-Yi Chien, Shyh-Yih Ma, and Liang-Gee Chen, Fellow, IEEE Hsin-Hua.
Order-Independent Texture Synthesis Li-Yi Wei Marc Levoy Gcafe 1/30/2003.
Image Quilting for Texture Synthesis and Transfer Alexei A. Efros1,2 William T. Freeman2.
Object Detection and Tracking Mike Knowles 11 th January 2005
Simultaneous Structure and Texture Image Inpainting by: Bertalmio, Sapiro, Vese, Osher Presented by: Shane Brennan June 7, 2007 EE 264 – Spring 2007.
Region Filling and Object Removal by Exemplar-Based Image Inpainting
1 Integration of Background Modeling and Object Tracking Yu-Ting Chen, Chu-Song Chen, Yi-Ping Hung IEEE ICME, 2006.
An Iterative Optimization Approach for Unified Image Segmentation and Matting Hello everyone, my name is Jue Wang, I’m glad to be here to present our paper.
Behavior Analysis Midterm Report Lipov Irina Ravid Dan Kotek Tommer.
Media Re-expression for Stereo Cinema Félix Raimbault, François Pitié and Anil Kokaram 1.
Video Motion Interpolation for Special Effect Applications Timothy K. Shih, Senior Member, IEEE, Nick C. Tang, Joseph C. Tsai, and Jenq-Neng Hwang, Fellow,
Summer School on Image Processing 2009, Debrecen, Hungary Colour image processing for SHADOW REMOVAL Alina Elena Oprea, University Politehnica of Bucharest.
Abstract Some Examples The Eye tracker project is a research initiative to enable people, who are suffering from Amyotrophic Lateral Sclerosis (ALS), to.
Efficient Editing of Aged Object Textures By: Olivier Clément Jocelyn Benoit Eric Paquette Multimedia Lab.
Graph Abstraction for Simplified Proofreading of Slice-based Volume Segmentation Ronell Sicat 1, Markus Hadwiger 1, Niloy Mitra 1,2 1 King Abdullah University.
Reporter: Zhonggui Chen
Reconstructing 3D mesh from video image sequences supervisor : Mgr. Martin Samuelčik by Martin Bujňák specifications Master thesis
Plug-in and tutorial development for GIMP- Cathy Irwin, 2004 The Development of Image Completion and Tutorial Plug-ins for the GIMP By: Cathy Irwin Supervisors:
1 Optimal Cycle Vida Movahedi Elder Lab, January 2008.
Feature-preserving Artifact Removal from Dermoscopy Images Howard Zhou 1, Mei Chen 2, Richard Gass 2, James M. Rehg 1, Laura Ferris 3, Jonhan Ho 3, Laura.
Previous lecture Texture Synthesis Texture Transfer + =
Depth Edge Detection with Multi- Flash Imaging Gabriela Martínez Final Project – Processamento de Imagem IMPA.
Feature-Based Stereo Matching Using Graph Cuts Gorkem Saygili, Laurens van der Maaten, Emile A. Hendriks ASCI Conference 2011.
Real-Time Exemplar-Based Face Sketch Synthesis Pipeline illustration Note: containing animations Yibing Song 1 Linchao Bao 1 Qingxiong Yang 1 Ming-Hsuan.
Synthesizing Natural Textures Michael Ashikhmin University of Utah.
Graphcut Textures Image and Video Synthesis Using Graph Cuts
October 1, 2013Computer Vision Lecture 9: From Edges to Contours 1 Canny Edge Detector However, usually there will still be noise in the array E[i, j],
Geometry Synthesis Ares Lagae Olivier Dumont Philip Dutré Department of Computer Science Katholieke Universiteit Leuven 10 August, 2004.
Quiz Week 8 Topical. Topical Quiz (Section 2) What is the difference between Computer Vision and Computer Graphics What is the difference between Computer.
Student: Chih-Wei Fang ( 方志偉 ) Adviser: Jenn-Jier James Lien ( 連震杰 ) Robotics Laboratory, Department of Computer Science and Information Engineering, National.
Improving Image Matting using Comprehensive Sampling Sets CVPR2013 Oral.
Edge Segmentation in Computer Images CSE350/ Sep 03.
Computer Vision Computer Vision based Hole Filling Chad Hantak COMP December 9, 2003.
Center for Machine Perception Department of Cybernetics Faculty of Electrical Engineering Czech Technical University in Prague Segmentation Based Multi-View.
SIGGRAPH 2007 Hui Fang and John C. Hart.  We propose an image editing system ◦ Preserve its detail and orientation by resynthesizing texture from the.
Plug-in and tutorial development for GIMP- Cathy Irwin, 2004 The Development of Image Completion and Tutorial Plug-ins for GIMP By: Cathy Irwin Supervisors:
Technological Uncanny K. S'hell, C Kurtz, N. Vincent et E. André et M. Beugnet 1.
Video Motion Interpolation for Special Effect Applications
Announcements Project 4 out today help session at the end of class.
Hole Filling 관련 논문 장호욱.
Fast Preprocessing for Robust Face Sketch Synthesis
A New Approach to Track Multiple Vehicles With the Combination of Robust Detection and Two Classifiers Weidong Min , Mengdan Fan, Xiaoguang Guo, and Qing.
Data-driven methods: Texture 2 (Sz 10.5)
Texture Quality Extensions to Image Quilting
Counting Iron-Absorbed Small Intestinal Cells
Analysis of Contour Motions
Grape Detection in Vineyards
Depth Aware Inpainting for Novel View Synthesis Jayant Thatte
Texture Synthesis and Transfer
--- Range Image Registration
Presentation transcript:

Background Estimation Mehdi Ghayoumi, MD Iftakharul Islam, Muslem Al-Saidi Department of Computer Science Kent State University, Kent, OH

Objective Fill in the area of an image based on existing background User selects an area, which is then filled based on surrounding pixels Smooth transitions

Introduction Object Removal – Remove object(s) from image – Fill the hole with information extracted from the surrounding area. Filled region should look “realistic” to the human eyes

Example Source Image Target Final Image

Greedy Approach A Greedy Patch-based Image Inpainting Framework

Diffusion-based Approach The idea is to track perfectly the local geometry of the damaged image and allowing diffusion only in the isophotes curves direction.

Exemplar Based Approach Idea 1. Sample color values of the surrounding area 2. Generate textures with sampling result to fill the hole

Criminisi’s Algorithm Assign each pixel with a priority value Give linear structures higher priorities

Criminisi’s Algorithm P(p) = C(p)D(p) Confidence term Data term 1. Compute the filling priority

Criminisi’s Algorithm (a) The confidence term assigns high filling priority to out-pointing appendices (in green) and low priority to in-pointing ones (in red), thus trying to achieve a smooth and roughly circular target boundary. (b) The data term gives high priority to pixels on the continuation of image structures (in green) and has the effect of favoring in-pointing appendices in the direction of incoming structures. Effects of data and confidence terms

Criminisi’s Algorithm 2. Search for the best matching patch

Criminisi’s Algorithm In this step, the algorithm fills the region corresponding to Ψp∩Ω by replicating the corresponding region in the best matching patch Ψ ^q to the target patch Ψp. Besides, the boundary of the target region δΩ has to be renewed. 3. Copy the best matching patch information and refresh the boundary of target region

Criminisi’s Algorithm(cont.) Structure Propagation by exemplar-based texture synthesis

Criminisi’s Algorithm(cont.)

Improved Criminisi’s Algorithm(cont.)

Expected Results Input Output

Future Work Implementing Algorithms in JAVA Make and install its Plugin in Imagej

Future Work More accurate propagation of curve structures Solve the problems

References A. Criminisi, P. Perez, K. Toyama. Region filling and object removal by exemplar-based Inpainting, IEEE Transactions on Image Processing,2004. Christine Guillemot and Olivier Le Meur,Image Inpainting, Signal Processing Magazin,IEEE,2014. Jing Wang and et all, Robust object removal with an exemplar-based image inpainting approach,Neurocomputing, IEEE,2014.

Thanks!