Thinking Beyond the Block Block Matching for Copy Move Forgery Detection Revisited
|
|
|
- Frederick Short
- 6 years ago
- Views:
Transcription
1 Thinking Beyond the Block Block Matching for Copy Move Forgery Detection Revisited Matthias Kirchner Pascal Schöttle Christian Riess Binghamton University University of Münster Stanford University IS&T/SPIE Media Watermarking, Security, and Forensics San Francisco, CA February 9, 2015
2 Yet Another Paper CMFD Paper? general detection/localization procedure since 2003 [Fridrich et al. 2003] suspect image pre-processing color space transforms saturated regions localization overlapping blocks key points (SIFT,... ) feature representation matching find similar blocks / key points in the feature space duplicated image regions error reduction remove false positives 2
3 Lexicographic Matching lexicographic sorting of feature vectors [Fridrich et al. 2003] compare i-th sorted vector to K neighbors f i search depth K
4 Yet Another Paper CMFD Paper? general detection/localization procedure since 2003 [Fridrich et al. 2003] suspect image pre-processing color space transforms saturated regions localization overlapping blocks key points (SIFT,... ) feature representation matching find similar blocks / key points in the feature space duplicated image regions error reduction remove false positives 4
5 Yet Another Paper CMFD Paper? general detection/localization procedure since 2003 [Fridrich et al. 2003] suspect image pre-processing color space transforms saturated regions localization overlapping blocks key points (SIFT,... ) feature representation matching find similar blocks / key points in the feature space duplicated image regions error reduction remove false positives 4
6 Yet Another Paper CMFD Paper? general detection/localization procedure since 2003 [Fridrich et al. 2003] suspect image pre-processing color space transforms saturated regions localization overlapping blocks key points (SIFT,... ) feature representation matching find similar blocks / key points in the feature space duplicated image regions error reduction remove false positives 4
7 Block-Based? reported typical runtimes (single-thread) blocks Zernike moments SIFT GRIP database (0.75 MP) 54 s 4 s [Cozzolino et al. 2014] Erlangen database (8 MP) 4900 s 126 s [Christlein et al. 2012], matching step only 5
8 Block-Based? reported typical runtimes (single-thread) blocks Zernike moments SIFT GRIP database (0.75 MP) 54 s 4 s [Cozzolino et al. 2014] Erlangen database (8 MP) 4900 s 126 s [Christlein et al. 2012], matching step only GRIP DB image TP C blocks SIFT 5
9 Block-Based? reported typical runtimes (single-thread) blocks Zernike moments SIFT GRIP database (0.75 MP) 54 s 4 s [Cozzolino et al. 2014] Erlangen database (8 MP) 4900 s 126 s [Christlein et al. 2012], matching step only GRIP DB image TP C blocks block-based kd tree matching is the method of choice for most accurate CMFD 5
10 Working Assumptions copied regions are spatially connected subsets of feature vectors {f i } we focus on rigid translations only feature vectors can be quantized to integers, f i x i N goal find all repeated occurrences of connected patches of integers 6
11 Bit Twiddling For One Dimension d d d x X N index matrix X N
12 Bit Twiddling For One Dimension d d d x X N index matrix X N >>2 >>1 7
13 Bit Twiddling For One Dimension d d d x X N index matrix X N >>2 >>
14 Bit Twiddling For One Dimension x X N d d d 1 2 shift/and for all blocks re-use earlier shifts buffer columns for non-unique elements index matrix X N >>2 >>
15 Extension to 2D column-major vectorization of the input 1st column 2nd column 3rd column 8
16 Extension to 2D column-major vectorization of the input to find duplicate w 1 patches d d d 1st column 2nd column 3rd column 8
17 Extension to 2D column-major vectorization of the input to find duplicate w 1 patches special treatment of border elements d 1st column 2nd column 3rd column 8
18 Extension to 2D 1st column 2nd column 3rd column column-major vectorization of the input to find duplicate w 1 patches special treatment of border elements varying masks for spatially inadmissible patches 8
19 Extension to 2D 1st column 2nd column 3rd column column-major vectorization of the input to find duplicate w 1 patches special treatment of border elements varying masks for spatially inadmissible patches 8
20 Extension to 2D 1st column 2nd column 3rd column column-major vectorization of the input to find duplicate w 1 patches special treatment of border elements varying masks for spatially inadmissible patches 8
21 Typical Results GRIP-UNINA Database, intensity-based exact matching, 5 1 patches BitMatch TP C TP C ground truth 9
22 Typical Results GRIP-UNINA Database, intensity-based exact matching, 5 1 patches bitmatch TP C TP C ground truth 9
23 Quantitative Results The Rise of Lexicographic Matching BitMatch total time for matching [s] image number GRIP-UNINA Database F-measure: F = F-measure 2TP 2TP + FP + FN runtime BitMatch
24 Quantitative Results The Rise of Lexicographic Matching total time for matching [s] BitMatch Lexi10 F-measure: F = F-measure 2TP 2TP + FP + FN runtime BitMatch Lexi image number GRIP-UNINA Database 10
25 Quantitative Results The Rise of Lexicographic Matching total time for matching [s] BitMatch Lexi10 Lexi100 Lexi F-measure: F = F-measure 2TP 2TP + FP + FN runtime BitMatch Lexi Lexi Lexi image number GRIP-UNINA Database 10
26 Quantitative Results The Rise of Lexicographic Matching total time for matching [s] BitMatch Lexi10 Lexi100 Lexi F-measure: F = F-measure 2TP 2TP + FP + FN runtime BitMatch Lexi Lexi Lexi image number GRIP-UNINA Database 10
27 Quantitative Results The Fall of BitMatch total time for matching [s] BitMatch Lexi10 Lexi100 Lexi500 average time for matching [s] BitMatch Lexi image number image size GRIP-UNINA Database Dresden Image Database 10
28 Bottlenecks BitMatch runtime [s] number of ANDs
29 Bottlenecks BitMatch runtime [s] texture number of ANDs
30 Bottlenecks BitMatch lexicographic matching runtime [s] texture runtime [s] number of ANDs time to search rows [s] 11
31 Bottlenecks BitMatch lexicographic matching runtime [s] texture runtime [s] smoothness number of ANDs time to search rows [s] 11
32 Back to the Roots blocks 800 equal shifts F-measure intensity-based features BRAVO kd BRAVO lexi WANG kd WANG lexi LIN kd LIN lexi LUO kd LUO lexi Erlangen DB sorted image index 12
33 Back to the Roots blocks 800 equal shifts F-measure moment-based features BLUR kd BLUR lexi HU kd HU lexi ZERNIKE kd ZERNIKE lexi Erlangen DB sorted image index 12
34 Back to the Roots blocks 800 equal shifts F-measure frequency-based features DCT kd DCT lexi DWT kd DWT lexi FMT kd FMT lexi Erlangen DB sorted image index 12
35 Summary BitMatch replace feature-matching with index-based bit-wise operations to find all exact duplications 13
36 Summary BitMatch replace feature-matching with index-based bit-wise operations to find all exact duplications current implementation has some (limited) benefits, but in general lexicographic matching works surprisingly well 13
37 Summary BitMatch replace feature-matching with index-based bit-wise operations to find all exact duplications current implementation has some (limited) benefits, but in general lexicographic matching works surprisingly well Back to the Roots? re-evaluation of kd-tree predominance highly recommended 13
38 Summary BitMatch replace feature-matching with index-based bit-wise operations to find all exact duplications current implementation has some (limited) benefits, but in general lexicographic matching works surprisingly well Back to the Roots? re-evaluation of kd-tree predominance highly recommended Future Work: Exact Matching? make working assumption of scalar feature-vector representations work 13
39 Summary BitMatch replace feature-matching with index-based bit-wise operations to find all exact duplications current implementation has some (limited) benefits, but in general lexicographic matching works surprisingly well Back to the Roots? re-evaluation of kd-tree predominance highly recommended Future Work: Exact Matching? make working assumption of scalar feature-vector representations work source code available: ws.binghamton.edu/kirchner 13
40 Thinking Beyond the Block Block Matching for Copy Move Forgery Detection Revisited Matthias Kirchner Pascal Schöttle Christian Riess Binghamton University University of Münster Stanford University IS&T/SPIE Media Watermarking, Security, and Forensics San Francisco, CA February 9, 2015
THE goal of blind image forensics is to determine the. An Evaluation of Popular Copy-Move Forgery Detection Approaches
IEEE TRANSACTIONS ON INFORMATION FORENSICS AND SECURITY 1 An Evaluation of Popular Copy-Move Forgery Detection Approaches Vincent Christlein, Student Member, IEEE, Christian Riess, Student Member, IEEE,
DYADIC WAVELETS AND DCT BASED BLIND COPY-MOVE IMAGE FORGERY DETECTION
DYADIC WAVELETS AND DCT BASED BLIND COPY-MOVE IMAGE FORGERY DETECTION Ghulam Muhammad*,1, Muhammad Hussain 2, Anwar M. Mirza 1, and George Bebis 3 1 Department of Computer Engineering, 2 Department of
Copy Move Forgery using Hu s Invariant Moments and Log-Polar Transformations
Copy Move Forgery using Hu s Invariant Moments and Log-Polar Transformations Tejas K, Swathi C, Rajesh Kumar M, Senior member, IEEE School of Electronics Engineering Vellore Institute of Technology Vellore,
Simulative Comparison of Copy- Move Forgery Detection Methods for Digital Images
Simulative Comparison of Copy- Move Forgery Detection Methods for Digital Images Harpreet Kaur 1, Jyoti Saxena 2 and Sukhjinder Singh 3 1 Research Scholar, 2 Professor and 3 Assistant Professor 1,2,3 Department
ON ROTATION INVARIANCE IN COPY-MOVE FORGERY DETECTION. Vincent Christlein, Christian Riess and Elli Angelopoulou
ON ROTATION INVARIANCE IN COPY-MOVE FORGERY DETECTION Vincent Christlein, Christian Riess and Elli Angelopoulou Pattern Recognition Lab University of Erlangen-Nuremberg sivichri@stud.informatik.uni-erlangen.de,
Copy-Move Forgery Detection using DCT and SIFT
Copy-Move Forgery Detection using DCT and SIFT Amanpreet Kaur Department of Computer Science and Engineering, Lovely Professional University, Punjab, India. Richa Sharma Department of Computer Science
SURF-based Detection of Copy-Move Forgery in Flat Region
SURF-based Detection of Copy-Move Forgery in Flat Region 1 Guang-qun Zhang, *2 Hang-jun Wang 1,First Author,* 2Corresponding Author School of Information Engineering, Zhejiang A&F University, 311300, Lin
A Study of Copy-Move Forgery Detection Scheme Based on Segmentation
IJCSNS International Journal of Computer Science and Network Security, VOL.18 No.7, July 2018 27 A Study of Copy-Move Forgery Detection Scheme Based on Segmentation Mohammed Ikhlayel, Mochamad Hariadi
Improved DSIFT Descriptor based Copy-Rotate-Move Forgery Detection
Improved DSIFT Descriptor based Copy-Rotate-Move Forgery Detection Ali Retha Hasoon Khayeat 1,2, Xianfang Sun 1, Paul L. Rosin 1 1 School of Computer Science & Informatices, Cardi University, UK KhayeatAR@Cardiff.ac.uk,
Copy-Move Image Forgery Detection Based on Center-Symmetric Local Binary Pattern
IOSR Journal of Computer Engineering (IOSR-JCE) e-issn: 2278-0661,p-ISSN: 2278-8727, Volume 17, Issue 4, Ver. I (July Aug. 2015), PP 66-70 www.iosrjournals.org Copy-Move Image Forgery Detection Based on
Methodology for Evidence Reconstruction in Digital Image Forensics
Methodology for Evidence Reconstruction in Digital Image Forensics Kalpana Manudhane* ME(CSE) 2nd year G.H. Riasoni College of Engineering & Management, Amravati, Maharashtra, India Mr. M.M. Bartere ME(CSE)
Cloning Localization Based On Feature Extraction and K-Means Clustering
Cloning Localization Based On Feature Extraction and K-Means Clustering Areej S. Alfraih, Johann A. Briffa, and Stephan Wesemeyer Department of Computing, University of Surrey, Guildford GU2 7XH, UK a.alfraih@surrey.ac.uk
On the Function of Graphic Language in Poster Design
doi:10.21311/001.39.9.30 On the Function of Graphic Language in Poster Design Hong Zhao Anhui Institute of Information Engineering, Wuhu Anhui, 241000, China Abstract Graphic language in this paper refers
An Improved SIFT-Based Copy-Move Forgery Detection Method Using T-Linkage and Multi-Scale Analysis
Journal of Information Hiding and Multimedia Signal Processing c 2016 ISSN 2073-4212 Ubiquitous International Volume 7, Number 2, March 2016 An Improved SIFT-Based Copy-Move Forgery Detection Method Using
Copy-Move Forgery Detection Scheme using SURF Algorithm
Copy-Move Forgery Detection Scheme using SURF Algorithm Ezhilvallarasi V. 1, Gayathri A. 2 and Dharani Devi P. 3 1 Student, Dept of ECE, IFET College of Engineering, Villupuram 2 Student, Dept of ECE,
A REVIEW BLOCK BASED COPY MOVE FORGERY DETECTION TECHNIQUES
Available Online at www.ijcsmc.com International Journal of Computer Science and Mobile Computing A Monthly Journal of Computer Science and Information Technology ISSN 2320 088X IMPACT FACTOR: 6.017 IJCSMC,
ScienceDirect. Pixel based Image Forensic Technique for copy-move forgery detection using Auto Color Correlogram.
Available online at www.sciencedirect.com ScienceDirect Procedia Computer Science 79 (2016 ) 383 390 7th International Conference on Communication, Computing and Virtualization 2016 Pixel based Image Forensic
COPY-MOVE FORGERY DETECTION USING DYADIC WAVELET TRANSFORM. College of Computer and Information Sciences, Prince Norah Bint Abdul Rahman University
2011 Eighth International Conference Computer Graphics, Imaging and Visualization COPY-MOVE FORGERY DETECTION USING DYADIC WAVELET TRANSFORM Najah Muhammad 1, Muhammad Hussain 2, Ghulam Muhammad 2, and
Motion illusion, rotating snakes
Motion illusion, rotating snakes Local features: main components 1) Detection: Find a set of distinctive key points. 2) Description: Extract feature descriptor around each interest point as vector. x 1
Combining cellular automata and local binary patterns for copy-move forgery detection. Dijana Tralic, Sonja Grgic, Xianfang Sun & Paul L.
Combining cellular automata and local binary patterns for copy-move forgery detection Dijana Tralic, Sonja Grgic, Xianfang Sun Paul L. Rosin Multimedia Tools and Applications An International Journal ISSN
Image Copy Move Forgery Detection using Block Representing Method
Image Copy Move Forgery Detection using Block Representing Method Rohini.A.Maind, Alka Khade, D.K.Chitre Abstract- As one of the most successful applications of image analysis and understanding, digital
Keywords Digital Image Forgery, Forgery Detection, Transform Domain, Phase Correlation, Noise Variation
Volume 5, Issue 5, May 2015 ISSN: 2277 128X International Journal of Advanced Research in Computer Science and Software Engineering Research Paper Available online at: www.ijarcsse.com Copy-Move Image
Digital Image Forensics in Multimedia Security: A Review
Digital Image Forensics in Multimedia Security: A Review Vivek Singh Computer Science & Engineering Department Jaypee University of engineering and technology, Raghogarh, guna, india Neelesh Kumar Jain
Advanced Digital Image Forgery Detection by Using SIFT
RESEARCH ARTICLE OPEN ACCESS Advanced Digital Image Forgery Detection by Using SIFT Priyanka G. Gomase, Nisha R. Wankhade Department of Information Technology, Yeshwantrao Chavan College of Engineering
[Programming Assignment] (1)
![[Programming Assignment] (1)](/thumbs/90/104460171.jpg "[Programming Assignment] (1)")
http://crcv.ucf.edu/people/faculty/bagci/ [Programming Assignment] (1) Computer Vision Dr. Ulas Bagci (Fall) 2015 University of Central Florida (UCF) Coding Standard and General Requirements Code for all
With ever-increasing growth of electronic
Journal of Advances in Computer Engineering and Technology, 3(2) 2017 Parallelization of Rich Models for Steganalysis of Digital Images using a CUDA-based Approach Mahmoud Kazemi 1, Meysam Mirzaee 2, Reza
Adaptive Learning of an Accurate Skin-Color Model
Adaptive Learning of an Accurate Skin-Color Model Q. Zhu K.T. Cheng C. T. Wu Y. L. Wu Electrical & Computer Engineering University of California, Santa Barbara Presented by: H.T Wang Outline Generic Skin
Computer Vision. Exercise 3 Panorama Stitching 09/12/2013. Compute Vision : Exercise 3 Panorama Stitching
Computer Vision Exercise 3 Panorama Stitching 09/12/2013 Compute Vision : Exercise 3 Panorama Stitching The task Compute Vision : Exercise 3 Panorama Stitching 09/12/2013 2 Pipeline Compute Vision : Exercise
Selective Search for Object Recognition
Selective Search for Object Recognition Uijlings et al. Schuyler Smith Overview Introduction Object Recognition Selective Search Similarity Metrics Results Object Recognition Kitten Goal: Problem: Where
Extracting Rankings for Spatial Keyword Queries from GPS Data
Extracting Rankings for Spatial Keyword Queries from GPS Data Ilkcan Keles Christian S. Jensen Simonas Saltenis Aalborg University Outline Introduction Motivation Problem Definition Proposed Method Overview
Detecting Multiple Copies of Copy-Move Forgery Based on SURF
ISSN (Online) : 2319-8753 ISSN (Print) : 2347-6710 International Journal of Innovative Research in Science, Engineering and Technology Volume 3, Secial Issue 3, March 2014 2014 International Conference
Quasi-thematic Features Detection & Tracking. Future Rover Long-Distance Autonomous Navigation
Quasi-thematic Feature Detection And Tracking For Future Rover Long-Distance Autonomous Navigation Authors: Affan Shaukat, Conrad Spiteri, Yang Gao, Said Al-Milli, and Abhinav Bajpai Surrey Space Centre,
Anushree U. Tembe 1, Supriya S. Thombre 2 ABSTRACT I. INTRODUCTION. Department of Computer Science & Engineering, YCCE, Nagpur, Maharashtra, India
ABSTRACT 2017 IJSRSET Volume 3 Issue 2 Print ISSN: 2395-1990 Online ISSN : 2394-4099 Themed Section: Engineering and Technology Copy-Paste Forgery Detection in Digital Image Forensic Anushree U. Tembe
Dual System for Copy-move Forgery Detection using Block-based LBP-HF and FWHT Features
Engineering Letters, 26:1, EL_26_1_20 Dual System for Copy-move Forgery Detection using Block-based LBP-HF and FWHT Features Badal Soni, Member, IAENG, Pradip K. Das and Dalton Meitei Thounaojam, Member,
Evaluating Classifiers
Evaluating Classifiers Charles Elkan elkan@cs.ucsd.edu January 18, 2011 In a real-world application of supervised learning, we have a training set of examples with labels, and a test set of examples with
Improved LBP and K-Nearest Neighbors Algorithm
Image-Splicing Forgery Detection Based On Improved LBP and K-Nearest Neighbors Algorithm Fahime Hakimi, Department of Electrical and Computer engineering. Zanjan branch, Islamic Azad University. Zanjan,
Nearest Neighbor 3D Segmentation with Context Features
Paper 10574-21 Session 4: Machine Learning, 3:30 PM - 5:30 PM, Salon B Nearest Neighbor 3D Segmentation with Context Features Evelin Hristova, Heinrich Schulz, Tom Brosch, Mattias P. Heinrich, Hannes Nickisch
BLIND MEASUREMENT OF BLOCKING ARTIFACTS IN IMAGES Zhou Wang, Alan C. Bovik, and Brian L. Evans. (
BLIND MEASUREMENT OF BLOCKING ARTIFACTS IN IMAGES Zhou Wang, Alan C. Bovik, and Brian L. Evans Laboratory for Image and Video Engineering, The University of Texas at Austin (Email: zwang@ece.utexas.edu)
Final Review. Image Processing CSE 166 Lecture 18
Final Review Image Processing CSE 166 Lecture 18 Topics covered Basis vectors Matrix based transforms Wavelet transform Image compression Image watermarking Morphological image processing Segmentation
Copy Move Forgery Detection through Graph Neighborhood Degree
Copy Move Forgery Detection through Graph Neighborhood Degree Prabhash Kumar Singh 1, Biswapati Jana 2, Sharmistha Halder (Jana) 3 1 Department of Computer Science, Vidyasagar University, Midnapore, WB,
Copy Move Forgery Detection Using Key-Points Structure
Copy Move Forgery Detection Using Key-Points Structure A Thesis Submitted in Partial Fulfillment of the Requirements for the Degree of Master of Science in Cyber Security by Vinod Parihar 14/MS/030 Under
Learning and Inferring Depth from Monocular Images. Jiyan Pan April 1, 2009
Learning and Inferring Depth from Monocular Images Jiyan Pan April 1, 2009 Traditional ways of inferring depth Binocular disparity Structure from motion Defocus Given a single monocular image, how to infer
Accurate 3D Face and Body Modeling from a Single Fixed Kinect
Accurate 3D Face and Body Modeling from a Single Fixed Kinect Ruizhe Wang*, Matthias Hernandez*, Jongmoo Choi, Gérard Medioni Computer Vision Lab, IRIS University of Southern California Abstract In this
Structured Light II. Thanks to Ronen Gvili, Szymon Rusinkiewicz and Maks Ovsjanikov
Structured Light II Johannes Köhler Johannes.koehler@dfki.de Thanks to Ronen Gvili, Szymon Rusinkiewicz and Maks Ovsjanikov Introduction Previous lecture: Structured Light I Active Scanning Camera/emitter
Idea. Found boundaries between regions (edges) Didn t return the actual region
Region Segmentation Idea Edge detection Found boundaries between regions (edges) Didn t return the actual region Segmentation Partition image into regions find regions based on similar pixel intensities,
Midterm Examination CS 534: Computational Photography
Midterm Examination CS 534: Computational Photography November 3, 2016 NAME: Problem Score Max Score 1 6 2 8 3 9 4 12 5 4 6 13 7 7 8 6 9 9 10 6 11 14 12 6 Total 100 1 of 8 1. [6] (a) [3] What camera setting(s)
Overview. Videos are everywhere. But can take up large amounts of resources. Exploit redundancy to reduce file size
Overview Videos are everywhere But can take up large amounts of resources Disk space Memory Network bandwidth Exploit redundancy to reduce file size Spatial Temporal General lossless compression Huffman
MapReduce Design Patterns
MapReduce Design Patterns MapReduce Restrictions Any algorithm that needs to be implemented using MapReduce must be expressed in terms of a small number of rigidly defined components that must fit together
Raster Data. James Frew ESM 263 Winter
Raster Data 1 Vector Data Review discrete objects geometry = points by themselves connected lines closed polygons attributes linked to feature ID explicit location every point has coordinates 2 Fields
Chapter 6 Solutions S-3
6 Solutions Chapter 6 Solutions S-3 6.1 There is no single right answer for this question. The purpose is to get students to think about parallelism present in their daily lives. The answer should have
Reduced Time Complexity for Detection of Copy-Move Forgery Using Discrete Wavelet Transform
Reduced Time Complexity for of Copy-Move Forgery Using Discrete Wavelet Transform Saiqa Khan Computer Engineering Dept., M.H Saboo Siddik College Of Engg., Mumbai, India Arun Kulkarni Information Technology
3D Computer Vision. Structured Light II. Prof. Didier Stricker. Kaiserlautern University.
3D Computer Vision Structured Light II Prof. Didier Stricker Kaiserlautern University http://ags.cs.uni-kl.de/ DFKI Deutsches Forschungszentrum für Künstliche Intelligenz http://av.dfki.de 1 Introduction
Data parallel algorithms 1
Data parallel algorithms (Guy Steele): The data-parallel programming style is an approach to organizing programs suitable for execution on massively parallel computers. In this lecture, we will characterize
Detection of Region Duplication in Digital Images: A Digital Forensic Approach Jatin Wadhwa (111CS0165) Talib Ahemad (111cs0511)
Detection of Region Duplication in Digital Images: A Digital Forensic Approach Jatin Wadhwa (111CS0165) Talib Ahemad (111cs0511) Department of Computer Science and Engineering National Institute of Technology
COVERAGE A NOVEL DATABASE FOR COPY-MOVE FORGERY DETECTION
COVERAGE A NOVEL DATABASE FOR COPY-MOVE FORGERY DETECTION Bihan Wen 1,2, Ye Zhu 3,4, Ramanathan Subramanian 1,5, Tian-Tsong Ng 4, Xuanjing Shen 3, Stefan Winkler 1 1 Advanced Digital Sciences Center, University
Solutions to Problem Set 1
CSCI-GA.3520-001 Honors Analysis of Algorithms Solutions to Problem Set 1 Problem 1 An O(n) algorithm that finds the kth integer in an array a = (a 1,..., a n ) of n distinct integers. Basic Idea Using
Image Processing Via Pixel Permutations
Image Processing Via Pixel Permutations Michael Elad The Computer Science Department The Technion Israel Institute of technology Haifa 32000, Israel Joint work with Idan Ram Israel Cohen The Electrical
Image Processing. CSCI 420 Computer Graphics Lecture 22
CSCI 42 Computer Graphics Lecture 22 Image Processing Blending Display Color Models Filters Dithering [Ch 7.13, 8.11-8.12] Jernej Barbic University of Southern California 1 Alpha Channel Frame buffer Simple
Image Processing. Alpha Channel. Blending. Image Compositing. Blending Errors. Blending in OpenGL
CSCI 42 Computer Graphics Lecture 22 Image Processing Blending Display Color Models Filters Dithering [Ch 6, 7] Jernej Barbic University of Southern California Alpha Channel Frame buffer Simple color model:
Short Run length Descriptor for Image Retrieval
CHAPTER -6 Short Run length Descriptor for Image Retrieval 6.1 Introduction In the recent years, growth of multimedia information from various sources has increased many folds. This has created the demand
Gradient-Based Differential Approach for Patient Motion Compensation in 2D/3D Overlay
Gradient-Based Differential Approach for Patient Motion Compensation in 2D/3D Overlay Jian Wang, Anja Borsdorf, Benno Heigl, Thomas Köhler, Joachim Hornegger Pattern Recognition Lab, Friedrich-Alexander-University
Cloud-Based Multimedia Content Protection System
Cloud-Based Multimedia Content Protection System Abstract Shivanand S Rumma Dept. of P.G. Studies Gulbarga University Kalaburagi Karnataka, India shivanand_sr@yahoo.co.in In day to day life so many multimedia
University of Cambridge Engineering Part IIB Module 4F12 - Computer Vision and Robotics Mobile Computer Vision
report University of Cambridge Engineering Part IIB Module 4F12 - Computer Vision and Robotics Mobile Computer Vision Web Server master database User Interface Images + labels image feature algorithm Extract
CS395T paper review. Indoor Segmentation and Support Inference from RGBD Images. Chao Jia Sep
CS395T paper review Indoor Segmentation and Support Inference from RGBD Images Chao Jia Sep 28 2012 Introduction What do we want -- Indoor scene parsing Segmentation and labeling Support relationships
A Review on Copy-Move Forgery Detection Techniques Based on DCT and DWT
Available Online at www.ijcsmc.com International Journal of Computer Science and Mobile Computing A Monthly Journal of Computer Science and Information Technology IJCSMC, Vol. 4, Issue. 3, March 2015,
Improving the Detection and Localization of Duplicated Regions in Copy-Move Image Forgery
Improving the Detection and Localization of Duplicated Regions in Copy-Move Image Forgery Maryam Jaberi, George Bebis Computer Science and Eng. Dept. University of Nevada, Reno Reno, USA (mjaberi,bebis)@cse.unr.edu
Texture Sensitive Image Inpainting after Object Morphing
Texture Sensitive Image Inpainting after Object Morphing Yin Chieh Liu and Yi-Leh Wu Department of Computer Science and Information Engineering National Taiwan University of Science and Technology, Taiwan
Optimizing Pixel Predictors for Steganalysis
Optimizing Pixel Predictors for Steganalysis Vojtěch Holub and Jessica Fridrich Dept. of Electrical and Computer Engineering SUNY Binghamton, New York IS&T / SPIE 2012, San Francisco, CA Steganography
CHAPTER 6 MODIFIED FUZZY TECHNIQUES BASED IMAGE SEGMENTATION
CHAPTER 6 MODIFIED FUZZY TECHNIQUES BASED IMAGE SEGMENTATION 6.1 INTRODUCTION Fuzzy logic based computational techniques are becoming increasingly important in the medical image analysis arena. The significant
7 Solutions. Solution 7.1. Solution 7.2
7 Solutions Solution 7.1 There is no single right answer for this question. The purpose is to get students to think about parallelism present in their daily lives. The answer should have at least 10 activities
Copy-move Forgery Detection in the Presence of Similar but Genuine Objects
Copy-move Forgery Detection in the Presence of Similar but Genuine Objects Ye Zhu 1, 2, Tian-Tsong Ng 2, Bihan Wen 3, Xuanjing Shen 1, Bin Li 4 1 College of Computer Science and Technology, Jilin University,
Texture. Frequency Descriptors. Frequency Descriptors. Frequency Descriptors. Frequency Descriptors. Frequency Descriptors
Texture The most fundamental question is: How can we measure texture, i.e., how can we quantitatively distinguish between different textures? Of course it is not enough to look at the intensity of individual
Generalized Tree-Based Wavelet Transform and Applications to Patch-Based Image Processing
Generalized Tree-Based Wavelet Transform and * Michael Elad The Computer Science Department The Technion Israel Institute of technology Haifa 32000, Israel *Joint work with A Seminar in the Hebrew University
The Analysis and Detection of Double JPEG2000 Compression Based on Statistical Characterization of DWT Coefficients
Available online at www.sciencedirect.com Energy Procedia 17 (2012 ) 623 629 2012 International Conference on Future Electrical Power and Energy Systems The Analysis and Detection of Double JPEG2000 Compression
AN ALGORITHM FOR BLIND RESTORATION OF BLURRED AND NOISY IMAGES
AN ALGORITHM FOR BLIND RESTORATION OF BLURRED AND NOISY IMAGES Nader Moayeri and Konstantinos Konstantinides Hewlett-Packard Laboratories 1501 Page Mill Road Palo Alto, CA 94304-1120 moayeri,konstant@hpl.hp.com
Algorithm for the Digital Forgery Catching Technique for Image Processing Application
Algorithm for the Digital Forgery Catching Technique for Image Processing Application Manish Jain 1, Vinod Rampure 2 ¹Department of Computer Science and Engineering, Modern Institute of Technology and
Gabor Filter HOG Based Copy Move Forgery Detection
IOSR Journal of Electronics and Communication Engineering (IOSR-JECE) e-issn: 2278-2834,p-ISSN: 2278-8735 PP 41-45 www.iosrjournals.org Gabor Filter HOG Based Copy Move Forgery Detection Monisha Mohan
Semantic Context Forests for Learning- Based Knee Cartilage Segmentation in 3D MR Images
Semantic Context Forests for Learning- Based Knee Cartilage Segmentation in 3D MR Images MICCAI 2013: Workshop on Medical Computer Vision Authors: Quan Wang, Dijia Wu, Le Lu, Meizhu Liu, Kim L. Boyer,
Analysis of Robustness of Digital Watermarking Techniques under Various Attacks
International Journal of Engineering Research and Development e-issn : 2278-067X, p-issn : 2278-800X, www.ijerd.com Volume 2, Issue 6 (August 2012), PP. 28-34 Analysis of Robustness of Digital Watermarking
Video Inter-frame Forgery Identification Based on Optical Flow Consistency
Sensors & Transducers 24 by IFSA Publishing, S. L. http://www.sensorsportal.com Video Inter-frame Forgery Identification Based on Optical Flow Consistency Qi Wang, Zhaohong Li, Zhenzhen Zhang, Qinglong
Using GPUs to compute the multilevel summation of electrostatic forces
Using GPUs to compute the multilevel summation of electrostatic forces David J. Hardy Theoretical and Computational Biophysics Group Beckman Institute for Advanced Science and Technology University of
DOI: /jos Tel/Fax: by Journal of Software. All rights reserved. , )
ISSN 1000-9825, CODEN RUXUEW E-mail: jos@iscasaccn Journal of Software, Vol17, No2, February 2006, pp315 324 http://wwwjosorgcn DOI: 101360/jos170315 Tel/Fax: +86-10-62562563 2006 by Journal of Software
CSE 486/586 Distributed Systems
CSE 486/586 Distributed Systems Mutual Exclusion Steve Ko Computer Sciences and Engineering University at Buffalo CSE 486/586 Recap: Consensus On a synchronous system There s an algorithm that works. On
Robust and accurate change detection under sudden illumination variations
Robust and accurate change detection under sudden illumination variations Luigi Di Stefano Federico Tombari Stefano Mattoccia Errico De Lisi Department of Electronics Computer Science and Systems (DEIS)
Forensics of High-Quality JPEG Images with Color Subsampling
MÜNSTER Forensics of High-Quality JPEG Images with Color Subsampling Matthias Carnein Pascal Schöttle Rainer Böhme 19th November 2015 Introduction uncompressed Q = 15 Q = 100 Block convergence analysis
Learning bottom-up visual processes using automatically generated ground truth data
Learning bottom-up visual processes using automatically generated ground truth data Kalle Åström, Yubin Kuang, Magnus Oskarsson, Lars Kopp an Martin Byröd Mathematical Imaging Group Center for Mathematical
Pipelining and Vector Processing
Chapter 8 Pipelining and Vector Processing 8 1 If the pipeline stages are heterogeneous, the slowest stage determines the flow rate of the entire pipeline. This leads to other stages idling. 8 2 Pipeline
A Survey on Face-Sketch Matching Techniques
A Survey on Face-Sketch Matching Techniques Reshma C Mohan 1, M. Jayamohan 2, Arya Raj S 3 1 Department of Computer Science, SBCEW 2 Department of Computer Science, College of Applied Science 3 Department
Topic 4 Image Segmentation
Topic 4 Image Segmentation What is Segmentation? Why? Segmentation important contributing factor to the success of an automated image analysis process What is Image Analysis: Processing images to derive
PASSIVE FORENSIC METHOD FOR DETECTING DUPLICATED REGIONS AFFECTED BY REFLECTION, ROTATION AND SCALING
17th European Signal Processing Conference (EUSIPCO 2009) Glasgow, Scotland, August 24-28, 2009 PASSIVE FORENSIC METHOD FOR DETECTING DUPLICATED REGIONS AFFECTED BY REFLECTION, ROTATION AND SCALING Sergio
Keywords: digital forensics, copy-move forgery, keypoint, feature extraction, reconstruction. GJCST-F Classification: I.4.0
Global Journal of Computer Science and Technology Graphics & Vision Volume 13 Issue 9 Version 1.0 Year 2013 Type: Double Blind Peer Reviewed International Research Journal Publisher: Global Journals Inc.
Evaluation and comparison of interest points/regions
Introduction Evaluation and comparison of interest points/regions Quantitative evaluation of interest point/region detectors points / regions at the same relative location and area Repeatability rate :
Keywords - DWT, Lifting Scheme, DWT Processor.
Lifting Based 2D DWT Processor for Image Compression A. F. Mulla, Dr.R. S. Patil aieshamulla@yahoo.com Abstract - Digital images play an important role both in daily life applications as well as in areas
Peripheral drift illusion
Peripheral drift illusion Does it work on other animals? Computer Vision Motion and Optical Flow Many slides adapted from J. Hays, S. Seitz, R. Szeliski, M. Pollefeys, K. Grauman and others Video A video
Digital Image Forgery Detection Based on GLCM and HOG Features
Digital Image Forgery Detection Based on GLCM and HOG Features Liya Baby 1, Ann Jose 2 Department of Electronics and Communication, Ilahia College of Engineering and Technology, Muvattupuzha, Ernakulam,
Available Online through
Available Online through www.ijptonline.com ISSN: 0975-766X CODEN: IJPTFI Research Article ANALYSIS OF CT LIVER IMAGES FOR TUMOUR DIAGNOSIS BASED ON CLUSTERING TECHNIQUE AND TEXTURE FEATURES M.Krithika
Does everyone have an override code?
Does everyone have an override code? Project 1 due Friday 9pm Review of Filtering Filtering in frequency domain Can be faster than filtering in spatial domain (for large filters) Can help understand effect
Literature Survey on Performance of Reversible Data Hiding Algorithm
Literature Survey on Performance of Reversible Data Hiding Algorithm Sona Ignacious PG Scholar Department of ECE, PET Engineering College, India Abstract-DATA hiding technique aims to embed some secret
Data Mining Techniques
Data Mining Techniques CS 6220 - Section 3 - Fall 2016 Lecture 16: Association Rules Jan-Willem van de Meent (credit: Yijun Zhao, Yi Wang, Tan et al., Leskovec et al.) Apriori: Summary All items Count
CS161 - Final Exam Computer Science Department, Stanford University August 16, 2008
CS161 - Final Exam Computer Science Department, Stanford University August 16, 2008 Name: Honor Code 1. The Honor Code is an undertaking of the students, individually and collectively: a) that they will