Detecting False Captioning Using Common Sense Reasoning James Byrd.

Slides:



Advertisements
Similar presentations
Jeanette Patterson Regional Coordinator – North East CAS Master Teacher CTL Technology – Kings Priory School
Advertisements

Segmentation In The Field Medicine Advanced Image Processing course By: Ibrahim Jubran Presented To: Prof. Hagit Hel-Or.
Artifact and Textured region Detection - Vishal Bangard.
Presenting your thesis as a series of papers – to do or not to do.... Dr Sato Juniper Manager, Graduate Research and Scholarships.
CIS 678 Artificial Intelligence problems deduction, reasoning knowledge representation planning learning natural language processing motion and manipulation.
ADVISE: Advanced Digital Video Information Segmentation Engine
An Authentication Service Against Dishonest Users in Mobile Ad Hoc Networks Edith Ngai, Michael R. Lyu, and Roland T. Chin IEEE Aerospace Conference, Big.
Evaluating the Quality of Image Synthesis and Analysis Techniques Matthew O. Ward Computer Science Department Worcester Polytechnic Institute.
Object Class Recognition using Images of Abstract Regions Yi Li, Jeff A. Bilmes, and Linda G. Shapiro Department of Computer Science and Engineering Department.
6 Systems Analysis and Design in a Changing World, Fourth Edition.
Digital Forensics Dr. Bhavani Thuraisingham The University of Texas at Dallas Lecture #12 Intelligent Digital Forensics September 30, 2009.
Time Series Data Analysis - II
Chapter 6: The Traditional Approach to Requirements
Image segmentation by clustering in the color space CIS581 Final Project Student: Qifang Xu Advisor: Dr. Longin Jan Latecki.
Database Systems: Design, Implementation, and Management Ninth Edition
Chapter 1 Database Systems. Good decisions require good information derived from raw facts Data is managed most efficiently when stored in a database.
Copyright © Cengage Learning. All rights reserved.
CHAPTER 12 ADVANCED INTELLIGENT SYSTEMS © 2005 Prentice Hall, Decision Support Systems and Intelligent Systems, 7th Edition, Turban, Aronson, and Liang.
The Art of Scientific Writing. Goals of Scientific Writing  Making a clear presentation of a complex scientific problem/accomplishment  Addressing a.
NOTE: To change the image on this slide, select the picture and delete it. Then click the Pictures icon in the placeholder to insert your own image. PROJECT.
Anomaly detection with Bayesian networks Website: John Sandiford.
E PRESENTATION : delivering your information product to the user
SVCL Automatic detection of object based Region-of-Interest for image compression Sunhyoung Han.
Exercise #5: Supervised Classification. Step 1. Delineating Training Sites and Generating Signatures An individual training site is delineated as an “area.
Imagine Schools’ Science Fair
Chapter 12 Information Systems. 2 Managing Information Information system Software that helps the user organize and analyze data Electronic spreadsheets.
CSCE 5013 Computer Vision Fall 2011 Prof. John Gauch
Bayesian networks Classification, segmentation, time series prediction and more. Website: Twitter:
1 By: Nour Hilal. Microsoft Access is a database software where data is stored in one or more Tables. A Database is a group of related Tables. Access.
11 A Hybrid Phish Detection Approach by Identity Discovery and Keywords Retrieval Reporter: 林佳宜 /10/17.
Summary Marie Yarbrough. Introduction History of Image Forgery Method Segmentation Classification Common-Sense Reasoning Conclusion.
Advances in the Use of Neurophysiologycally-based Fusion for Visualization and Pattern Recognition of Medical Imagery M. Aguilar, J. R. New and E. Hasanbelliu.
Automatic Image Annotation by Using Concept-Sensitive Salient Objects for Image Content Representation Jianping Fan, Yuli Gao, Hangzai Luo, Guangyou Xu.
ECE738 Advanced Image Processing Face Detection IEEE Trans. PAMI, July 1997.
Map of the Great Divide Basin, Wyoming, created using a neural network and used to find likely fossil beds See:
Computer Graphics and Image Processing (CIS-601).
MedIX – Summer 07 Lucia Dettori (room 745)
AL-MAAREFA COLLEGE FOR SCIENCE AND TECHNOLOGY INFO 232: DATABASE SYSTEMS CHAPTER 1 DATABASE SYSTEMS Instructor Ms. Arwa Binsaleh.
A Mobile Terminal Based Trajectory Preserving Strategy for Continuous Querying LBS Users Yunxia Feng, Peng Liu, Jianhui Zhang May , 2012 Hangzhou,
Advances in digital image compression techniques Guojun Lu, Computer Communications, Vol. 16, No. 4, Apr, 1993, pp
Digital Forensics Dr. Bhavani Thuraisingham The University of Texas at Dallas Lecture 23 Intelligent Digital Forensics October 22, 2007.
Multiplication of Real Numbers Section 2.5. Multiplying Rules 1) If the numbers have the same signs then the answer is positive. (-7) (-4) = 28 2) If.
1Ellen L. Walker Category Recognition Associating information extracted from images with categories (classes) of objects Requires prior knowledge about.
October Andrew C. Gallagher, Jiebo Luo, Wei Hao Improved Blue Sky Detection Using Polynomial Model Fit Andrew C. Gallagher, Jiebo Luo, Wei Hao Presented.
Selected Responses How deep does the question dig?????
Support Vector Machines and Gene Function Prediction Brown et al PNAS. CS 466 Saurabh Sinha.
Rectangles and Multiplication Here is a rectangle with sides 3 and 7. The total number of squares can be found by multiplying 3 and
6 Systems Analysis and Design in a Changing World, Fourth Edition.
DATA MINING TECHNIQUES (DECISION TREES ) Presented by: Shweta Ghate MIT College OF Engineering.
Grid-Based Genetic Algorithm Approach to Colour Image Segmentation Marco Gallotta Keri Woods Supervised by Audrey Mbogho.
Content Based Coding of Face Images
Object-based Classification
Session 7: Face Detection (cont.)
Map of the Great Divide Basin, Wyoming, created using a neural network and used to find likely fossil beds See:
: Chapter 9: Image Segmentation
Web Data Extraction Based on Partial Tree Alignment
University College London (UCL), UK
Project Implementation for ITCS4122
Picture with Caption layout
Title Layout Subtitle.
Supervised Classification
Introduction to Pattern Recognition
3.1.1 Introduction to Machine Learning
University College London (UCL), UK
PowerPoint Information
YOUR TITLE HERE Your name here.
Picture with Caption layout
Supervised machine learning: creating a model
DREAMWEAVER FIREWORKS PHOTOSHOP FLASH.
Presentation transcript:

Detecting False Captioning Using Common Sense Reasoning James Byrd

Picture editing is popular Medical, Journalism, Science all at risk how do we detect what is real from what is not? We shall introduce a nearly flawless mathematical technique to tell the true from the false Abstract

Pictures are a compelling way to communicate information Why modify? o To make the picture tell a different story o “Yellow Journalism” Intro

4 ways a. Deletion of Details - deleting details b. Insertion of Details - inserting additional details c. Photomontage - combining multiple images d. False Captioning - misrepresenting image content Photo Manipulation

Photomontage False Captioning This Paper’s Focus

1.Segmentation 2.Classification 3.Common Sense Reasoning Steps for detection

1.Segment the image into regions 2.Make an “importance map” to compare across images in a given corpus Segmentation

Perhaps the most important part Segment based color scheme compare segments among images Classification

2 approaches o resolve local classification ambiguities within images; we will query a knowledge base to resolve proper relations o reason across a larger corpa of images to find unique or missing elements during an investigation Common Sense Reasoning

Image segmentation Importance Map Calculating ROIs Classification Reasoning Methods

Segment the image o mean-shift image segmentation to decompose an image into homogeneous regions o choosing parameter values is often difficult o therefore we adds tons of colors and do many segmetns Image Segmentation

to truly understand the importance of an image requires a thorough understanding of what the image contains and what the viewer needs recognize objects (faces) and regions are important Importance Map

2 step process o Identify Candidate ROI  minimal image that identifies key important parts of the image o Grow the ROI  combine the ROI by using a clustering algorithm recursively Calculating ROI

Supervised Classification o Training Sites - predetermined objects of interest in an image o Software uses these to create a “signature analysis” Unsupervised Classification o Takes a large number of ROI and divides them into classes based on grouping in them o becoming increasingly popular Classification

Resolve local ambiguities within an image Answer questions the program has o i.e. water versus sky Then the software determines if the anomalies are consistent across images or show signs of tampering o More pictures to examine are better for consistency Reasoning

methods are limited by the performance of the components of image segmentation and important object identification Conclusion