advertisement

Tas Talk

33 %
67 %
advertisement
Information about Tas Talk
Education

Published on February 27, 2008

Author: Danior

Source: authorstream.com

advertisement

Multimedia Signal Processing & Content-Based Image Retrieval:  Multimedia Signal Processing & Content-Based Image Retrieval Anastasios N. Venetsanopoulos University of Toronto Contact: anv@dsp.toronto.edu http://www.dsp.toronto.edu http://www.ece.toronto.edu OUTLINE:  OUTLINE INTRODUCTION MULTIMEDIA APPLICATIONS IMPACT OF MULTIMEDIA CONTENT-BASED IMAGE RETRIEVAL (CBIR) MPEG-7 RESEARCH ISSUES INTRODUCTION-1:  INTRODUCTION-1 WHAT IS MULTIMEDIA? WHAT IS MULTIMEDIA PROCESSING? GOALS OF MULTIMEDIA PROCESSING INTRODUCTION-2:  INTRODUCTION-2 DIFFICULT TO DEFINE GENERALLY CONSISTS OF: MULTIMEDIA DATA INTERACTION SET MULTIMEDIA DATA: MULTI-SOURCE, MULTI-TYPE, MULTI-FORMAT INTERACTION SET: WITHOUT INTERACTIONS BETWEEN MULTIMEDIA COMPONENTS, MULTIMEDIA IS MERELY A COLLECTION OF DATA WHAT IS MULTIMEDIA? INTRODUCTION-3:  INTRODUCTION-3 REAL OBJECTS VIRTUAL OBJECTS REAL SPEECH Mutimedia Data Components COMPLEX INTERACTIONS BETWEEN COMPONENTS IN THE SCENE MAKE VIRTUAL COMPONENTS SEEM MORE REALISTIC EXAMPLE: AUGMENTED REALITY CONFERENCE INTRODUCTION-4:  INTRODUCTION-4 MULTIMEDIA PROCESSING APPLY SIGNAL PROCESSING TOOLS TO MULTIMEDIA DATA TO ENABLE: REPRESENTATION INTERPRETATION ENCODING DECODING WHAT IS MULTIMEDIA PROCESSING? INTRODUCTION-5:  INTRODUCTION-5 EFFECTIVE & EFFICIENT ACCESS MANIPULATION EXCHANGE STORAGE OF MULTIMEDIA CONTENT GOALS OF MULTIMEDIA PROCESSING CONTINUING…:  CONTINUING… INTRODUCTION MULTIMEDIA APPLICATIONS IMPACT OF MULTIMEDIA CONTENT-BASED IMAGE RETRIEVAL (CBIR) MPEG-7 RESEARCH ISSUES MULTIMEDIA APPLICATIONS-1:  MULTIMEDIA APPLICATIONS-1 GPS NAVIGATION SCALABLE VIDEO STREAMING MULTIMEDIA APPLICATIONS-2:  MULTIMEDIA APPLICATIONS-2 E-COMMERCE TELEPRESENCE CELLULAR MULTIMEDIA APPLICATIONS-3:  MULTIMEDIA APPLICATIONS-3 MORE SPECIFIC EXAMPLES MULTIMEDIA APPLICATION GOALS IMPROVE INTERPERSONAL COMMUNICATION PROMOTE UNDERSTANDING OF IDEAS ALLOW INTERACTIVITY WITH MEDIA INCREASE ACCESSIBILITY TO DATA MPEG-4, 7, 21 JPEG-2000 MP3 & PERCEPTUAL CODING MULTIMEDIA STORAGE VIDEO-ON-DEMAND DIGITAL CINEMA AUTHENTICATION GOING ON…:  GOING ON… INTRODUCTION MULTIMEDIA APPLICATIONS IMPACT OF MULTIMEDIA CONTENT-BASED IMAGE RETRIEVAL (CBIR) MPEG-7 RESEARCH ISSUES IMPACT OF MULTIMEDIA-4:  IMPACT OF MULTIMEDIA-4 WORLD INTERNET USAGE (July 23, 2005) IMPACT OF MULTIMEDIA-2:  IMPACT OF MULTIMEDIA-2 USERS (S0CIETY) DEMAND INCREASED MOBILITY EASE-OF-USE PERSONAL CUSTOMIZATION DEVICE FLEXIBILITY HIGH LEVEL OF COLLABORATION WITH PEERS DEVICES MUTATE AND BECOME MULTI-FUNCTIONAL, NOT SPECIALIZED EFFORTLESSLY PORTABLE, NOT STATIONARY UBIQUITOUSLY NETWORKED, NOT ISOLATED IMPACT OF MULTIMEDIA-3:  MULTI-FUNCTIONAL DEVICES MUST BROWSE INTERNET ENTERTAIN BE EASY-TO-USE CUSTOMIZATION PERSONALIZATION (THEMES, PREFERENCES) NETWORKED CAPABLE OF CONNECTING TO MANY DIFFERENT NETWORKS (INTERNET, P.O.T.S., LAN, CELLULAR, BLUETOOTH, 802.11b, GPS) FACILITATE MANY TYPES OF WORKFLOW MANAGE USER’S TIME IMPACT OF MULTIMEDIA-3 IMPACT OF MULTIMEDIA-4:  CONVERGENCE TECHNOLOGIES WHICH WERE TOTALLY UNRELATED 10 YEARS AGO ARE NOW UNIFIED UNDER THE CONCEPT OF MULTIMEDIA IMPACT OF MULTIMEDIA-4 IMPACT OF MULTIMEDIA-5:  EXAMPLE: CELLULAR PHONES IMPACT OF MULTIMEDIA-5 PRIMARY CONSUMER USE: WIRELESS TELEPHONY CONVERGED USES PERSONAL ORGANIZER INTERNET BROWSER/EMAIL ENTERTAINMENT (MP3, RADIO) VIDEO/STILL CAMERA PAGER/MESSAGING (SMS) IMPACT OF MULTIMEDIA-6:  IMPACT OF MULTIMEDIA-6 DEMANDS FUNCTIONALITY CONSUMPTION OF MANY MEDIA TYPES CONNECTIVITY PORTABILITY, ETC. RESULT HIGHLY COMPLEX DEVICES PUSH TOWARDS DENSE CIRCUITRY MULTIMEDIA DEVICES BECOME UBIQUITOUS DEVICES GENERATE MULTIMEDIA DATA (INCLUDING IMAGES, VIDEO, AUDIO) OVERALL MOVING ALONG…:  MOVING ALONG… INTRODUCTION MULTIMEDIA APPLICATIONS IMPACT OF MULTIMEDIA CONTENT-BASED IMAGE RETRIEVAL (CBIR) MPEG-7 RESEARCH ISSUES CBIR OVERVIEW:  MOTIVATION & GOALS WHAT IS CBIR? CONTRIBUTING DISCIPLINES APPLICATION SCENARIOS SOME SPECIFIC ISSUES TYPICAL CAPABILITIES CBIR OVERVIEW CBIR MEDIA FLOODING:  EFFECTS & PROCESSING RESULT: DIGITAL MEDIA FLOOD HOW DO WE COPE, TRACK, ORGANIZE IT ALL? POLAROID FILED FOR BANKRUPTCY HAS DIGITAL KILLED FILM? IF SO, WHY? CHEAP & DENSE STORAGE CBIR MEDIA FLOODING EXAMPLE: GENERAL PHOTOGRAPHY SNAPSHOT PREVIEWS EASY SHARING VIA INTERNET MEMORY REUSABLE PRINTER TECHNOLOGY CBIR MOTIVATION:  DEVICE FUNCTION CONVERGENCE DATA RAPIDLY GENERATED BY MANY DEVICES INTERNET ACTS AS GLOBAL TRANSPORT DATA CONSUMED BY DEVICES ON DEMAND MULTIMEDIA DATA NEEDS TO BE EFFICIENTLY STORED INDEXED ACCURATELY EASILY RETRIEVED CBIR MOTIVATION CBIR IS…:  CONTENT BASED IMAGE RETRIEVAL PART OF MULTIMEDIA INDEXING IMAGES (2-D SPACE-DEPENDENT SIGNALS) VIDEO (TIME-VARYING IMAGE SET) AUDIO (1-D TIME-DEPENDENT SIGNALS) TEXT (e.g. BOOK INDEX, SEARCH ENGINES) COMPUTER BASED HIGHLY AUTOMATED DIFFICULT TO DO PROPERLY CBIR IS… CBIR SIMPLE EXAMPLE:  FOR A GIVEN QUERY… EXAMPLE IMAGE ROUGH SKETCH EXPLICIT DESCRIPTION CRITERIA …RETURN ALL ‘SIMILAR’ IMAGES CBIR SIMPLE EXAMPLE RETRIEVAL SYSTEM CBIR QUERY TYPES:  CBIR QUERY TYPES SKETCH EXAMPLE COLOR SHAPE TEXTURE MORE COMPLEX TYPES EXIST YET ABOVE ARE MOST FUNDAMENTAL & MOST REGULARLY USED CBIR CONTRIBUTORS:  COMBINES HIGH-TECH ELEMENTS MULTIMEDIA/SIGNAL/IMAGE PROCESSING COMPUTER VISION/PATTERN RECOGNITION COMPUTER SCIENCES (I.E. HUMAN-COMPUTER INTERACTION) AND MORE TRADITIONAL CONCEPTS PSYCHOLOGY/HUMAN PERCEPTION INFORMATION SCIENCES (I.E. LIBRARY) CBIR CONTRIBUTORS CBIR SCENARIOS:  a a a GOVERNMENT (E.G. MUGSHOTS) ENTERTAINMENT (FILM, TV) DESIGN/VISUAL ARTS INDUSTRY (LOGO MANAGEMENT) SOME CBIR APPLICATION AREAS CBIR SCENARIOS MEDICAL IMAGING ART/CULTURAL HERITAGE CBIR VERSUS TEXT:  IMPORTANT QUESTION ARISES: “WHY NOT SIMPLY INDEX USING TEXT?” (YAHOO! HAS HAD SOME SUCCESS WITH THIS) INTUITIVE, YET USING TEXT IS SIMPLE BUT SIMPLISTIC TIME CONSUMING – CAN’T AUTOMATE HIGHLY SUBJECTIVE & USER-DEPENDENT SUSCEPTIBLE TO TRANSLATION PROBLEMS CBIR VERSUS TEXT CBIR BASIC STRUCTURE:  CBIR BASIC STRUCTURE FEATURE EXTRACTION I N D E X SIMILARITY CALCULATION GENERATION OF RESULTS USER INTERFACE SIMILAR RESULTS QUERY FEATURE DESCRIPTIONS 3 BASIC FEATURES COLOR, TEXTURE, SHAPE MANY DESCRIPTORS MPEG-7 IS ISO STANDARD REALLY A DESIGN CHOICE SIMILARITY OPEN TO RESEARCH LITTLE PERCEPTUAL CONSIDERATION CBIR (DIS)SIMILARITY?:  ON WHAT BASIS ARE THEY SIMILAR? COLOR CONTENT? SHAPE CONTENT? HIGH LEVEL IDEAS (‘MASKS’, ‘GENDER’)? PERCEPTION IS ALWAYS AN ISSUE CONSIDER THREE IMAGES CBIR (DIS)SIMILARITY? SIMILARITY IS NOT SO SIMPLE CBIR SIMILARITY:  CBIR SIMILARITY DOMAIN [0,1] CAN BE CALCULATED MANY WAYS GENERALIZED MINKOWSKI CANBERRA PERCEPTUAL MEASURE CBIR TYPICAL ABILITIES:  EFFECTIVE QUERIES IN COLOR, TEXTURE, SHAPE SIMPLE HYBRID QUERIES DESCRIPTOR SUPERVECTORS WEIGHTED AVERAGE OF (DIS)SIMILARITIES RELEVANCE FEEDBACK USER PLACED IN LOOP GIVES BETTER RESULTS STATISTICAL APPROACHES APPLY/ADJUST FEATURE WEIGHTS TO RELEVANT/IRRELEVANT ELEMENTS CBIR TYPICAL ABILITIES CBIR SUMMARY:  CBIR SUMMARY BORN FROM MULTIMEDIA FLOOD TEXT TOO SIMPLE AND LABORIOUS SYSTEMS WORK DECENTLY IN VITRO QUERY BY SHAPE, COLOR, TEXTURE, EXAMPLE SHORTCOMINGS NEED RELEVANCE FEEDBACK & PERCEPTUAL HYBRID QUERIES DIFFICULT TO CREATE SEMANTIC GAP NEEDS TO BE BRIDGED MPEG-7: IMPORTANT DEVELOPMENT GOING FORWARD…:  GOING FORWARD… INTRODUCTION MULTIMEDIA APPLICATIONS IMPACT OF MULTIMEDIA CONTENT-BASED IMAGE RETRIEVAL (CBIR) MPEG-7 RESEARCH ISSUES MPEG:  MPEG MOTION PICTURES EXPERT GROUP MPEG-1 MPEG-2 MPEG-4 MPEG-7: ISO/IEC 15938 MULTIMEDIA CONTENT DESCRIPTION INTERFACE MPEG-21 MPEG-1 & MPEG-2:  MPEG-1 & MPEG-2 MPEG-1 (c. 1992) BASIC VIDEO CODING USING DPCM & DCT TARGET: CD-BASED VIDEO & MULTIMEDIA USE I, B & P-FRAMES IN YUV SPACE MPEG-2 (c. 1994) SUPERSET OF MPEG-1 GOAL: DTV/DSS OR ATM TRANSPORT MINIMUM OF NTSC/PAL QUALITY MORE ERROR RESILIENT SCALABLE – GRACEFUL DEGRADATION MPEG-4 & MPEG-21:  MPEG-4 & MPEG-21 MPEG-4 (c. 1998) TOOLS TO AUTHOR MULTIMEDIA CONTENT TRAFFIC AWARE, ERROR RESILIENT OBJECT-BASED CODING VERY EFFICIENT FOR LOW BIT-RATES MPEG-21 (STARTED JUNE 2000) AN OPEN “MULTIMEDIA FRAMEWORK” IDEA ADDRESSES DIGITAL RIGHTS MANAGEMENT ENHANCED DELIVERY & ACCESS OF DATA FOR DEVICES ON HETEROGENEOUS NETWORKS MPEG-7 NEW PARADIGM:  MPEG-7 NEW PARADIGM UNLIKE MPEG-1, MPEG-2, & MPEG-4 DOESN’T REPRESENT CONTENT ITSELF MPEG-7 ONLY DESCRIBES CONTENT DIFFICULT CONCEPT FOR SOME TO GRASP APPLICABLE TO IMAGES VIDEO INDEPENDENT OF STORAGE ARCHITECTURE AUDIO & SPEECH TEXT TRANSPORT CODING MPEG-7 HOW IT DIFFERS:  MPEG-7 HOW IT DIFFERS MPEG-1 TAKES INPUT FRAMES AND REPRESENTS AS AN BINARY ENCODED VIDEO BITSTREAM MPEG-7 TAKES VIDEO FRAMES (SAY MPEG-1 FORMAT) AND DESCRIBES CONTENTS OF EACH FRAME. FRAME 1: COLOR CONTENT: 20% WHITE, 14% BLUE, SHAPES: BRIDGE, etc. FRAME 2: COLOR CONTENT: 20% WHITE, 15% BLUE, SHAPES: BRIDGE, etc. FRAME 3: COLOR CONTENT: 21% WHITE, 14% BLUE, SHAPES: BRIDGE, etc. MPEG-7 SCOPE:  MPEG-7 SCOPE MPEG-7 SCOPE FEATURE EXTRACTION ALGORITHM CODING SCHEME CONTENT DESCRIPTION OTHER ELEMENTS . . . MULTIMEDIA DATA MPEG-7 GOALS:  MPEG-7 GOALS DESCRIBE MULTIMEDIA CONTENT SET OF DESCRIPTORS (D) RELATIONS BETWEEN DESCRIPTORS SET OF DESCRIPTION SCHEMES (DS) LANGUAGE DEFINING D’s & DS’s DESCRIPTION DEFINITION LANGUAGE (DDL) BASED ON XML (eXtensible Markup Language) USED TO BUILD UP NEW D’s & DS’s ENCODING OF D’s FOR EFFICIENCY MPEG-7 SUMMARY-1:  MPEG-7 SUMMARY-1 STANDARDIZED DESCRIPTIONS APPLIES TO ALL DIGITAL MEDIA CBIR IS CASE FOR STILL IMAGES DOES NOT REPRESENT DATA ITSELF DESCRIBES WHAT DATA REPRESENTS SETS THE BAR FOR SYSTEMS MULTIMEDIA/IMAGE RETRIEVAL SYSTEMS NEED AT LEAST MPEG-7 CONFORMANCE MPEG-7 SUMMARY-2:  MPEG-7 SUMMARY-2 DOES NOT ADDRESS SIMILARITY RELEVANCE FEEDBACK FEATURE EXTRACTION HYBRID QUERY GENERATION ARCHIVE ORGANIZATION THE ABOVE ISSUES HAVE BEEN PURPOSEFULLY LEFT OPEN FOR INNOVATION FORGING AHEAD…:  FORGING AHEAD… INTRODUCTION MULTIMEDIA APPLICATIONS IMPACT OF MULTIMEDIA CONTENT-BASED IMAGE RETRIEVAL (CBIR) MPEG-7 RESEARCH ISSUES RESEARCH ISSUES:  SHORTCOMINGS OF CBIR SYSTEMS ONGOING RESEARCH RELEVANCE FEEDBACK HYBRID QUERY GENERATION DISTRIBUTED MULTIMEDIA INDEXING OPEN RESEARCH AVENUES RESEARCH ISSUES CBIR SHORTCOMINGS-1:  CBIR SHORTCOMINGS-1 COLOR USUALLY GLOBAL HIGH DIMENSIONALITY GAMMA NONLINEARITIES CAUSE PROBLEMS SHAPE COMPLICATED & DIFFICULT OCCLUSION ISSUES DURING EXTRACTION TEXTURE COMPLICATED & UNINTUITIVE USER-SYSTEM RIFT FOR QUERY CREATION CBIR SHORTCOMINGS-2:  CBIR SHORTCOMINGS-2 PERCEPTUAL ISSUES SUBTLE DIFFERENCES BETWEEN VIEWERS COLOR-BLIND USERS SIMILARITY MEASURES NEED TO BE TUNED TO DESCRIPTORS e.g. EUCLIDEAN DISTANCE NOT APPLICABLE IN NON-EUCLIDEAN DESCRIPTION SPACE RELEVANCE FEEDBACK PERFORMED AT GLOBAL (IMAGE) LEVEL NEED TO ADDRESS SPECIFIC IMAGE ELEMENTS ONGOING RESEARCH-2:  ONGOING RESEARCH-2 ITERATIVE QUERY REFINEMENT PLACE USER IN LOOP TO ITERATIVELY IMPROVE RETRIEVAL RATES HIGH-DIMENSIONAL SPACE NEEDS PRUNING EMPHASIZED FEATURE(S) MUST BE FOUND TYPICAL APPROACHES STATISTICAL METHODS FEATURE WEIGHTING RELEVANCE FEEDBACK ONGOING RESEARCH-2:  ONGOING RESEARCH-2 FEATURE SELECTIVE INTERFACE WHY CHOOSE IMAGES ON WHOLE? REQUIRES PROCESSING/STATS TO FIND GOOD FEATURES USER CAN EXPLICITLY INDICATE ELEMENTS OF IMAGE WHICH ARE GOOD: NO GUESSWORK RELEVANT COLOR RELEVANT SHAPE EXPLICIT FEATURES TO R.F. ENGINE RELEVANCE FEEDBACK ONGOING RESEARCH-3:  ONGOING RESEARCH-3 TYPICALLY USED APPROACHES BOOLEAN (AND, OR & NOT OPERATORS) EUCLIDEAN (MINKOWSKI W/ r=1) WEIGHTED AVERAGE (WA) i.e. SUPERVECTORS DISADVANTAGES EUCLIDEAN: FCN OF DESCRIPTORS – CHANGE DESCRIPTOR, DRASTICALLY ALTER MEASURE WA: INFLEXIBLE FOR HIGH LEVEL QUERIES, SUPERVECTORS IMPOSE CERTAIN STRUCTURE BOOLEAN: HARD LIMITED TO LOGIC FCNs ALL LACK PERCEPTUAL CONSIDERATIONS SIMILARITY AGGREGATION/HYBRID QUERIES ONGOING RESEARCH-4:  FUZZY AGGREGATION OF DECISIONS USE MEMBERSHIP FUNCTION TO ‘FUZZIFY’ DISTANCES & GENERATE A ‘FUZZY DECISION’ EXPONENTIAL MODELS HUMAN PERCEPTION ONGOING RESEARCH-4 SIMILARITY AGGREGATION/HYBRID QUERIES FUZZY MEMBERSHIP FUNCTION SIMILARITY DISTANCE d FUZZY DISTANCE DECISION m ONGOING RESEARCH-5:  INDEXES USUALLY CENTRALIZED ENTIRE SYSTEM FAILS IF COMPONENT FAILS NO GRACEFUL PERFORMANCE DEGRADATION HIGH DATA VOLUME = HIGH SYSTEM REQ’S DISTRIBUTED INDEXES SPREAD WORKLOAD OVER MANY SUBSYSTEMS INCREASE REDUNDANCY P2P SYSTEMS LACK CENTRALIZED ELEMENTS P2P SYSTEMS RESEMBLE SOCIAL NETWORKS ONGOING RESEARCH-5 DISTRIBUTED MULTIMEDIA INDEXING ONGOING RESEARCH-6:  SMALL WORLD INDEXING MODEL1 SOCIOLOGICAL PEER DESCRIPTIONS WE ARE NOT BLIND TO WHO OUR PEERS ARE PEOPLE KEEP MEMORY OF THEIR PEERS WE ARE NOT BLIND TO HOW OUR PEERS ARE WE REFER OTHERS TO OUR PEERS EXAMPLE ONGOING RESEARCH-6 DISTRIBUTED MULTIMEDIA INDEXING [1] P. Androutsos, D. Androutsos and A. N. Venetsanopoulos, “A distributed fault-tolerant MPEG-7 retrieval scheme based on small world theory”, Distributed Media Technologies and Applications Special Issue of IEEE Transactions on Multimedia, under review. ONGOING RESEARCH-7:  INDEX AND ARCHIVE BECOME ONE SWIM DATA STORED IN ARCHIVE OBJECTS EACH DATA OBJECT BEHAVES AS OWN AGENT AGENTS ARE EFFECTIVE IN HIGHLY NETWORKED ENVIRONMENTS (SWIM) RETRIEVALS AGENT BASED RETRIEVAL USE OF REFERRAL BASED TECHNIQUE SIMILAR TO ‘SIX DEGREES OF SEPARATION’ CURRENTLY PERFORMED WITH IMAGES ONGOING RESEARCH-7 DISTRIBUTED MULTIMEDIA INDEXING ONGOING RESEARCH-8:  ONGOING RESEARCH-8 DISTRIBUTED MULTIMEDIA INDEXING2 [2] P. Androutsos, D. Androutsos and A. N. Venetsanopoulos, “Graceful image retrieval performance degradation using small world distributed indexing”, International Conference on Image Processing ICIP2005, Genoa, Italy. RESEARCH AVENUES-1:  RESEARCH AVENUES-1 HYBRID QUERIES & AGGREGATION WHAT DO WEIGHTS MEAN? HOW TO CHOOSE? ALTERNATIVE AGGREGATIONS METHODS ADAPTIVE SCHEMES USING REL. FEEDBACK USER INTERFACE BRIDGE SEMANTIC GAP BETWEEN USER’S IDEA, AND ABILITY TO EXPRESS AS A QUERY ALTERNATIVE INTERFACES–ICONIC, SEMANTIC RESEARCH AVENUES-2:  RESEARCH AVENUES-2 PERCEPTUAL ISSUES EMPHASIS OF DOMINATING FEATURES FEATURE MASKING EMOTIONAL INDEXING/ ALL USERS DIFFERENT–CUSTOMIZED PROFILE ARCHIVE DEPENDENCE SYSTEMS USUALLY SPECIALIZED ADAPTIVE INDEXING – MOST APPROPRIATE SYSTEM USED BASED ON PRELIMINARY SURVEY OF CANDIDATE DATABASE RESEARCH AVENUES-3:  RESEARCH AVENUES-3 DISTRIBUTED INDEXING DISTRIBUTED INDEXES & RETRIEVAL INDEX SYNCHRONIZATION RESULTS ORGANIZATION & RANKING SWIM OVERHEAD ESTIMATION EXTENSION OF SWIM TO OTHER DATA TYPES INCORPORATE TEXT METHODS TEXT-INDEXING USING LIMITED VOCABULARY DON’T REJECT BUT USE INTELLIGENTLY EXTEND TO MPEG-21 & METADATA SUMMARY-1:  SUMMARY-1 MULTIMEDIA PROCESSING RESULTS FROM MULTIMEDIA EXPLOSION USERS DEMANDING MORE FROM DEVICES DEVICES ARE CONVERGING CONTENT BASED IMAGE RETRIEVAL NECESSARY TO TRACK VISUAL SEA OF DATA GOOD CAPABILITIES, BUT W/ SHORTCOMINGS PERCEPTUAL/SUBJECTIVE ISSUES RELEVANCE FEEDBACK DISTRIBUTED CONCEPTS BECOMING CRITICAL SUMMARY-2:  SUMMARY-2 MPEG-7 AIMED AT STANDARDIZING DESCRIPTIONS RADICALLY DIFFERENT THAN PREVIOUS MPEGs DDL IS AN EXTENSION OF XML SCHEMA APPLICABLE TO ALL MULTIMEDIA DATA ALWAYS MORE TO DO MPEG-7 HAS LEFT MANY ISSUES OPEN CBIR NEEDS TO ADDRESS USERS, PERCEPTION, HYBRID QUERIES, DISTRIBUTED SYSTEMS, ETC VIBRANT RESEARCH COMMUNITY THANK YOU:  THANK YOU IMPACT OF MULTIMEDIA:  HIGH FLEXIBILITY RESULTS IN RISE IN DATA GENERATION & STORAGE INCREASE IN BANDWIDTH NEEDS ONE TOOL DOING WORK OF MANY MANY TYPES OF NETWORKS CAUSE COMPLEX HARDWARE COMBINATIONS ONE DEVICE CONNECTING TO ALL NETWORKS SMALL, PORTABLE DEVICES MINIATURIZATED WITH HUGE CAPABILITIES ONE DEVICE REPLACES MANY IMPACT OF MULTIMEDIA CBIR WHO’S WHO:  CBIR WHO’S WHO MPEG-7 D, DS, & DDL:  DEFINED VIA DDL DEFINED IN MPEG-7 STANDARD MPEG-7 D, DS, & DDL DDL D D DS DS D D DS D BUILDING MORE Ds & DSs USING THE DDL MPEG-7 COMPONENTS:  MPEG-7 COMPONENTS SYSTEMS DDL VISUAL PRIMARY CONCERN FOR THIS PRESENTATION AUDIO MULTIMEDIA DESCRIPTION SCHEMES EXPERIMENTATION MODEL (XM) CONFORMANCE MPEG-7 VISUAL COMPONENT:  MPEG-7 VISUAL COMPONENT BASIC DESCRIPTORS GRID LAYOUT 2D/3D VIEW TIME SERIES SPATIAL 2D COORDS TEMPORAL INTERPOLATION COLOR DESCRIPTORS COLOR SPACE COLOR QUANTIZATION DOMINANT COLOR SCALABLE COLOR COLOR STRUCTURE COLOR LAYOUT GoF/GoP COLOR OTHER FACE RECOGNITION TEXTURE DESCRIPTORS EDGE HISTOGRAM HOMOGENEOUS TEXTURE TEXTURE BROWSING SHAPE DESCRIPTORS REGION-BASED CONTOUR-BASED 3D SHAPE MOTION DESCRIPTORS CAMERA MOTION MOTION TRAJECTORY PARAMETRIC MOTION MOTION ACTIVITY LOCALIZATION SPATIO-TEMPORAL REGION LOCATOR HIGHLIGHTED DESCRIPTORS USED BY UofT ONGOING RESEARCH:  FUZZY AGGREGATION OF DECISIONS AGGREGATE DECISIONS USING LOGIC USE COMPENSATIVE OPERATOR PARAMETER g CONTROLS DEGREE OF ANDNESS (max) & ORNESS (min) RESULT IS A SINGLE VALUE IN [0,1] INDICATING OVERALL IMAGE SIMILARITY ONGOING RESEARCH SIMILARITY AGGREGATION/HYBRID QUERIES

Add a comment

Related presentations

Related pages

TAS Talks | TAS - The Armidale School, TAS | TAS

TAS Talks TAS Talks is the weekly newsletter of The Armidale School and published in digital format every Wednesday.
Read more

TED: Ideas worth spreading

TED Talk: Fascinating research that proves where your money goes matters 9 great tips for public speaking Playlist: Advice on the ...
Read more

Tas Filippou (@Tas_Talk) | Twitter

@Tas_Talk your Twitter timeline was exactly how I expected it to be - full of reality show bs. You don't disappoint, Tas. 0 replies 0 retweets 0 likes. Reply.
Read more

CXOTALK | Leadership, Innovation, Disruption

Robert Tas. Senior Vice President and Chief Marketing Officer Pegasystems
Read more

Agentur | TAS Emotional Marketing GmbH

TAS ist eine Event- und Kommunikationsagentur im Ruhrgebiet. Schwerpunkte sind Live-Kommunikation, PR, Social Media, POS-Marketing, strategische ...
Read more

Paket 300: surfen und telefonieren supergünstig – Aldi Talk

Das ALDI TALK Paket 300 ist nach Ihrer Bestellung jederzeit über “Mein ALDI TALK”, die ALDI TALK App und unter der kostenlosen Konto-Hotline 1155 ab ...
Read more

TSP Talk - Thrift Savings Plan

TSP Thrift Savings Plan Talk - TSP Talk provides TSP fund allocation information and help for government employees and military personnel participating in ...
Read more

Registrieren – ALDI TALK

Registrieren Sie sich bei Aldi Talk online, über die Hotline oder per Post und schon kann es losgehen. Startseite ALDI Talk ALDI Homepage Kontakt.
Read more

Urlaub, Hotels, Ferienwohnung - Tannheimer Tal Tourismus

Offizielle Internetseite des Tannheimer Tal. 400 buchbare Angebote. Wellnesshotel, Wanderhotel, Hotel, Pension, Privatpension, Ferienwohnungen, Campingplatz
Read more