Visual Information Systems visual information retrieval.

Slides:



Advertisements
Similar presentations
Pseudo-Relevance Feedback For Multimedia Retrieval By Rong Yan, Alexander G. and Rong Jin Mwangi S. Kariuki
Advertisements

Image Retrieval: Current Techniques, Promising Directions, and Open Issues Yong Rui, Thomas Huang and Shih-Fu Chang Published in the Journal of Visual.
Chapter 5: Introduction to Information Retrieval
Multimedia Database Systems
Query Languages. Information Retrieval Concerned with the: Representation of Storage of Organization of, and Access to Information items.
ARNOLD SMEULDERS MARCEL WORRING SIMONE SANTINI AMARNATH GUPTA RAMESH JAIN PRESENTERS FATIH CAKIR MELIHCAN TURK Content-Based Image Retrieval at the End.
1 Content-Based Retrieval (CBR) -in multimedia systems Presented by: Chao Cai Date: March 28, 2006 C SC 561.
Web- and Multimedia-based Information Systems. Assessment Presentation Programming Assignment.
Information Retrieval Review
T.Sharon - A.Frank 1 Internet Resources Discovery (IRD) Classic Information Retrieval (IR)
ISP 433/533 Week 2 IR Models.
Basic IR: Queries Query is statement of user’s information need. Index is designed to map queries to likely to be relevant documents. Query type, content,
Image Search Presented by: Samantha Mahindrakar Diti Gandhi.
T.Sharon - A.Frank 1 Internet Resources Discovery (IRD) IR Queries.
Information Retrieval Concerned with the: Representation of Storage of Organization of, and Access to Information items.
Presentation Outline  Project Aims  Introduction of Digital Video Library  Introduction of Our Work  Considerations and Approach  Design and Implementation.
INFO 624 Week 3 Retrieval System Evaluation
Visual Information Retrieval Chapter 1 Introduction Alberto Del Bimbo Dipartimento di Sistemi e Informatica Universita di Firenze Firenze, Italy.
Vector Space Model CS 652 Information Extraction and Integration.
Presented by Zeehasham Rasheed
Information retrieval Finding relevant data using irrelevant keys Example: database of photographic images sorted by number, date. DBMS: Well structured.
Computer comunication B Information retrieval Repetition Retrieval models Wildcards Web information retrieval Digital libraries.
CS292 Computational Vision and Language Visual Features - Colour and Texture.
Ranking by Odds Ratio A Probability Model Approach let be a Boolean random variable: document d is relevant to query q otherwise Consider document d as.
Visual Information System visual information retrieval (VIR) Lilian Tang.
Recuperação de Informação. IR: representation, storage, organization of, and access to information items Emphasis is on the retrieval of information (not.
Text Mining: Finding Nuggets in Mountains of Textual Data Jochen Dijrre, Peter Gerstl, Roland Seiffert Presented by Drew DeHaas.
Chapter 5: Information Retrieval and Web Search
SIEVE—Search Images Effectively through Visual Elimination Ying Liu, Dengsheng Zhang and Guojun Lu Gippsland School of Info Tech,
Modeling (Chap. 2) Modern Information Retrieval Spring 2000.
«Tag-based Social Interest Discovery» Proceedings of the 17th International World Wide Web Conference (WWW2008) Xin Li, Lei Guo, Yihong Zhao Yahoo! Inc.,
Multimedia Databases (MMDB)
Chapter 7 Web Content Mining Xxxxxx. Introduction Web-content mining techniques are used to discover useful information from content on the web – textual.
Multimedia Information Retrieval
Content-Based Image Retrieval
Basics of Information Retrieval Lillian N. Cassel Some of these slides are taken or adapted from Source:
Modern Information Retrieval Computer engineering department Fall 2005.
Thanks to Bill Arms, Marti Hearst Documents. Last time Size of information –Continues to grow IR an old field, goes back to the ‘40s IR iterative process.
Data Mining Chapter 1 Introduction -- Basic Data Mining Tasks -- Related Concepts -- Data Mining Techniques.
Information Retrieval Models - 1 Boolean. Introduction IR systems usually adopt index terms to process queries Index terms:  A keyword or group of selected.
Xiaoying Gao Computer Science Victoria University of Wellington Intelligent Agents COMP 423.
Chapter 6: Information Retrieval and Web Search
Introduction to Digital Libraries hussein suleman uct cs honours 2003.
Web- and Multimedia-based Information Systems Lecture 2.
Introduction to Information Retrieval Aj. Khuanlux MitsophonsiriCS.426 INFORMATION RETRIEVAL.
WEB 2.0 PATTERNS Carolina Marin. Content  Introduction  The Participation-Collaboration Pattern  The Collaborative Tagging Pattern.
1 Information Retrieval LECTURE 1 : Introduction.
Information Retrieval CSE 8337 Spring 2007 Introduction/Overview Some Material for these slides obtained from: Modern Information Retrieval by Ricardo.
Recuperação de Informação Cap. 01: Introdução 21 de Fevereiro de 1999 Berthier Ribeiro-Neto.
Information Retrieval
Search Engine using Web Mining COMS E Web Enhanced Information Mgmt Prof. Gail Kaiser Presented By: Rupal Shah (UNI: rrs2146)
Digital Video Library Network Supervisor: Prof. Michael Lyu Student: Ma Chak Kei, Jacky.
Colour and Texture. Extract 3-D information Using Vision Extract 3-D information for performing certain tasks such as manipulation, navigation, and recognition.
Chapter. 3: Retrieval Evaluation 1/2/2016Dr. Almetwally Mostafa 1.
A Genetic Algorithm-Based Approach to Content-Based Image Retrieval Bo-Yen Wang( 王博彥 )
Visual Information Systems Lilian Tang. Description of Content – image processing Primitive image properties Primitive image properties Through image.
Xiaoying Gao Computer Science Victoria University of Wellington COMP307 NLP 4 Information Retrieval.
Visual Information Retrieval
Modern Information Retrieval
Introduction Multimedia initial focus
Datamining : Refers to extracting or mining knowledge from large amounts of data Applications : Market Analysis Fraud Detection Customer Retention Production.
Multimedia Information Retrieval
Information Retrieval
Multimedia Information Retrieval
CSE 635 Multimedia Information Retrieval
Ying Dai Faculty of software and information science,
Ying Dai Faculty of software and information science,
Search Engine Architecture
Recuperação de Informação
Presentation transcript:

Visual Information Systems visual information retrieval

Computational steps for visual retrieval systems 1. image processing (colour, texture etc) 1. human perception and computer perception (computer vision) 2. Sensory gap 2. features definition, extraction 1. low-level and high-level 2. content, semantics, and concepts 3. small scale and large scale 4. knowledge domain, knowledge elicitation, knowledge discovery and management 3. Similarity measure, learn from feedback, and dynamic indexing 4. Databases and system architecture 5. Evaluation, not just system performance, but insights for the future

VIR and Traditional Database? A traditional SQL database has as its basic element data items in a relation: A traditional SQL database has as its basic element data items in a relation: select name from employee, project where employee.deptnumber = “25” AND project.number = “100” project.number = “100” databases exploit known structures and relations databases exploit known structures and relations DBMS retrieval is not probabilistic DBMS retrieval is not probabilistic How different from the WWW? How different from the WWW? And from traditional IR? And from traditional IR?

VIR and Traditional IR systems? IR systems can be considered the precursors to VIR IR systems can be considered the precursors to VIR The basic unit of a IR system is a document and the focus is on textual retrieval The basic unit of a IR system is a document and the focus is on textual retrieval exact matching - Boolean, text pattern searching exact matching - Boolean, text pattern searching inexact matching - probabilistic, vector space, clustering inexact matching - probabilistic, vector space, clustering Visual information has its own characteristics that traditional IR is incapable to handle Visual information has its own characteristics that traditional IR is incapable to handle

Recap IR: What’s IR Motivation Motivation the larger the holdings of the archive, the more useful it is the larger the holdings of the archive, the more useful it is however, it is harder to find what you want however, it is harder to find what you want IR is all about finding what you want when what you want is buried in a mass of what you don’t want IR is all about finding what you want when what you want is buried in a mass of what you don’t want

from Lesk,

Simple IR Model User QueryResults Pre- Processing Post- Processing Searching Storage Collection & Processing Stuff Boolean Vector Stemming Thesaurus Signature Ranking Clustering Weighting Boolean Vector Feedback Flat Files Inverted Files Signature Files PAT Trees Stemming Stoplist

Recap IR: Precision and Recall Precision Precision “ratio of the number of relevant documents retrieved over the total number of documents retrieved” “ratio of the number of relevant documents retrieved over the total number of documents retrieved” how much extra stuff did you get? how much extra stuff did you get? Recall Recall “ratio of relevant documents retrieved for a given query over the number of relevant documents for that query in the database” “ratio of relevant documents retrieved for a given query over the number of relevant documents for that query in the database” how much did you miss? how much did you miss?

Recap IR: Text Retrieval  The most popular approach is to extract keywords from each text document in the database to form the indices of the document.  The keyword extraction process may be divided into three major steps, stopwords removal, stemming and word weighting  stopwords removal: “a”, “an” and “the”.  stemming: removes the suffix and prefix of each word.  word weighting: estimates the weighting of each word.

Recap IR: Text Retrieval - Query will go through the same procedure - Similarity matching: calculated from the pre- computed weighting of the matched keywords. - All documents with a similarity value higher than a certain threshold will be considered as relevant documents and returned to the user. - These relevant document may be ranked according to the similarity values when presenting to the user. (Most web search engines do this.)

Visual Information Retrieval- keyword It is difficult for text to capture the perceptual saliency of some visual features It is difficult for text to capture the perceptual saliency of some visual features Pictures cannot speak, but they are stronger than words. Pictures cannot speak, but they are stronger than words. Text is not well suited for modelling perceptual similarity. Text is not well suited for modelling perceptual similarity. Subjective. Subjective. “What is needed in these cases is the use of a more concrete description of visual content, one more closely related to human perception, and a new way of interaction that fully exploits human perception capabilities.”

Textual content : free text search image content : image features, shapes, color, textures, spatial relationships Video content : motions, image features, scene composition, video semantics, audio, etc. Visual information Retrieval – content-based approach

Content-Based Image Retrieval As happens during the maturation process of many a discipline, after early successes in a few applications, research is now concentrating on deeper problems, challenging the hard problems at the crossroads of the discipline from which it was born (Arnold 2000) As happens during the maturation process of many a discipline, after early successes in a few applications, research is now concentrating on deeper problems, challenging the hard problems at the crossroads of the discipline from which it was born (Arnold 2000) computer vision, databases, and information retrieval. computer vision, databases, and information retrieval. Deeper analysis is needed and semantics is more desirable – make use of domain knowledge Deeper analysis is needed and semantics is more desirable – make use of domain knowledge

Domain and Variability A narrow domain has a limited and predictable variability in all relevant aspects of its appearance. A narrow domain has a limited and predictable variability in all relevant aspects of its appearance. Semantics is well-defined, and unique. Semantics is well-defined, and unique. A broad domain has an unlimited and unpredictable variability in its appearance even for the same semantic meaning A broad domain has an unlimited and unpredictable variability in its appearance even for the same semantic meaning Semantics is more ambiguous, and partial Semantics is more ambiguous, and partial Need more contextual information Need more contextual information

Domain and Variability The notions of broad and narrow domains are helpful in characterizing patterns of use, in selecting features, and in designing systems. The notions of broad and narrow domains are helpful in characterizing patterns of use, in selecting features, and in designing systems. For narrow, specialized image domains, the gap between features and their semantic interpretation is usually smaller, so domain- specific models may help. For narrow, specialized image domains, the gap between features and their semantic interpretation is usually smaller, so domain- specific models may help. In a broad image domain, the gap between the feature description and the semantic interpretation is generally wide In a broad image domain, the gap between the feature description and the semantic interpretation is generally wide the required number of computational variables would be enormous. the required number of computational variables would be enormous. Research issues raised…… Research issues raised……

Research issues How to handle variability? How to handle variability? Multiple processors and fusion process? Multiple processors and fusion process? Inference engines? Inference engines?

Domain Knowledge Laws of syntactic (literal) equality and similarity define the relation between image pixels or image features regardless of its physical or perceptual causes. Laws describing the human perception of equality and similarity Physical laws describing equality and difference of images under differences in sensing and object surface properties. The physics of illumination, surface reflection, and image formation have a general effect on images. Geometric and topological rules describe equality and differences of patterns in space. Category-based rules encode the characteristics common to class z of the space of all notions Z. Finally, man-made customs or man-related patterns introduce rules of culture-based equality and difference.

Difficulties in VIS The sensory gap and the semantic gap The sensory gap and the semantic gap

The Semantic Gap A linguistic description is almost always contextual, whereas an image may live by itself. A linguistic description is almost always contextual, whereas an image may live by itself. associate higher level semantics to data-driven observables associate higher level semantics to data-driven observables labelling is seldom complete, context sensitive, and, in any case, there is a significant fraction of requests whose semantics can't be captured by labelling alone. Both methods will cover the semantic gap only in isolated cases. labelling is seldom complete, context sensitive, and, in any case, there is a significant fraction of requests whose semantics can't be captured by labelling alone. Both methods will cover the semantic gap only in isolated cases. This works well in narrow domain like I-Browse, though it is not the perfect solution This works well in narrow domain like I-Browse, though it is not the perfect solution

From broad domain to narrow domain The challenge for image search engines on a broad domain is to tailor the engine to the narrow domain the user has in mind via specification, examples, and interaction. The challenge for image search engines on a broad domain is to tailor the engine to the narrow domain the user has in mind via specification, examples, and interaction.

Bridging the Gap New challenges in content-based retrieval are the huge amount of objects to search among, the incomplete query specification, the incomplete image description, and the variability of sensing conditions and object states. New challenges in content-based retrieval are the huge amount of objects to search among, the incomplete query specification, the incomplete image description, and the variability of sensing conditions and object states. The aim of content-based retrieval systems must be to provide maximum support in bridging the semantic gap between the simplicity of available visual features and the richness of the user semantics. The aim of content-based retrieval systems must be to provide maximum support in bridging the semantic gap between the simplicity of available visual features and the richness of the user semantics. The broader the domain, the more browsing or search by association can be the right solution. The narrower the domain, the more likely an application of domain knowledge will succeed The broader the domain, the more browsing or search by association can be the right solution. The narrower the domain, the more likely an application of domain knowledge will succeed

Video Retrieval There are three major processes to prepare a video for retrieval, video segmentation, index extraction and keyframe extraction. There are three major processes to prepare a video for retrieval, video segmentation, index extraction and keyframe extraction. From another perspective, video retrieval could be considered simpler than image retrieval since video reveals its objects more easily as the points corresponding to one object move together. From another perspective, video retrieval could be considered simpler than image retrieval since video reveals its objects more easily as the points corresponding to one object move together. In addition, video has a linear timeline, as important to the narrative structure of video as it is in text. In addition, video has a linear timeline, as important to the narrative structure of video as it is in text.

Video Retrieval V ideo segmentation divides the video into a number of segments by detecting the camera breaks. V ideo segmentation divides the video into a number of segments by detecting the camera breaks. Index extraction: manual indexing, image analysis and computer vision and object recognition Index extraction: manual indexing, image analysis and computer vision and object recognition Keyframe extraction is to select representative image frames from each video segment to represent the segment. These keyframes may be used for browsing and for presentation. Keyframe extraction is to select representative image frames from each video segment to represent the segment. These keyframes may be used for browsing and for presentation.