Association Rule Mining on Multi-Media Data Auto Annotation on Images Bhavika Patel Hau San Si Tou Juveria Kanodia Muhammad Ahmad.

Slides:



Advertisements
Similar presentations
Visit the ccScan Website Scan, Import, and Automatically File documents to the Cloud SCAN, IMPORT, AND AUTOMATICALLY FILE DOCUMENTS TO SALESFORCE ® Introduction.
Advertisements

Organisation Of Data (1) Database Theory
CHAPTER OBJECTIVE: NORMALIZATION THE SNOWFLAKE SCHEMA.
Database management system (DBMS)  a DBMS allows users and other software to store and retrieve data in a structured way  controls the organization,
Frequent Itemset Mining Methods. The Apriori algorithm Finding frequent itemsets using candidate generation Seminal algorithm proposed by R. Agrawal and.
How the edges of a line, paragraph, object, or table are positioned horizontally and vertically between the margins or on a page.
CoMMA Combined Multi-Relational Multi-media Associations By Juveria Kanodia Muhammad Aurangzeb.
Creating Accessible Presentations Training Guide.
Final Project of Information Retrieval and Extraction by d 吳蕙如.
Christoph F. Eick Questions and Topics Review Dec. 1, Give an example of a problem that might benefit from feature creation 2.Compute the Silhouette.
DATA MINING -ASSOCIATION RULES-
1 Discovering Unexpected Information from Your Competitor’s Web Sites Bing Liu, Yiming Ma, Philip S. Yu Héctor A. Villa Martínez.
Software Development, Programming, Testing & Implementation.
Database Design IST 7-10 Presented by Miss Egan and Miss Richards.
Accessible Word Document Training Microsoft Word 2010.
1.Learning the Terms Learning the TermsLearning the Terms 2.Accessing the Internet from a PC Accessing the Internet from a PCAccessing the Internet from.
Basic Data Mining Techniques
DETECTING NEAR-DUPLICATES FOR WEB CRAWLING Authors: Gurmeet Singh Manku, Arvind Jain, and Anish Das Sarma Presentation By: Fernando Arreola.
Chapter 16 The World Wide Web Chapter Goals ( ) Compare and contrast the Internet and the World Wide Web Describe general Web processing.
LSP 121 Week 1 Intro to Databases. Welcome to LSP 121 Quantitative Reasoning and Technological Literacy II Continuation of quantitative data concepts.
Multimedia Databases (MMDB)
Copyright © 2007, Oracle. All rights reserved. Managing Concurrent Requests.
To enhance learning, service, and research through an advanced information technology environment. Our Mission:To enhance learning, service,and research.
McGraw-Hill Technology Education © 2004 by the McGraw-Hill Companies, Inc. All rights reserved. Office Access 2003 Lab 3 Analyzing Data and Creating Reports.
Planning a website by Katie Hardaker There are lots of things to think about when deciding about creating a website…
ITCS 6162 Project Action Rules Implementation
Data Mining Algorithms for Large-Scale Distributed Systems Presenter: Ran Wolff Joint work with Assaf Schuster 2003.
IR Homework #2 By J. H. Wang Mar. 31, Programming Exercise #2: Query Processing and Searching Goal: to search relevant documents for a given query.
Copyright © 2010 – MICS 2010, Curt Hill Instructor Tools: Test Data Generation Curt Hill Valley City State University.
22 November Databases. Presentations Tega: news 1954 Prediction.
McGraw-Hill/Irwin The O’Leary Series © 2002 The McGraw-Hill Companies, Inc. All rights reserved. Microsoft Access 2002 Lab 3 Analyzing Tables and Creating.
6 th Annual Focus Users’ Conference 6 th Annual Focus Users’ Conference Import Testing Data Presented by: Adrian Ruiz Presented by: Adrian Ruiz.
GROUP 4 BHUTAN CHINA SRI LANKA PHILIPPINES. COMMON PROBLEMS PROPOSALS 1.Budget There is no budget specified for agricultural statistical programs. Omission.
Database Management Systems (DBMS)
Introduction of Geoprocessing Lecture 9. Geoprocessing  Geoprocessing is any GIS operation used to manipulate data. A typical geoprocessing operation.
Web Design and Development. World Wide Web  World Wide Web (WWW or W3), collection of globally distributed text and multimedia documents and files 
Introduction to KE EMu Unit objectives: Introduction to Windows Use the keyboard and mouse Use the desktop Open, move and resize a.
Chapter 11 Enhancing an Online Form and Using Macros Microsoft Word 2013.
Session 1 Module 1: Introduction to Data Integrity
Introduction to KE EMu Unit objectives: Introduction to Windows Use the keyboard and mouse Use the desktop Open, move and resize a.
Our MP3 Search Engine Crawler –Searching for Artist Name –Searching for Song Title Website Difficulties Looking Back.
Write a function rule for a graph EXAMPLE 3 Write a rule for the function represented by the graph. Identify the domain and the range of the function.
Description and exemplification use of a Data Dictionary. A data dictionary is a catalogue of all data items in a system. The data dictionary stores details.
CSCI 6962: Server-side Design and Programming Shopping Carts and Databases.
Apriori Algorithm and the World Wide Web Roger G. Doss CIS 734.
THE EYESWEB PLATFORM - GDE The EyesWeb XMI multimodal platform GDE 5 March 2015.
Software. Because databases can get very big, it is important to decide exactly what is going to be stored in each field. Fields can be text, number,
Principles in the Evolutionary Design of Digital Circuits J. F. Miller, D. Job, and V. K. Vassilev Genetic Programming and Evolvable Machines.
Improvement of Apriori Algorithm in Log mining Junghee Jaeho Information and Communications University,
ACCESS LESSON 1 DATABASE BASICS VOCABULARY. BACKSTAGE VIEW A menu of options and commands that allows you to access various screens to perform common.
IR Homework #2 By J. H. Wang Apr. 13, Programming Exercise #2: Query Processing and Searching Goal: to search for relevant documents Input: a query.
Course Contents Overview: Database basics Lesson 1: Benefits of using a database Lesson 2: Table that data Lesson 3: Analyzing, viewing, and reporting.
Works of Art How to access INTERPOL’s Works of Art database via https.
1 CAA 2009 Cross Cal 9, Jesus College, Cambridge, UK, March 2009 Caveats, Versions, Quality and Documentation Specification Chris Perry.
DEVRY CIS 336 W EEK 7 G ROUP P ROJECT T ASK 5 Check this A+ tutorial guideline at
Algorithms and Problem Solving
GO! with Microsoft Office 2016
Microsoft Office Access 2010 Lab 2
<Dissertations>
Data Mining Jim King.
GO! with Microsoft Access 2016
Software Word Processors.
Databases Software This icon indicates the slide contains activities created in Flash. These activities are not editable. For more detailed instructions,
Access/SQL Server Eliminate Duplicates with SELECT DISTINCT
Algorithms and Problem Solving
Chapter 16 The World Wide Web.
5.00 Apply procedures to organize content by using Dreamweaver. (22%)
Presentation transcript:

Association Rule Mining on Multi-Media Data Auto Annotation on Images Bhavika Patel Hau San Si Tou Juveria Kanodia Muhammad Ahmad

Auto Annotation on Images This project is on performing Association Rule Mining on Multi-relational, Multimedia Data, particularly pictures and text. Corpus: a group of 798 pictures of different kinds such as art, landscape … with descriptions Generate association rules on image data (the RGBY values), and on text data separately. Propose an algorithm to link these two different domains together. Goal: return words that will describe a given unknown picture

Offline Processing Collect 789 pictures (.jpg,.bmp) with picture descriptions Picture descriptions are saved in a file (picDescription.txt) with the format: picture description Extract keywords from the picture descriptions. Run through KeywordExtractor program to remove stop words and duplicate keywords. (keywordList.dat) Format: kewyrod1 keyword2 keyword3 Run through Apriori implementation to generate association rules Each picture is saved with the name of its unique ID. Run the pictures through a program to extract features (R, G, B, Y, orientation, intensity) values Format: R G B Y I Run the generated feature table through alterfeature program to append a unique identify for each values, as well as changing the values to relative percentage. Run through Apriori implementation to generate association rules

Multi-Arm Program Read in the 9 feature values extracted from a given image Look for all association rules in the file containing the rules on image data, with these 9 feature values as the body. Check in the feature table to find out all the pictures that have these feature values Obtain the keywords associated with each picture identified Search for all association rules in the file containing the rules on text data, with any of these keywords Output all the keywords as descriptive/related words for the given image

Association Rules on Text RulesImpliesBodySupport %Confidence % RAY<- CHANDRA2.90%87.00% CHANDRA<- RAY3.10%80.00% PAINTING<- PAINT2.50%80.00% GUIDE<- VE2.80%90.90% ARTIST<- VE2.80%90.90% PAINTING<- VE2.80%95.50% PAINTING<- COLOURS4.30%82.40% PAINTING<- GUIDE6.10%95.90% PAINTING<- ARTIST8.10%83.10% RAY<- CHANDRA IMAGE2.10%88.20% ARTIST<- VE GUIDE2.50%95.00% GUIDE<- VE ARTIST2.50%95.00% PAINTING<- VE GUIDE2.50%100.00% GUIDE<- VE PAINTING2.60%95.20% PAINTING<- VE ARTIST2.50%100.00% ARTIST<- VE PAINTING2.60%95.20% GUIDE<- FACE PAINTING2.00%81.20% ARTIST<- FACE PAINTING2.00%81.20% PAINTING<- COLOUR ARTIST2.00%93.80% ARTIST<- COLOURS GUIDE2.80%86.40% PAINTING<- COLOURS GUIDE2.80%100.00% PAINTING<- COLOURS ARTIST3.10%96.00%

Association Rules on Text RulesImpliesBodySupport %Confidence % ARTIST<- COLOURS PAINTING3.50%85.70% ARTIST<- TOP GUIDE2.30%88.90% GUIDE<- TOP ARTIST2.30%88.90% PAINTING<- TOP GUIDE2.30%100.00% GUIDE<- TOP PAINTING2.60%85.70% PAINTING<- TOP ARTIST2.30%100.00% ARTIST<- TOP PAINTING2.60%85.70% PAINTING<- WORK ARTIST2.30%83.30% PAINTING<- GUIDE ARTIST4.90%100.00% ARTIST<- GUIDE PAINTING5.90%83.00% PAINTING<- VE GUIDE ARTIST2.40%100.00% ARTIST<- VE GUIDE PAINTING2.50%95.00% GUIDE<- VE ARTIST PAINTING2.50%95.00% PAINTING<- COLOURS GUIDE ARTIST2.40%100.00% ARTIST<- COLOURS GUIDE PAINTING2.80%86.40% PAINTING<- TOP GUIDE ARTIST2.00%100.00% ARTIST<- TOP GUIDE PAINTING2.30%88.90% GUIDE<- TOP ARTIST PAINTING2.30%88.90%

Association Rules on Image Data RulesImpliesBodySupport %Confidence % 1D135<- 0B 1D02.20%82.40% 1D90<- 0B 1D02.20%94.10% 1D45<- 0B 1D02.20%88.20% 1I<- 0B 1D02.20%100.00% 1D90<- 0B 1D %85.70% 1D135<- 0B 1D902.70%85.70% 1D45<- 0B 1D %85.70% 1D135<- 0B 1D452.80%81.80% 1I<- 0B 1D %90.50% 1D45<- 0B 1D902.70%90.50% 1D90<- 0B 1D452.80%86.40% 1I<- 0B 1D902.70%100.00% 1D90<- 0B 1I3.00%87.50% 1I<- 0B 1D452.80%86.40% 1I<- 1R 1D02.40%84.20% 1D45<- 1R 1D %81.80% 1D45<- 1R 1D902.40%84.20% 1I<- 1R 1D902.40%84.20% 1D90<- 1Y 1D %80.00% 1D90<- 1D0 1D %86.90% 1D135<- 1D0 1D %86.90% 1D0<- 1D135 1D %81.60% 1D45<- 1D0 1D %83.20%

Association Rules on Image Data RulesImpliesBodySupport %Confidence % 1D135<- 1D0 1D %90.80% 1I<- 1D0 1D %90.70% 1D135<- 1D0 1I14.70%83.60% 1D0<- 1D135 1I14.80%82.90% 1D45<- 1D0 1D %82.20% 1D90<- 1D0 1D %89.80% 1D0<- 1D90 1D %80.00% 1I<- 1D0 1D %88.80% 1D90<- 1D0 1I14.70%81.90% 1I<- 1D0 1D %91.80% 1D45<- 1D135 1D %86.00% 1D90<- 1D135 1D %83.10% 1D135<- 1D90 1D %89.10% 1I<- 1D135 1D %86.00% 1D90<- 1D135 1I14.80%83.80% 1D135<- 1D90 1I15.20%81.70% 1I<- 1D135 1D %83.90% 1D45<- 1D135 1I14.80%84.60% 1D135<- 1D45 1I15.20%82.50% 1I<- 1D90 1D %89.10% 1D45<- 1D90 1I15.20%81.70% 1D90<- 1D45 1I15.20%81.70% 1D135<- 1D0 1D %90.80%

# of text association rules generated from different combination of min supp & conf

# of image association rules generated from different combination of min supp & conf

Single pass rebuild Specify common key Rebuild the tables based on the common key Use Apriori EXAMPLE: Table 1: purchase(customer,item,amount) item(customer,item_id) Table 2 purchase_total(customer,items) Query: Customers who buy a lot of stuff what do they usually but? purchase_total(X,items) return item(X,item_id)

Conclusion So we have a partial solution multimedia ARM problem, however there many things that can be done further, to improve upon it. Need to find a way to restrict the number of keywords that we get. Need to find an easier method than the present lookup method, as too many files are involved. Need for an efficient data structure to do the above point. Alternative Schemes

The End Please visit our project’s website at to find detailed information.

Questions?