Presented by: Michal Nir, Saar Gross Supervisors: Nadav Golbandi, Oren Somekh Computer Science Department Industrial Project (234313) Tuesday, January.

Slides:



Advertisements
Similar presentations
1 Searching Internet of Sensors Junghoo (John) Cho (UCLA CS) Mark Hansen (UCLA Stat) John Heidemann (USC/ISI)
Advertisements

Master/Slave Architecture Pattern Source: Pattern-Oriented Software Architecture, Vol. 1, Buschmann, et al.
EEC 688/788 Secure and Dependable Computing Lecture 12 Wenbing Zhao Department of Electrical and Computer Engineering Cleveland State University
“ The Anatomy of a Large-Scale Hypertextual Web Search Engine ” Presented by Ahmed Khaled Al-Shantout ICS
Software: Systems and Application Software
Multi-criteria infrastructure for location-based applications Shortly known as: Localization Platform Ronen Abraham Ido Cohen Yuval Efrati Tomer Sole'
The Museum Project The Museum Project Yoav Gvili & Asaf Stein Supervisor : Alexander Arlievsky.
Optimized Data Migration within a System of Linked Medical Research Databases By Jared Christopherson U. of Connecticut.
INFO 624 Week 3 Retrieval System Evaluation
Academic Advisor: Prof. Ronen Brafman Team Members: Ran Isenberg Mirit Markovich Noa Aharon Alon Furman.
1 CS 430 / INFO 430 Information Retrieval Lecture 24 Usability 2.
Distance Education & Document Delivery Basic goals for our Discussion Explain use of Document Delivery for Distance Education Library Services at Portland.
Apache : Installation, Configuration, Basic Security Presented by, Sandeep K Thopucherela, ECE Department.
Generic Simulator for Users' Movements and Behavior in Collaborative Systems.
3D Object Retrieval Client-Server Project
Secau – Security Research Centre Edith Cowan University Geotagging – Where Cyberspace comes to your space Craig Valli & Peter Hannay secau – Security Research.
Personalized Ontologies for Web Search and Caching Susan Gauch Information and Telecommunications Technology Center Electrical Engineering and Computer.
ANDROID PROGRAMMING MODULE 1 – GETTING STARTED
CrowdSearch: Exploiting Crowds for Accurate Real-Time Image Search on Mobile Phones Original work by Yan, Kumar & Ganesan Presented by Tim Calloway.
Frank Rowe John Gaetano Chuck Figiel.  CryptoViz implements and visualizes the Data Encryption Standard (DES) algorithm.  DES was used by the government.
 What I hate about you things people often do that hurt their Web site’s chances with search engines.
Application for Internet Radio Directory 19/06/2012 Industrial Project (234313) Kickoff Meeting Supervisors : Oren Somekh, Nadav Golbandi Students : Moran.
Students: Nadia Goshmir, Yulia Koretsky Supervisor: Shai Rozenrauch Industrial Project Advanced Tool for Automatic Testing Final Presentation.
Scenario testing Tor Stålhane. Scenario testing – 1 There are two types of scenario testing. Type 1 – scenarios used as to define input/output sequences.
Students: Ilya Paskhover, Itay Gal Supervisors: Oleg Rokhlenko, Nadav Golbandi.
What’s New in Kinetic Task 3.0 Ben Christenson 3 About Me  Ben Christenson  Employee at Kinetic Data for 13 years and a member of the Product Development.
Finding Wormholes with Flickr Geotags Maarten Clements Marcel Reinders Arjen de Vries Pavel Serdyukov December 3 rd, 2009 GIS.
MOVIE QUOTES SEARCH ENGINE Students: Meytal Bialik Zvi Cahana Supervisors: Hayim Makabee Oren Somekh Technion – Israel Institute Of Technology Computer.
6/1/2001 Supplementing Aleph Reports Using The Crystal Reports Web Component Server Presented by Bob Gerrity Head.
Naming and Directories. Recall from the last time… File system components Disk management organizes disk blocks into files. Many disk blocks management.
Server-side Scripting Powering the webs favourite services.
Mobile search engine for a smart phone / navigation system can be used to search and compare hundreds of stores and their products in seconds. © 2001 –
1 CMPT 275 High Level Design Phase Architecture. Janice Regan, Objectives of Design  The design phase takes the results of the requirements analysis.
COMP 410 & Sky.NET May 2 nd, What is COMP 410? Forming an independent company The customer The planning Learning teamwork.
Advanced PI Calculation Engine Makes Complex PI Calculations Easy! Use of EDICTvb for Multi-Plant Advanced PI Calculations Dane OverfieldEXELE Information.
Generating Intelligent Links to Web Pages by Mining Access Patterns of Individuals and the Community Benjamin Lambert Omid Fatemieh CS598CXZ Spring 2005.
File Processing - Database Overview MVNC1 DATABASE SYSTEMS Overview.
WHAT IS A SEARCH ENGINE A search engine is not a physical engine, instead its an electronic code or a software programme that searches and indexes millions.
Program documentation Using the Doxygen tool Program documentation1.
Search - on the Web and Locally Related directly to Web Search Engines: Part 1 and Part 2. IEEE Computer. June & August 2006.
1 Wenguang WangRichard B. Bunt Department of Computer Science University of Saskatchewan November 14, 2000 Simulating DB2 Buffer Pool Management.
Planning a search strategy.  A search strategy may be broadly defined as a conscious approach to decision making to solve a problem or achieve an objective.
BIRT Deployment Plan BIRT Reporting Server Server to Server Integration Integration with Client Side Scripting.
$aveZone Milestone 3 $aveZone Milestone 3 Fifth team: Dima Reshidko Oren Gafni Shiko Raboh.
CLASS Information Management Presented at NOAATECH Conference 2006 Presented by Pat Schafer (CLASS-WV Development Lead)
Use cases Practice 4. Task 1  The author of the article “Author” send his paper (“SendPaper”) to the editor of the magazine (“Edition”). The editor send.
CrowdSearch: Exploiting Crowds for Accurate Real-Time Image Search on Mobile Phones Original work by Tingxin Yan, Vikas Kumar, Deepak Ganesan Presented.
Image Comparison Tool Product Proposal Tim La Fond and Peter Beckfield.
1 City With a Memory CSE 535: Mobile Computing Andreea Danielescu Andrew McCord Brandon Mechtley Shawn Nikkila.
AliEn AliEn at OSC The ALICE distributed computing environment by Bjørn S. Nilsen The Ohio State University.
1. 2 Google Session 1.About MIT’s Google Search Appliance (GSA) 2.Adding Google search to your web site 3.Customizing search results 4.Tips on improving.
 Product Variations and User Uploads  Product and Categories are not enough  Needs to extend product information  User can customize product information.
ICM – API Server & Forms Gary Ratcliffe.
ICM – API Server Gary Ratcliffe. 2 Agenda Webinar Programme API Server Overview JSON-RPC iCM API Service API Server and Forms New services under.
Augmenting (personal) IR Readings Review Evaluation Papers returned & discussed Papers and Projects checkin time.
for all Hyperion video tutorial/Training/Certification/Material Essbase Optimization Techniques by Amit.
Using Workflow With Dataforms Tim Borntreger, Director of Client Services.
Jianping Fan Department of Computer Science University of North Carolina at Charlotte Charlotte, NC Relevance Feedback for Image Retrieval.
WebScan: Implementing QueryServer 2.0 Karl Geiger, Amgen Inc. BRS NA UG August 1999.
General Architecture of Retrieval Systems 1Adrienn Skrop.
/16 Final Project Report By Facializer Team Final Project Report Eagle, Leo, Bessie, Five, Evan Dan, Kyle, Ben, Caleb.
INFORMATION RETRIEVAL MEASUREMENT OF RELEVANCE EFFECTIVENESS 1Adrienn Skrop.
Secure Access and Mobility Jason Kunst, Technical Marketing Engineer March 2016 Location Based Services with Mobility Services Engine ISE Location Services.
This document is proprietary. Any dispatch or disclosure of content is authorized only after written authorization by MEEO S.r.l. SAS FP – ESA-ESRIN Frascati.
Doron Orbach UCMDB Product Manager
Improving searches through community clustering of information
Section 14.1 Section 14.2 Identify the technical needs of a Web server
PROJECTS SUMMARY PRESNETED BY HARISH KUMAR JANUARY 10,2018.
Photo Classification Evaluation Tool
WEB DESIGN Cross 11, Tapovan Enclave Nala pani Road, Dehradun : ,
Presentation transcript:

Presented by: Michal Nir, Saar Gross Supervisors: Nadav Golbandi, Oren Somekh Computer Science Department Industrial Project (234313) Tuesday, January 24, 2012

 This project extends on a previous project which includes a client application (Android) and a server application (Running on Tomcat).  The user takes a photo using his smartphone and records an audio linked to that photo.  Tags are extracted from the audio using speech-to-text and the photo, with its tags, is uploaded to Flickr.  The speech-to-text engine (Sphinx) works best using small dictionaries.  In our project, we will try to supply Sphinx with a custom dictionary created for each photo (Or stack of photos) using the photo’s geo- location information.  Using the geo-location info, we can extract relevant tags from Flickr, thus creating the custom dictionary.

 Implement a new module, running on the server application, that will create custom dictionaries for the Sphinx voice-to-text engine.  Optimize the algorithm for creating the custom dictionary while achieving optimal results with acceptable hit on performance.

 The server generates tag recommendations, in one of two ways:  Uploading an image (Or multiple images) that contains a geo- location, with an audio file attached, will trigger the server to create a custom dictionary for the Sphinx voice-to-text engine.  The client may ask for tag recommendations by sending a request containing the image’s geo-location only.  The server can also be instructed not to use the image’s geo-location for compiling the recommendations list (Privacy concerns) and in that case, only the user’s “private tags” will be used.

 The server supports uploading multiple images-  When uploading multiple images, images are clustered into different groups based on location (Using a simple and deterministic algorithm).  The server will compile a recommendation list for each group.  Every image with an audio file attached will be processed using Sphinx with its group’s custom dictionary.  All images will be uploaded to Flickr using their identified tags and user-supplied tags.  Returning recommendations only for a group of images is essentially the same.  Except, we only return recommendations for the largest group of images.

 Method of compiling a recommendation list for an image (Or group of images): Group of images Public Tags (Based on geo-location) By ranking tags found in images near the given geo-location Public Tags (Based on geo-location) By querying Flicker’s Places API Private Tags (NOT using geo-location) By ranking the user’s past used tags Implemented using independent threads (All running in parallel) Implemented using independent threads (All running in parallel) Merging Results Merging parameters are configurable To Android Client (When asking for Tag Recommendations only) To Sphinx (When uploading images to Flickr)

 Server side: 1. Tag Recommendation are compiled for an image/group of images and can be presented to the user (Recommendation only) or used for Sphinx voice-to-text. 2. Performance: 1. In general- Pretty good. 2. Compiling a recommendation list usually takes no more than a few seconds. 3. In any case, a time limit is enforced. 4. Most interaction with Flickr is completely multi-threaded to avoid bottlenecks. 5. Compiled recommendation lists are cached based on time and location to optimize performance further.

 Server properties file: 1. Virtually all parameters needed for the server are acquired externally from a properties (Settings) file. 1. Tweaking the server becomes an easy and intuitive task. 2. The server uses 2 different sets of settings: 1. Settings to be used when uploading images to Flickr. 2. Settings to be used when asking for Tag Recommendations only. 1. Gives us more flexibility when changing the server’s settings. 3. Example from imageupload.properties: x

Client side:

 Merged the Camera and Gallery applications into one.  Added a new Tag Editor (Can now add/edit and remove tags from images).  Added support for working with multiple images and getting tag recommendations.  Many bug fixes and GUI improvements:  New Image Properties dialog.  Updated menus and icons.  Improved gallery performance and design.

 For evaluating the algorithm’s performance, we would like to do the following:  Find a user who uploaded many tagged images (With a reasonable time difference between them) in a popular location (San Francisco bridge, Las-Vegas Strip).  Perform a cross-validation analysis-  Choose a subset of images from the user’s images.  Send the images to server and receive tag recommendations for them.  Evaluate the accuracy (Precision and Recall) of the recommendations using the 2 left-out images.  Repeat…  Our expectations are that accuracy will be affected by many factors-  Number of tags merged into final recommendation list from each source.  Dictionary size.

 We wrote TagRecTestFramework-  Completely automated.  Behaves like a “normal” client (Server thinks it’s talking to an Android client).  For each given location-  Finds a user with enough tagged images (Configurable…) in the area with a small time difference between images (Also configurable).  Perform cross-validation on grouped images.

-10 images in each group, Min. of 20 tags per image -Search radius: 1 KM, Time difference between images: Max. 1 day Piazza San Pietro (Vatican City) ( , )

 Algorithm’s accuracy is very image/user-dependent:  We found that most images in Flickr are not tagged or tagged with irrelevant tags.  Most images on Flickr are not geotagged.  Flickr has ~5 billion photos.  Only ~170 million are geotagged (~3% of all photos).  Quality of results could be improved by tweaking the server’s settings-  Giving more weight to private/public tags affects the accuracy.  Compiling a larger recommendation list (And thus, a larger dictionary for Sphinx) improves recall but may hurt Sphinx’s performance (Sphinx works best with small dictionaries).