COMPUTER SCIENCE DEPARTMENT Technion Israel Institute of Technology

  • Slides: 9
Download presentation
COMPUTER SCIENCE DEPARTMENT Technion - Israel Institute of Technology EXTRACTING INFORMATION FROM PICASA &

COMPUTER SCIENCE DEPARTMENT Technion - Israel Institute of Technology EXTRACTING INFORMATION FROM PICASA & ONEDRIVE FOR CORTANA Final Meeting Students: Ron Saad and Eliran Weiss Supervisors: Adi Miller and Michael Sterenberg PM 6: 10: 09 CS 234313 Technion 1

THE TEAM � Adi Miller and Michael Shterenberg �Microsoft Supervisors � Eliran Weiss and

THE TEAM � Adi Miller and Michael Shterenberg �Microsoft Supervisors � Eliran Weiss and Ron Saad �Technion CS Students PM 6: 10: 12 CS 234313 Technion 2

GOALS § Extract photo metadata from users’ Picasa and One. Drive accounts. § Process

GOALS § Extract photo metadata from users’ Picasa and One. Drive accounts. § Process the data and find trips the user has taken with various metadata features. § Implement a tunable and configurable algorithm for experimentation and visualization. PM 6: 10: 13 CS 234313 Technion 3

METHODOLOGY � Our project was research-driven �We started off with a vague concept of

METHODOLOGY � Our project was research-driven �We started off with a vague concept of what we should accomplish. �We’ve studied various public APIs and common user usage of cloud services. �After we realized the capabilities of each API, we decided (with our advisors) that trips -inferring would be the best course of action. �We’ve then studied several clustering algorithms to use in our own trips-inferring algorithm. PM 6: 10: 13 CS 234313 Technion 4

METHODOLOGY (CONT. ) � After we’ve finished All research, we focused on coding We’ve

METHODOLOGY (CONT. ) � After we’ve finished All research, we focused on coding We’ve build a small WPF tool to test our initial algorithm, with a relatively small amount of data. � We’ve built a web application that saves the user’s data and shows him a textual representation of trips we discovered with semantic names (e. g. New York instead of 34. 321 79. 543) and time span. � After we gathered enough data, we tweaked our algorithm and developed a web-based tool to tune the algorithm parameters and visualize the results on a map. � PM 6: 10: 14 CS 234313 Technion 5

ACHIEVEMENTS �A modifiable algorithm for trips inference. � A web application that shows users

ACHIEVEMENTS �A modifiable algorithm for trips inference. � A web application that shows users their trips as a textual result. � A web tool to tune the algorithm and view the results on a given user. � We’ve gathered valuable data: We have a database of over 700, 000 photos meta -data from over 100 users. PM 6: 10: 18 CS 234313 Technion 6

EXAMPLES PM 6: 10: 18 CS 234313 Technion 7

EXAMPLES PM 6: 10: 18 CS 234313 Technion 7

PM 6: 10: 20 CS 234313 Technion 8

PM 6: 10: 20 CS 234313 Technion 8

CONCLUSIONS � The idea of recognizing trips with merely photo metadata is indeed feasible.

CONCLUSIONS � The idea of recognizing trips with merely photo metadata is indeed feasible. � We successfully differ between trips and short visits, casual hangouts, workplaces and home. � More adapting and parameterizing can be done if the developer wishes to. PM 6: 10: 22 CS 234313 Technion 9

Related presentations

Ulsan national institute of science and technology (unist)Ulsan national institute of science and technology (unist)
Masdar institute of science and technologyMasdar institute of science and technology
Madhav institute of technology and scienceMadhav institute of technology and science
Kigali institute of science and technologyKigali institute of science and technology
Iist puneIist pune
Shri dadaji institute of technology and scienceShri dadaji institute of technology and science
Corporate institute of science and technology bhopalCorporate institute of science and technology bhopal
Onedrive technionOnedrive technion
Technion aerospaceTechnion aerospace
Michael silverstein technionMichael silverstein technion