Mobile APplications Lab
APL 1.0
Dec. 17, 2013

Relational Social Image Search - Leveraging Big Data To Improve Image Search On Facebook and Flickr

UPDATE: The United States Patent and Trademark Office has just issued US Patent #8,611,673 “Method, system and computer program for interactive spatial link-based image searching, sorting and/or displaying”.

UPDATE #2: Read the background story on Parham Aarabi's WIRED post:

UPDATE #3: Read the full coverage on WIRED Magazine:

UPDATE #4: Read about the coverage on CTV News:

UPDATE #5: Here is the latest coverage by Mashable including a very nice video explaining our technology:

UPDATE #6: Here is the latest coverage of this work on CNN and GigaOM:

On December 10, at the IEEE International Symposium on Multimedia in Anaheim we will be showcasing a new method of searching and finding the relationship between objects based on their spatial arrangement in a set of tagged images. Based on the relative coordinates of each object tag, we compute a joint Relativity between each tag pair. We then propose an efficient image search method using the joint Relativity graphs and provide simple examples where the proposed Relational Social Image (RSI) search produces more relevant and intuitive results than simple search.


Hidden within the relative location of tags in images is a relational model that can identify how close two individuals are, or, the affinity of a person to an object or a brand. RSIS can make searching on social networks such as Facebook better by:

Relevant publications:

Ron Appel, Parham Aarabi, From Images To Maps, Canadian Conference on Electrical and Computer Engineering, 2009.

Ron Appel, From Images To Maps, M.A.Sc. Thesis, Department of Electrical and Computer Engineering, University of Toronto, 2009.

Parham Aarabi, Relational Social Image Search, IEEE International Symposium on Multimedia, December, 2013.

Related Links:       Read Poster      

About the APL:

The Mobile Applications Lab (APL) focuses on novel algorithms, technologies, and systems that use the advanced sensing and visual+acoustic+tactile interaction mechanisms of modern smartphones/tablets. In other words, we explore ways to create disruptive mobile apps with a particular focus on sensing and information processing.

Our physical lab, in the Bahen Center for Information Technology (Room 4158), hosts a variety of dedicated stations for application exploration, simulation, and testing, including iOS and Android equipped development stations (more platforms to come soon). This facility is open to any and all UofT student/employee/faculty who are interested in mobile applications research (if you are interested to use our facility, please send an email to Prof. Aarabi at p (AT) arh (D0T) am).

If you are interested in creating and learning about mobile apps, please visit the ECE1778S course website or the ECE1780S course website.
Mobile App Lab Demo Night - April 17, 2014 @ 6:00pm in SF 1105
Apr. 17, 2013
Ioannis Verdelis, Founder and COO of Fleksy, To Give a Talk at UofT/APL on Monday April 7 at 5pm in BA1180
Apr. 7, 2013
Relational Social Image Search - Leveraging Big Data To Improve Image Search On Facebook and Flickr
Dec. 17, 2013
Mobile UI Talk: Will Walmsley of Whirlscape/Minuum
Sept. 18, 2013
APL Palo Alto Meetup - July 20, 2013
July 20, 2013
TechVibes: The Mobile Applications Lab is Canada's First Laboratory for Mobile App Development
June 24, 2013
Venturebeat: What the future of mobile keyboards will look like
June 8, 2013
APL Los Angeles Meetup - June 12, 2013
June 5, 2013
Globe and Mail: Phone app relieves parents' angst over proper fever medicine dose for young kids
May 6, 2013
Extended Touch: New APL Technology Makes Any Surface Touch-Sensitive By Just Placing a Mobile Device On It
April 30, 2013
VentureBeat: 5 tips for creating great mobile app user interfaces
April 8, 2013
Prof. Rose Featured on “Virtual Researchers On Call”
January 7, 2013
APL-created “Heart Tricorder” app becomes the #1 medical app in over 20 countries
January 4, 2013
CBC News: “App creation is becoming a growing part of the Canadian economy”
December 1, 2012
APL researchers create real-time object tracking on iPhone
December 6, 2011
Tiny Videos: A Large Data Set for Nonparametric Video Retrieval and Frame Classification
November 1, 2011
Intelligent Ad Resizing
December 1, 2010
Quick Links
• APL 1.0 Website
• ECE1778S

• ECE1780F

• Prof. Parham Aarabi
• Prof. Jonathan Rose
Contact Us
If you have any questions, please contact us:
Prof. Aarabi: p(AT)arh(D0T)am
Prof. Rose: jayar(at)
© 2014 University of Toronto