A Survey of Research Prospects          for more Manageable Personal              Digital Photo Collections               ...
what metadata matters?•   event•   location•   people•   time
the metaphorical shoebox                 “Shoebox No. 1” by Flickr user kahala under CC BY-NC-ND 2.0
our digital photos are proliferating                         Good: “How many photos have ever been taken?”
our digital photos are distributed
our digital photos are many               Lev Manovich: “Cultural Analytics visualizations on ultra high resolution displa...
we have some tools       “My work table and some beloved tools~ 6 of 6 photos” by Flickr user Urban Woodswalker under CC B...
facial recognition                “Picasa Face Recognition is cool” by Flickr user vanholy under CC BY-NC-ND 2.0
geotagging             flickr: “Explore everyones photos on a Map”
social annotation               “The Facebook Manual Auto-tag” by Flickr user Ambuj Saxena under CC BY 2.0
metadata standards           “Adding IPTC Metadata with Adobe Bridge” by Flickr user StevenErat under CC BY-NC-SA 2.0
prospective tools                    “Space Cameras” by Flickr user HeatherMG under CC BY-NC-ND 2.0
tools provenance• forensics (security, law enforcement,  counterterrorism)• robotics (autonomous)• consumer applications (...
dating digitized photos by color     processing technology                     Palermo, Hays, and Efros: “Dating Historica...
image orientation detection of      digitized photos           Datar and Qi: “Automatic Image Orientation Detection Using ...
probabalistic regionalgeotagging by visual similarity               Hays and Efros: “IM2GPS: estimating geographic informa...
satellite and ground imagerycorroboration for geotagging                  Grosse and Johnson: “Matching a photograph to sa...
identifying cities by                                    trivial visual elementsDoersch et al.: “What Makes Paris Look Lik...
geotagging and 3D scene construction       using large photo sets                  Snavely, Seitz, and Szeliski: “Photo To...
historical photo overlay              WhatWasThere: “Jimmy Carter on a Campaign Stop in Plains”
automatic “event” identification by  temporal and visual clustering          Cooper et al.: “Temporal Event Clustering for...
recognizing persons using                                  body patch matching                                            ...
recognizing persons using      social context          Naaman et al.: “Leveraging Context to Resolve Identity in Photo Alb...
recognizing persons using  social network context       Stone et al.: “Autotagging Facebook: Social Network Context Improv...
inferring photographerbased on height of shot      Farid: “Who Took That Picture? (Or at least, how tall was the photograp...
graphing incidence ofindividuals over time               Hangal: “Muse: Revive Precious Memories Using Email.”
Nicholas Taylor @nullhandle                  “Thank You” by Flickr user muffintinmom under CC BY 2.0
Upcoming SlideShare
Loading in …5
×

A Survey of Research Prospects for more Manageable Personal Digital Photo Collections

3,082 views

Published on

Presentation given at Personal Digital Archiving on promising technologies demonstrated in research literature that may ultimately improve annotation and management of personal digital photo collections.

Published in: Technology
0 Comments
1 Like
Statistics
Notes
  • Be the first to comment

No Downloads
Views
Total views
3,082
On SlideShare
0
From Embeds
0
Number of Embeds
7
Actions
Shares
0
Downloads
19
Comments
0
Likes
1
Embeds 0
No embeds

No notes for slide
  • https://chrome.google.com/webstore/detail/picasa/onlgmecjpnejhfeofkgbfgnmdlipdejbhttps://play.google.com/store/apps/details?id=com.amazon.clouddrive.photoshttps://www.adobe.com/designcenter-archive/photoshopelements/articles/lrvid2312_pse.htmlhttp://www.amazon.com/gp/feature.html?ie=UTF8&docId=1000828861https://www.apple.com/apps/iphoto/http://www.canon.com/camera-museum/design/frontline/product/kissx5/http://www.g4tv.com/thefeed/blog/post/725553/how-google-glass-could-change-video-games/http://www.intel.com/content/www/us/en/tablets/tablets.htmlhttp://www.wired.co.uk/news/archive/2012-10/23/memoto
  • Photographic prints from different time periods have different, identifiable color signatures based on the distinct succession of chemical processing technologies, facilitating EXIF timestamp generation.
  • The orientation of digitized photos can be detected and automatically corrected.
  • Cities can be identified by far less than their most visually iconic landmarks. Photos from different European cities were successfully localized relying on seemingly trivial elements in the visual environment: lamp-posts, grating iron-work, door frames, etc.
  • EXIF timestamps and the visual content of photos can be used to organize them into probable “events.”
  • Extending recognition algorithms to examine other parts of the body aside from the face increases accuracy.
  • Knowing which individuals are commonly in photos with which other individuals informs person recognition.
  • Who an individual is connected to and interacts with on social networks can help narrow likely candidates for person annotation in photos.
  • The angel from which the photo was shot relative to a vanishing point and the ground plane can be used to infer the height of the camera, which may provide insight into who the photographer was.
  • Muse is a personal data mining application for e-mail that shows, among other things, the frequency of communications with different individuals and groups of people over time; perhaps something like it could be adapted for use with photos?
  • A Survey of Research Prospects for more Manageable Personal Digital Photo Collections

    1. A Survey of Research Prospects for more Manageable Personal Digital Photo Collections Nicholas Taylor @nullhandlePersonal Digital ArchivingFebruary 21, 2013 “Photo Mosaic-Orange Daisy” by Flickr user BerniMartin under CC BY-ND 2.0
    2. what metadata matters?• event• location• people• time
    3. the metaphorical shoebox “Shoebox No. 1” by Flickr user kahala under CC BY-NC-ND 2.0
    4. our digital photos are proliferating Good: “How many photos have ever been taken?”
    5. our digital photos are distributed
    6. our digital photos are many Lev Manovich: “Cultural Analytics visualizations on ultra high resolution displays”
    7. we have some tools “My work table and some beloved tools~ 6 of 6 photos” by Flickr user Urban Woodswalker under CC BY-NC-ND 2.0
    8. facial recognition “Picasa Face Recognition is cool” by Flickr user vanholy under CC BY-NC-ND 2.0
    9. geotagging flickr: “Explore everyones photos on a Map”
    10. social annotation “The Facebook Manual Auto-tag” by Flickr user Ambuj Saxena under CC BY 2.0
    11. metadata standards “Adding IPTC Metadata with Adobe Bridge” by Flickr user StevenErat under CC BY-NC-SA 2.0
    12. prospective tools “Space Cameras” by Flickr user HeatherMG under CC BY-NC-ND 2.0
    13. tools provenance• forensics (security, law enforcement, counterterrorism)• robotics (autonomous)• consumer applications (photo management)
    14. dating digitized photos by color processing technology Palermo, Hays, and Efros: “Dating Historical Color Images”
    15. image orientation detection of digitized photos Datar and Qi: “Automatic Image Orientation Detection Using the Supervised Self-Organizing Map”
    16. probabalistic regionalgeotagging by visual similarity Hays and Efros: “IM2GPS: estimating geographic information from a single image”
    17. satellite and ground imagerycorroboration for geotagging Grosse and Johnson: “Matching a photograph to satellite images”
    18. identifying cities by trivial visual elementsDoersch et al.: “What Makes Paris Look Like Paris?” “Eiffel Tower” by Flickr user HarshLight under CC BY 2.0
    19. geotagging and 3D scene construction using large photo sets Snavely, Seitz, and Szeliski: “Photo Tourism: Exploring Photo Collections in 3D”
    20. historical photo overlay WhatWasThere: “Jimmy Carter on a Campaign Stop in Plains”
    21. automatic “event” identification by temporal and visual clustering Cooper et al.: “Temporal Event Clustering for Digital Photo Collections”
    22. recognizing persons using body patch matching Suh and Bederson: “Semi-Automatic Photo Annotation Strategies Using Event Based Clustering and Clothing Based Person Recognition”Cooray et al.: “Identifying Person Re-Occurrences for Personal Photo Management Applications”
    23. recognizing persons using social context Naaman et al.: “Leveraging Context to Resolve Identity in Photo Albums”
    24. recognizing persons using social network context Stone et al.: “Autotagging Facebook: Social Network Context Improves Photo Annotation”
    25. inferring photographerbased on height of shot Farid: “Who Took That Picture? (Or at least, how tall was the photographer?)”
    26. graphing incidence ofindividuals over time Hangal: “Muse: Revive Precious Memories Using Email.”
    27. Nicholas Taylor @nullhandle “Thank You” by Flickr user muffintinmom under CC BY 2.0

    ×