[MCN-L] Facial recognition technology and photos
Hi all, I'm curious as to whether anyone has investigated facial recognition software as a way to quickly identify people who show up in photos in large photographic collections. We're in the process of digitizing a collection of about 3500 auto racing photographs, a number of which are posed and/or have people facing the camera straight-on. We're wondering if facial recognition technology could help us identify the numerous people who recur throughout the collection in a efficient and semi-automated fashion, allowing us to add some useful metadata with relatively low effort. Has anybody tried this, or thought about it? I would love to hear your thoughts/experiences. Thanks! Ellice Engdahl, Digital Collections Initiative Manager The Henry Ford 20900 Oakwood Blvd., Dearborn, MI 48124 (o) 313.982.6005 | (e) ElliceE at thehenryford.org
[MCN-L] Facial recognition technology and photos
Hi Ellice, Have you seen Tim Sherrat's work on Invisible Australia? http://discontents.com.au/the-real-face-of-white-australia/ There's some code that will extract faces out of the photographs available at: https://github.com/wragge/Facial-detection Richard J. Urban, Assistant Professor College of Communication and Information School of Library and Information Studies Florida State University Florida's iSchool rurban at fsu.edu @musebrarian On May 20, 2013, at 3:50 PM, Ellice Engdahl wrote: Hi all, I'm curious as to whether anyone has investigated facial recognition software as a way to quickly identify people who show up in photos in large photographic collections. We're in the process of digitizing a collection of about 3500 auto racing photographs, a number of which are posed and/or have people facing the camera straight-on. We're wondering if facial recognition technology could help us identify the numerous people who recur throughout the collection in a efficient and semi-automated fashion, allowing us to add some useful metadata with relatively low effort. Has anybody tried this, or thought about it? I would love to hear your thoughts/experiences. Thanks! Ellice Engdahl, Digital Collections Initiative Manager The Henry Ford 20900 Oakwood Blvd., Dearborn, MI 48124 (o) 313.982.6005 | (e) ElliceE at thehenryford.org ___ You are currently subscribed to mcn-l, the listserv of the Museum Computer Network (http://www.mcn.edu) To post to this list, send messages to: mcn-l at mcn.edu To unsubscribe or change mcn-l delivery options visit: http://mcn.edu/mailman/listinfo/mcn-l The MCN-L archives can be found at: http://toronto.mediatrope.com/pipermail/mcn-l/
[MCN-L] Facial recognition technology and photos
Don't know about photographic collections, but UC Riverside's Art History Dept. is exploring this technology for identifying individuals in paintings. See http://ucrtoday.ucr.edu/5453. BTW - They just received their second NEH-ODH grant to explore the use of this technology for this purpose, so I am guessing they see some potential in its use? Diane Diane M. Zorich Cultural Heritage Consultant ? Digital Strategies for Culture Organizations 113 Gallup Road Princeton, NJ 08540 USA Voice: 609 252-1518 Email: dzorich at mindspring.com or dianezorich at comcast.net Twitter: @dzorich -- On 5/20/13 3:50 PM, Ellice Engdahl ElliceE at thehenryford.org wrote: Hi all, I'm curious as to whether anyone has investigated facial recognition software as a way to quickly identify people who show up in photos in large photographic collections. We're in the process of digitizing a collection of about 3500 auto racing photographs, a number of which are posed and/or have people facing the camera straight-on. We're wondering if facial recognition technology could help us identify the numerous people who recur throughout the collection in a efficient and semi-automated fashion, allowing us to add some useful metadata with relatively low effort. Has anybody tried this, or thought about it? I would love to hear your thoughts/experiences. Thanks! Ellice Engdahl, Digital Collections Initiative Manager The Henry Ford 20900 Oakwood Blvd., Dearborn, MI 48124 (o) 313.982.6005 | (e) ElliceE at thehenryford.org ___ You are currently subscribed to mcn-l, the listserv of the Museum Computer Network (http://www.mcn.edu) To post to this list, send messages to: mcn-l at mcn.edu To unsubscribe or change mcn-l delivery options visit: http://mcn.edu/mailman/listinfo/mcn-l The MCN-L archives can be found at: http://toronto.mediatrope.com/pipermail/mcn-l/