IP: Now that's what I call filtering

[Dave Farber <farber () central cis upenn edu>]

Date: Sat, 18 Nov 1995 16:38:01 -0800 (PST)
From: Declan McCullagh <declan () eff org>
To: fight-censorship+ () andrew cmu edu


As a research project, this might be even more interesting than Marty's. 


-Declan




// declan () eff org // My opinions are not in any way those of the EFF //






 From: Alix Herrmann <alix () physihp1 unil ch>
 Date: Fri, 10 Nov 95 10:03:13 +0100
 To: darbnet () ugcs caltech edu
 Subject: How to find naked people
 Reply-To: Alix.HerrmannScheurer () ipn unil ch
 
 Here is part of an announcement I got for a provocative upcoming
 (snicker) seminar at Tech.  Anyone going?   net.paranoia discussion
 topic:  does anyone know what possible applications there might be
 besides censorship or spying?
 
 --Alix
 
 Begin forwarded message:
 
 There is an ERC sponsored seminar this Monday, November 13, 1995 at
 4:00 pm in 24 Beckman Behavioral Biology.  Refreshments will be
 served prior to the seminar.  We hope to see you there (clothed, of
 course).
 
 
 Finding Naked People
 David Forsyth, Assistant Professor, Computer Science, UC Berkeley.
 
 abstract:
 
 This talk describes a content-based retrieval strategy that can
 tell whether there are naked people present in an image.
 No manual intervention is required.  The approach combines color and
 texture properties to obtain an effective mask for skin regions.  The
 skin mask is shown to be effective for a wide range of shades and
 colors of skin.  These skin regions are then fed to a specialized
 grouper, which attempts to group a human figure using geometric
 constraints on human structure.    This approach introduces a new
 view of object recognition, where an object model is an organized
 collection of grouping hints obtained from a combination of
 constraints on geometric properties such as the structure of
 individual parts, and the relationships between parts,  and
 constraints on color and texture.
 The system is demonstrated to have 60% precision and 52% recall on
 a test set of 138 uncontrolled images of naked people, mostly
 obtained from the internet, and 1401 assorted control images, drawn
 from a wide collection of sources.
 
 Marilyn Mollinedo
 Center for Neuromorphic Systems Engineering
 California Institute of Technology
 Mail Code 256-80
 Pasadena, California 91125
 (818) 395-6255