Interesting People mailing list archives
IP: Now that's what I call filtering
From: Dave Farber <farber () central cis upenn edu>
Date: Mon, 20 Nov 1995 13:21:03 -0500
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
Current thread:
- IP: Now that's what I call filtering Dave Farber (Nov 20)