Computer Image Retrieval by Features: Selecting the Best Facial Features for Suspect Identification Systems.
Eric S. Lee, Thomas Whalen:
Computer Image Retrieval by Features: Selecting the Best Facial Features for Suspect Identification Systems.
CIKM 1994: 105-111@inproceedings{DBLP:conf/cikm/LeeW94,
author = {Eric S. Lee and
Thomas Whalen},
title = {Computer Image Retrieval by Features: Selecting the Best Facial
Features for Suspect Identification Systems},
booktitle = {Proceedings of the Third International Conference on Information
and Knowledge Management (CIKM'94), Gaithersburg, Maryland, November
29 - December 2, 1994},
publisher = {ACM},
year = {1994},
pages = {105-111},
ee = {db/conf/cikm/LeeW94.html, http://doi.acm.org/10.1145/191246.191266},
crossref = {DBLP:conf/cikm/94},
bibsource = {DBLP, http://dblp.uni-trier.de}
}
BibTeX
Abstract
Correct suspect identification of known offenders by witnesses deteriorates rapidly as more are
examined in mugshot albums. Feature approaches, where mugshots are displayed in order of
similarity to witnesses' descriptions, increase identification success by reducing this number. System
performance depends on selection of system features. Four methods of selecting features are
evaluated empirically: theory, random, hill-climbing algorithm, and hybrid. The theory asserts
success depends on five properties of system features: informativeness, orthogonality, sufficiency,
consistency, and observability. Comparing system performance on the best 10 features selected
(from a pool of 90) by each method supports our contention. In four experimental tests of a system
with 1000 official mugshots, over 90% of witness searches resulted in photos of target suspects
retrieved in the first ten mugshots displayed for examination (using all 90 system features). On
average, suspects were retrieved in the first 54, 7, 22, and 70 mugshots when using only the best 10
model features. Hybrid and hill-climbing algorithms did not improve on this performance, and
performance of randomly selected sets of 10 features was poor.
Copyright © 1994 by the ACM,
Inc., used by permission. Permission to make
digital or hard copies is granted provided that
copies are not made or distributed for profit or
direct commercial advantage, and that copies show
this notice on the first page or initial screen of
a display along with the full citation.
CDROM Version: Load the CDROM "Volume 2 Issue 4, CIKM, DOLAP, GIS, SIGFIDET, ..." and ...
DVD Version: Load ACM SIGMOD Anthology DVD 1" and ...
BibTeX
Printed Edition
Proceedings of the Third International Conference on Information and Knowledge Management (CIKM'94), Gaithersburg, Maryland, November 29 - December 2, 1994.
ACM 1994
Contents BibTeX
Online Edition
Citation Page
BibTeX
BibTeX
ACM SIGMOD Anthology - DBLP:
[Home | Search: Author, Title | Conferences | Journals]
CIKM 1994 Proceedings, ACM SIGMOD Anthology: Copyright © by ACM (info@acm.org), Corrections: anthology@acm.org
DBLP: Copyright © by Michael Ley (ley@uni-trier.de), last change: Sat May 16 23:01:44 2009
