Pill-ID

Matching and retrieval of drug pill images

Young Beom Lee, Unsang Park, Anil K. Jain, Seong Whan Lee

Research output: Contribution to journalArticle

20 Citations (Scopus)

Abstract

Worldwide, law enforcement agencies are encountering a substantial increase in the number of illicit drug pills being circulated in our society. Identifying the source and manufacturer of these illicit drugs will help deter drug-related crimes. We have developed an automatic system, called Pill-ID to match drug pill images based on several features (i.e.; imprint, color, and shape) of the tablet. The color and shape information is encoded as a three-dimensional histogram and invariant moments, respectively. The imprint on the pill is encoded as feature vectors derived from SIFT and MLBP descriptors. Experimental results using a database of drug pill images (1029 illicit drug pill images and 14,002 legal drug pill images) show 73.04% (84.47%) rank-1 (rank-20) retrieval accuracy.

Original languageEnglish
Pages (from-to)904-910
Number of pages7
JournalPattern Recognition Letters
Volume33
Issue number7
DOIs
Publication statusPublished - 2012 May 1

Fingerprint

Color
Crime
Law enforcement

Keywords

  • Color histogram
  • Illicit drugs
  • Image retrieval
  • Imprints
  • Moment invariants
  • Pill images

ASJC Scopus subject areas

  • Software
  • Artificial Intelligence
  • Computer Vision and Pattern Recognition
  • Signal Processing

Cite this

Pill-ID : Matching and retrieval of drug pill images. / Lee, Young Beom; Park, Unsang; Jain, Anil K.; Lee, Seong Whan.

In: Pattern Recognition Letters, Vol. 33, No. 7, 01.05.2012, p. 904-910.

Research output: Contribution to journalArticle

Lee, Young Beom ; Park, Unsang ; Jain, Anil K. ; Lee, Seong Whan. / Pill-ID : Matching and retrieval of drug pill images. In: Pattern Recognition Letters. 2012 ; Vol. 33, No. 7. pp. 904-910.
@article{4038c432a8b64998ba783eb6205160ff,
title = "Pill-ID: Matching and retrieval of drug pill images",
abstract = "Worldwide, law enforcement agencies are encountering a substantial increase in the number of illicit drug pills being circulated in our society. Identifying the source and manufacturer of these illicit drugs will help deter drug-related crimes. We have developed an automatic system, called Pill-ID to match drug pill images based on several features (i.e.; imprint, color, and shape) of the tablet. The color and shape information is encoded as a three-dimensional histogram and invariant moments, respectively. The imprint on the pill is encoded as feature vectors derived from SIFT and MLBP descriptors. Experimental results using a database of drug pill images (1029 illicit drug pill images and 14,002 legal drug pill images) show 73.04{\%} (84.47{\%}) rank-1 (rank-20) retrieval accuracy.",
keywords = "Color histogram, Illicit drugs, Image retrieval, Imprints, Moment invariants, Pill images",
author = "Lee, {Young Beom} and Unsang Park and Jain, {Anil K.} and Lee, {Seong Whan}",
year = "2012",
month = "5",
day = "1",
doi = "10.1016/j.patrec.2011.08.022",
language = "English",
volume = "33",
pages = "904--910",
journal = "Pattern Recognition Letters",
issn = "0167-8655",
publisher = "Elsevier",
number = "7",

}

TY - JOUR

T1 - Pill-ID

T2 - Matching and retrieval of drug pill images

AU - Lee, Young Beom

AU - Park, Unsang

AU - Jain, Anil K.

AU - Lee, Seong Whan

PY - 2012/5/1

Y1 - 2012/5/1

N2 - Worldwide, law enforcement agencies are encountering a substantial increase in the number of illicit drug pills being circulated in our society. Identifying the source and manufacturer of these illicit drugs will help deter drug-related crimes. We have developed an automatic system, called Pill-ID to match drug pill images based on several features (i.e.; imprint, color, and shape) of the tablet. The color and shape information is encoded as a three-dimensional histogram and invariant moments, respectively. The imprint on the pill is encoded as feature vectors derived from SIFT and MLBP descriptors. Experimental results using a database of drug pill images (1029 illicit drug pill images and 14,002 legal drug pill images) show 73.04% (84.47%) rank-1 (rank-20) retrieval accuracy.

AB - Worldwide, law enforcement agencies are encountering a substantial increase in the number of illicit drug pills being circulated in our society. Identifying the source and manufacturer of these illicit drugs will help deter drug-related crimes. We have developed an automatic system, called Pill-ID to match drug pill images based on several features (i.e.; imprint, color, and shape) of the tablet. The color and shape information is encoded as a three-dimensional histogram and invariant moments, respectively. The imprint on the pill is encoded as feature vectors derived from SIFT and MLBP descriptors. Experimental results using a database of drug pill images (1029 illicit drug pill images and 14,002 legal drug pill images) show 73.04% (84.47%) rank-1 (rank-20) retrieval accuracy.

KW - Color histogram

KW - Illicit drugs

KW - Image retrieval

KW - Imprints

KW - Moment invariants

KW - Pill images

UR - http://www.scopus.com/inward/record.url?scp=84858437554&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=84858437554&partnerID=8YFLogxK

U2 - 10.1016/j.patrec.2011.08.022

DO - 10.1016/j.patrec.2011.08.022

M3 - Article

VL - 33

SP - 904

EP - 910

JO - Pattern Recognition Letters

JF - Pattern Recognition Letters

SN - 0167-8655

IS - 7

ER -