Skip to main content skip navigation
  • Account
    • Login
    • Manage
  • Subscribe
    • JUSTINFO
    • Register
  • Shopping Cart
  • Contact Us
    • Email
    • Feedback
    • Chat
    • Phone or Mail
  • Site Help
National Criminal Justice Reference Service
Office of Justice Programs header with links to bureaus/offices: BJA, BJS, NIJ, OJJDP, OVC, SMART Office of Justice Programs BJA BJS NIJ OJJDP OVC SMART Office of Justice Programs
Advanced Search  Search Help
    Browse By Topics  down arrow
  • A–Z Topics
  • Corrections
  • Courts
  • Crime
  • Crime Prevention
  • Drugs
  • Justice System
  • Juvenile Justice
  • Law Enforcement
  • Victims
CrimeSolutions
Add your conference to our Justice Events calendar
  • ABOUT NCJRS
  • OJP PUBLICATIONS
  • LIBRARY
  • SEARCH Q & A
  • GRANTS & FUNDING
  • JUSTICE EVENTS
Home / Publications / NCJRS Abstract

PUBLICATIONS

Register for Latest Research

Stay Informed
Register with NCJRS to receive NCJRS's biweekly e-newsletter JUSTINFO and additional periodic emails from NCJRS and the NCJRS federal sponsors that highlight the latest research published or sponsored by the Office of Justice Programs.

NCJRS Abstract

The document referenced below is part of the NCJRS Virtual Library collection. To conduct further searches of the collection, visit the Virtual Library. See the Obtain Documents page for direction on how to access resources online, via mail, through interlibrary loans, or in a local library.

1 record(s) found

 

NCJ Number: 254636 Find in a Library
Title: DeepPatrol: Finding Illicit Videos for Law Enforcement
Document: PDF
Author(s): Marco Alvarez Vega
Date Published: April 2020
Annotation: This is the Final Summary Report on the methodology and results of the development of DeepPatrol, an innovative software tool to assist law enforcement agencies in investigating child pornography cases.
Abstract: This project used recent advances in computer vision and machine learning to automate the process of identifying sexually exploitative Imagery of children (SEIC), so as to reduce the time investigators spend in collecting image evidence. Traditional machine learning methods for this task rely on manual feature engineering and tend to produce many false positives. When many files are on a suspect’s hard drive, the agent reviewing evidence may be overwhelmed with imagery that is falsely flagged as SEIC, especially when a variety of pornographic images are present. This occurs because pornographic content is difficult to distinguish from SEIC when using traditional techniques. Researchers have recently had greater success in detecting nudity; however, these models have difficulty in differentiating nudity in SEIC from nudity in adult pornography. In addressing this issue, the current project fused the predictions of these more accurate deep-learning models for nudity detection with apparent age estimation to identify SEIC images. This novel approach provides a framework that can be as fine or coarse a filter as an investigator specifies. It can distinguish between challenging examples of pornographic and SEIC videos with 89-percent accuracy, using the default thresholds. Since this approach relies on automatic representation learning with the use of convolutional neural networks, investigators are not required to be directly exposed to pornographic or SEIC images. The models were tested on a series of challenging datasets in analyzing their performance prior to presenting results on data collected from actual cases. 2 figures
Main Term(s): Police equipment
Index Term(s): Child Pornography; Computer aided investigations; Computer aided operations; Computer crime investigative Training; Computer evidence; Investigative techniques; NIJ final report; NIJ grant-related documents; NIJ Resources; Video imaging
Grant Number: 2016-MU-CX-K015
Sponsoring Agency: National Institute of Justice (NIJ)
Washington, DC 20531
US Dept of Justice NIJ Pub
Washington, DC 20531
Sale Source: US Dept of Justice NIJ Pub
810 Seventh Street, NW
Washington, DC 20531
United States of America
Page Count: 11
Format: Document; Document (Online)
Type: Program/Project Description; Report (Grant Sponsored); Report (Study/Research); Research (Applied/Empirical)
Language: English
Country: United States of America
To cite this abstract, use the following link:
http://www.ncjrs.gov/App/publications/abstract.aspx?ID=277881

*A link to the full-text document is provided whenever possible. For documents not available online, a link to the publisher's website is provided. Tell us how you use the NCJRS Library and Abstracts Database - send us your feedback.




Find in a Library

You have clicked Find in a Library. A title search of WorldCat, the world's largest library network, will start when you click "Continue." Here you will be able to learn if libraries in your community have the document you need. The results will open in a new browser and your NCJRS session will remain active for 30 minutes. Learn More.

You have selected:

This article appears in

In WorldCat, verify that the library you select has the specific journal volume and issue in which the article appears. Learn How.

Continue to WorldCat

You are about to access WorldCat, NCJRS takes no responsibility for and exercises no control over the WorldCat site.

 
Office of Justice Programs Facebook Page  Twitter Page
  • Bureau of Justice Assistance Facebook Page Twitter Page
  • Bureau of Justice Statistics Twitter Page
  • National Institute of Justice Facebook Page Twitter Page
  • Office for Victims of Crime Facebook Page Twitter Page
  • Office of Juvenile Justice and Delinquency Prevention Facebook Page Twitter Page
  • Office of Sex Offender Sentencing, Monitoring, Apprehending, Registering, and Tracking Facebook Page Twitter Page
Contact Us | Feedback | Site Map
Freedom of Information Act | Privacy Statement | Legal Policies and Disclaimers
USA.gov | CrimeSolutions
Department of Justice | Office of Justice Programs