Automatic Weapon Detection in Social Media Image Data using a Two-Pass Convolutional Neural Network

  • Jens Elsner Munich Innovation Labs
  • Thomas Fritz Munich Innovation Labs
  • Laura Henke Munich Innovation Labs
  • Oussama Jarrousse Munich Innovation Labs
  • Stefan Taing Munich Innovation Labs
  • Mathias Uhlenbrock Munich Innovation Labs
Keywords: Image Classification, Weapon Detection, TensorFlow, Social Network Analysis

Abstract

Police analysts are faced with a deluge of data when monitoring the activities in specific areas of social networks and other internet data sources. Image recognition can help to prioritize the reading and subsequent analysis. The paper presents a case study for weapon detection in image data that has the potential to reduce the workload of the analyst by a factor of 200. 

 

 

Published
2018-10-26
How to Cite
Elsner, J., Fritz, T., Henke, L., Jarrousse, O., Taing, S., & Uhlenbrock, M. (2018). Automatic Weapon Detection in Social Media Image Data using a Two-Pass Convolutional Neural Network. European Law Enforcement Research Bulletin, (4 SCE), 61-65. Retrieved from https://bulletin.cepol.europa.eu/index.php/bulletin/article/view/323
Issue
No 4 SCE (2019): Innovations in Law Enforcement - Implications for practice, education and civil society (Special Conference Edition)
Section
Conference Contribution
Creative Commons License

This work is licensed under a Creative Commons Attribution-NonCommercial-NoDerivatives 4.0 International License.

The copyright of individual articles are with the author(s) and CEPOL. Reproduction without alterations is authorised for non-commercial purposes, provided the source is acknowledged.