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

Jens P. Elsner, Thomas Fritz, Laura Henke, Oussama Jarrousse, Stefan Taing, M. Uhlenbrock · European Law Enforcement Research Bulletin · 2019

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.

Read the paper · More papers on PaperTik