U.S. flag

An official website of the United States government, Department of Justice.

NCJRS Virtual Library

The Virtual Library houses over 235,000 criminal justice resources, including all known OJP works.
Click here to search the NCJRS Virtual Library

Classifying crime places by neighborhood visual appearance and police geonarratives: a machine learning approach

NCJ Number
Md Amiruzzaman; Andrew Curtis; Ye Zhao; Suphanut Jamonnak; Xinyue Ye
Date Published
November 2021
25 pages

In this document, the authors examine the linkage of place-based visual imagery to crime with artificial intelligence, by classifying granular scale crime places based on potential connections to activities such as where drugs are purchased, where drug use occurs, and where overdoses will occur most frequently; the authors’ research goal was to improve drug overdose intervention with Project Dawn kits by identifying different overdose locations.


The complex interrelationship between the built environment and social problems is often described but frequently lacks the data and analytical framework to explore the potential of such a relationship in different applications. The authors address this gap using a machine learning (ML) approach to study whether street-level built environment visuals can be used to classify locations with high-crime and lower-crime activities. For training the ML model, the authors used spatialized expert narratives to label different locations. Semantic categories (e.g., road, sky, greenery, etc.) were extracted from Google Street View (GSV) images of those locations through a deep learning image segmentation algorithm. From these, local visual representatives were generated and used to train the classification model. The authors applied the model to two cities in the U.S. to predict the locations as being linked to high crime rates. Results show that the authors’ model can predict high- and lower-crime areas with high accuracies. Publisher Abstract Provided