Proposal of shoplifting prevention service using image analysis and ERP check

In this paper, we propose a software‐as‐a‐service application that prevents shoplifting using image analysis and enterprise resource planning (ERP). In Japan, the total damage due to shoplifting has reached ¥450 billion per year, and each year more than 1000 small book stores give up their business because of shoplifting damage. Based on the recent advancement in cloud technology and data analysis technology, we propose a shoplifting prevention service with the image analysis of security camera movie and ERP data check for small shops. We also confirm the precision ratio of security camera stream movie analysis using the online machine learning framework Jubatus. © 2017 Institute of Electrical Engineers of Japan. Published by John Wiley & Sons, Inc.