AI-Based Facial Recognition Software for Employee Monitoring
About Our Client
The Client is an Australian subsidiary of an international chain of convenience stores.
Challenge
The Client had difficulty in monitoring employee time and attendance, as do most large companies. The Client’s stores were equipped with CCTV cameras for monitoring employees and detecting unauthorized activity. However, the existing monitoring system was limited in functionality and often misidentified people.
Solution
To improve and simplify employee time tracking, ScienceSoft enhanced the existing solution by introducing image analysis algorithms.
Also, the existing CCTV camera sets were replaced with the system-on-chip devices powered by the Snapdragon 410/410E processors that had strong embedded radio modules and ability to process high-definition multimedia files. This enabled seamless connection between the cameras and the central server, and ensured a good quality of the recorded video.
Upon recognize a face, the system automatically captured employee clock in/out time and delivered data to the time & attendance monitoring system. When a camera identified a new face, it took a picture and transmitted it to the server. The users who had access to the server marked the picture with an employee’s name and sends it back to the device.
The Android application gave users access to the settings of each device and any recorded video. Besides, it allowed setting the following camera parameters:
- Recognition accuracy.
- Time intervals between the consecutive camera operations.
- Recognition algorithm.
- Limiting angle of face turn.
- Video quality, etc.
The application also offered Google Maps mode that showed all store locations across the country and floor plan mode that displayed all camera locations within the store. In case a store contained several rooms equipped with cameras, each room was assigned a separate floor plan. The number of rooms was not limited.
Results
ScienceSoft’s team delivered custom software based on image analysis algorithms, successfully integrated it with the Client’s ERP and provided comprehensive supporting documentation. The new software solution increased the efficiency of employee monitoring and reduced the direct involvement of managers in the process. We continued to maintain and support the implemented software.
Technologies and Tools
ASP.NET MVC, ASP.NET Web API, .NET Framework 4.5, Entity Framework, Microsoft Visual Studio, C#, Java, HTML, CSS, Materialize CSS, JavaScript, jQuery, TypeScript. Microsoft SQL Server, Android Studio, Gradle, WebRTC.
