About
Innowise developed a custom face recognition software solution for the retail industry to enhance security and streamline identification processes. Our client is an Australian software development and service provider company specializing in IT solutions for the retail industry. This company has an impressive track record of conceptualizing, designing, developing, and launching a range of innovative retail services catering to various products.
Challenge, approach, and impact
Development of Cutting-Edge Facial Recognition for Retail
Creating a scalable and distributed architecture employing various algorithms for accurate face recognition and face training, with the ability to extract faces from live video feeds for real-time capabilities.
Custom Facial Recognition Software Tailored for Retail Industry
Development of a custom facial recognition software with diverse face recognition algorithms, efficient batch image processing, enhancements for accuracy and performance of images, integration with a Closed-Circuit Television (CCTV) system, and a fully-customizable face recognition system.
DIVERSE FACE RECOGNITION ALGORITHMS
We implemented a collection of face-recognition modules featuring different algorithms, such as Unmanaged Face Recognition PCA, Managed Face Recognition PCA, and Managed Face Recognition Eigenfaces. These modules were seamlessly interchangeable, offering flexibility and adaptability to meet the specific requirements.
EFFICIENT BATCH IMAGE PROCESSING
To simplify image processing tasks, we integrated a batch image processing module. This powerful tool allowed us to extract images from image series, videos, or cameras efficiently. It significantly saved time and effort, enabling smooth operations even when handling large volumes of data.
ENHANCEMENTS FOR ACCURACY AND PERFORMANCE OF IMAGES
We focused on improving the accuracy and performance of our system, particularly for images with inferior quality. By leveraging two OpenCV algorithms for face detection and eye localization, we achieved stable and reliable face detection.
How we built
Testimonials
Anonymous
Innowise Sp. z o.o
“As Business Analyst on this facial recognition project, I'm proud of Innowise's delivery. We tackled inconsistent video quality/lighting challenges, achieving 80% face identification accuracy and 75% faster authentication. Scrum with Jira/Confluence/Teams ensured client alignment. CCTV integration enabled real-time tracking/alerts across retail environments. Transformed security with scalable, robust face training + live extraction. Outstanding computer vision expertise!“
Team structure
Client team
Jack
Project Manager
Daily point of contact
The client stakeholders were working closely with the team at Innowise Sp. z o.o
Agency team
1 x Business Analyst
Production
1 x Project Manager
Production
1 x Data Scientist
Production
1 x QA
Production
