Computer vision checkout

Valiance (India) built an AI-powered video intelligence suite on Google Cloud to improve wildlife conservation and civic safety. The platform turns large CCTV and video streams into real-time incident intelligence for public-sector operators.Its flagship products, Wildlife Eye and CivicEye, use custom computer vision models, multimodal data fusion, and intelligent alerting. CivicEye also lets officers query video footage in natural language through Google AI capabilities.

ValiancePublic Sector

Supr Daily, a grocery ordering and delivery service based in Bangalore, serves over 200,000 customers with fresh groceries delivered early morning across six cities.The company faced challenges with manual verification of delivery photos which was slow, error-prone, and led to unnecessary refunds, as well as manual inventory forecasting inefficiencies.To scale and improve, Supr Daily implemented AWS machine learning services: Amazon Rekognition Custom Labels for automated image verification with 95% accuracy and 350 ms latency, and Amazon Forecast for demand forecasting that improved inventory management accuracy by 25%.The solution automated delivery verification in near real-time, reducing manual work and enabling instant feedback to delivery partners to improve photo quality and reduce fraudulent refund claims.Inventory management became simpler and more accurate through automated forecasting and notifications sent to procurement, helping ensure timely stock replenishment.The backend infrastructure is hosted on AWS Elastic Beanstalk to support scalability for millions of customers.Overall, the implementation supports a 70% user growth and enhances partner and customer satisfaction.

Supr DailyRetail

Microsoft Azure Vision Studio is a no-code platform enabling real-time visual inspections, inventory tracking, quality control automation, and enhanced supply chain visibility in retail and logistics.The platform integrates Azure's robust Computer Vision APIs including object detection, optical character recognition (OCR), spatial and facial analysis.Microsoft Azure Vision Studio improves processes such as automated shelf audits, cashierless checkout systems, package scouting, damage detection, vehicle recognition, and shipment tracking.The solution integrates with other Microsoft services like Power BI, Dynamics 365, and Azure IoT to provide business intelligence and operational improvements.

C.H. RobinsonRetail

Lush built Lush Lens, an AI-powered image recognition system, to identify packaging-free products at checkout and reduce manual product entry.The system was integrated with mobile point-of-sale devices so staff can point a camera at products and automatically add items to a customer basket.Google Cloud Vertex AI supports model development, training, and deployment, while Cloud Storage hosts the image library used for training.

LushRetail

Powered by Vertex AI, SAVI (Semi Automated Vision Inspection) is transforming surgical instrument identification and cataloging to reduce missed instruments and manual inspection workload.Johnson & Johnson MedTech worked with Max Kelsen and Google Cloud to build a system that manages tens of thousands of individual devices and their tray characteristics for surgical sets used by surgeons.The solution was piloted in a Queensland distribution center serving over 100 hospitals and then rolled out across Australia, New Zealand, and Japan.

Johnson & Johnson MedTechHealthcare

dnata, a global aviation and cargo service provider based in Singapore, sought to enhance operational efficiency in cargo handling at Changi Airport. The challenges included improving cargo build-up, weight measurement, space loading, and reducing manual paperwork errors. Partnering with SPEEDCARGO and leveraging Microsoft Azure technologies, dnata implemented an AI-driven digital platform incorporating Azure IoT Edge, Azure IoT Hub, Azure Data Lake, and 3D Time-of-Flight camera-based computer vision technology. This system captures real-time cargo dimensions, integrates with dnata's systems, and automates cargo planning and manifest creation, improving capacity utilization and operational accuracy.

dnataLogistics

Arvato, a subsidiary of Bertelsmann, partnered with Microsoft to automate quality control in their logistics operations for Microsoft devices. The company operates international distribution centers for Microsoft device supply chains in the US, Europe, Australia, and Asia, adapting product packaging for different markets and supporting rapid market demands. Previously, quality checks were performed manually, leading to inefficiencies and a higher risk of error. Leveraging Azure Cognitive Services for image recognition, Arvato developed a platform where packaged devices are visually scanned from all angles by five cameras as they move through a tunnel on conveyor belts. Images are uploaded to Azure, where AI models assess packaging integrity and labeling. Results are sent to an SAP-integrated control program (Armada), which then automates sorting of the packages. The system delivers nearly 100% error detection and reduces lead times while enabling consistent, objective quality checks. The platform is designed for scalability across regions and industries, with future applications planned for returns handling and sustainability features.

Simbe Robotics developed 'Tally', an inventory robot using computer vision, RFID, and fixed sensors combined with Google Cloud AI services to improve inventory management, pricing accuracy, and operational efficiency in physical retail stores.The platform aggregates real-time shelf data using AI models deployed on Google Cloud services including Vertex AI, Compute Engine, BigQuery, and Looker for analytics and predictive modeling.Security and compliance are ensured through Cloud Security Command Center and Identity and Access Management, securing sensitive data and maintaining access controls.The solution delivers over 98% on-shelf availability, pricing and promotion accuracy above 90%, a 2% sales lift annually, and a 4x return on investment within 90 days for retailers using the platform.

Simbe RoboticsRetail

Trigo has developed a checkout-free grocery shopping system that digitizes store operations to enable seamless, automated shopping experiences in traditional grocery stores.The solution uses AI computing and 3D modeling from hundreds of cameras to generate real-time, highly accurate 3D models of the store environment and shopper behavior, enabling shoppers to pick items and walk out without checkout.Google Cloud infrastructure components including BigQuery for large-scale data storage and analysis, and Google Kubernetes Engine (GKE) for managing autoscaling microservices provide the scalable, low-latency backend support.The implementation allows Trigo to rapidly transition stores from test to live environments while improving accuracy and operational efficiency.Trigo partners with DoiT International for implementation support and benefit from Google Cloud's global server presence for reduced data latency and reliable, scalable service to stores worldwide.

TrigoRetail