At Embedded World 2025, embedUR Systems collaborated with Infineon Technologies to showcase two unique Edge AI demonstrations, powered solely by the PSOC™ Edge platform. These live demonstrations received a lot of attention for their real-time responsiveness, ultra-low power operation, and practical use cases in both consumer and industrial applications.
Voice-Activated Object Recognition + Recipe Generation
The first demo included wake word detection and real-time item identification. Attendees engaged the Edge AI system with a voice command, which then displayed an image of several ingredients.
The AI identified objects and suggested recipes in real-time on the PSOC™ Edge platform, eliminating the need for cloud-based processing.
This presentation demonstrated the possibilities for intuitive, AI-powered user interfaces in smart home products.
Facial Recognition with Mobile-Based Registration
The second demo showcased a facial recognition use case for mobile onboarding. embedUR created a companion mobile app where people could submit and register their facial profiles. Once registered, the PSOC™ Edge platform detects and recognizes users in real time, conducting AI inference locally on the board. This edge-based authentication solution proved secure, low-latency identity identification for both consumer and industrial devices.
Edge AI Innovation Powered by PSOC™ Edge
Infineon’s PSOC™ Edge family supports AI applications with hardware-accelerated neural network processing, a Cortex®-M55 core with Helium DSP support, and advanced security features. Designed for consumer and industrial applications, the platform offers a seamless AI development experience, allowing developers to create quick, secure, and power-efficient edge solutions.
embedUR systems: Engineering the Edge AI Experience
embedUR systems designed, refined, and deployed demos that integrated real-time speech and vision AI inference on the PSOC™ Edge platform. With significant expertise in embedded software, AI model development and quantification, and real-time systems, embedUR enables businesses to bring high-performance, AI-powered products to market more quickly—without the need for considerable in-house AI programming. For Infineon customers, embedUR provides full-stack technical support, ranging from mobile app integration and AI model tuning to deployment and system-level optimization.
More AI at the Edge: embedUR’s Broader Demo Showcase
In addition to joint demos with Infineon, embedUR demonstrated a wide range of Edge AI applications at their own display, running on several industry-leading AI silicon platforms such as Infineon’s PSOC™ Edge. These examples validated embedUR’s capacity to deliver efficient, high-performance AI on memory-constrained, low-power platforms.
All demo models are available through ModelNova, AI resource hub. Developers can browse a growing library of pre-trained Edge AI models to build fast PoCs. When a model fits the target use case, embedUR offers services to help refine, optimize, and deploy it—accelerating time-to-market. Learn more at modelnova.ai.
Leadership Comments
“Our collaboration with embedUR systems showcases the power of PSOC™ Edge in enabling real-time, power-efficient Edge AI applications,” said Omar Cruz, Senior Manager at Infineon Technologies. “These demos highlight how our platform accelerates intelligent automation for smart home, consumer, and industrial use cases.”
“At embedUR, we’re focused on making Edge AI real—delivering practical, production-ready solutions that run on today’s silicon,” said John Marconi, VP of Technology at embedUR systems. “The work we’ve done on Infineon platforms demonstrates how edge intelligence can be deployed quickly and securely, whether it’s voice-activated control or face-based access—all without relying on the cloud.”
