Next‑generation inspection systems don’t just classify defects—they record full visual logs, timestamps, and identifiers for comprehensive traceability, enabling analytics, compliance, and root‑cause analysis.

Multispectral and hyperspectral machine vision systems deliver powerful inspection capabilities, but their complexity and cost can be a barrier to their use in cost-sensitive applications. Using two case studies, this talk presents hardware-level strategies for reducing system cost. These real-world applications utilize intelligent camera selection and application-matched LED illumination design.

The first approach consolidates a dual RGB-and SWIR-based machine vision solution, into a single system utilizing a multi-sensor, prism-based CMOS and InGaAs sensor combined with a configurable RGB-SWIR multispectral LED line light. The reduction in camera and emitter count, and associated electrical ancillaries and integration overhead, without sacrificing on performance, significantly improved the Performance-Cost ratio of this machine vision system.

The second approach uses a dual-sensor SWIR camera where each sensor targets a discrete spectral band. By carefully pairing, and strobing, specific wavelengths in the LED source in order to elicit a response to a known, possible material in only one sensor, the system is able to detect foreign material presence or absence without broadband illumination or spectral filtering hardware.

Attendees will leave with practical cost-reduction frameworks and an understanding of the lighting parameters required to implement them.

In this TechTalk, we explore how machine vision enables end-to-end food inspection and automation across the food production chain. Using real-world case studies from agriculture to food inspection, sorting, packaging, and storage, we examine the challenges encountered throughout the pipeline and discuss how industrial cameras help system designers achieve reliable imaging, improved inspection accuracy, and higher throughput in demanding food processing environments.

Join Ron Müller, Seb Dignard, and Joe Gemma in this roundtable that will explore the evolving landscape of machine vision technology amid the rise of humanoid robots. As humanoids integrate advanced sensing, perception, and AI capabilities, these machine vision experts will examine whether traditional machine vision systems face obsolescence or will coexist synergistically. Moderated by Vision Systems Design's Head of Content Sharon Spielman, the panel will discuss challenges and opportunities in accuracy, adaptability, cost and application domains.

Key questions include:

• Can humanoid vision surpass established systems in industrial and commercial sector?
• Will the humanoids in mass-production be cheaper in purchase, integration, and operation?
• How will the interplay between humanoid and traditional vision affect future automation, safety, and human-robot collaboration?

You don't want to miss this dynamic discussion on the future of machine vision.

Manufacturers are under pressure to do more with less—faster production, higher quality, and greater flexibility. AI-powered machine vision is unlocking a new level of factory intelligence by turning visual data and barcode events into actionable insights.

This session demonstrates how organizations are using machine vision and AI to reduce defects, enable real-time traceability, and empower frontline workers with instant decision support. The result: fewer errors, faster throughput, and a connected factory that continuously learns and improves.

Machine vision systems have evolved from complex integrations of lighting, optics, cameras, and software into streamlined smart camera solutions that simplify deployment and reduce cost. More recently, the rise of AI has accelerated adoption but also introduced a growing over-reliance on data-driven decision-making, often at the expense of system-level design.

This presentation examines the progression from traditional vision systems to AI-enabled smart cameras, highlighting the strengths and limitations of each approach. While AI excels in handling variability, it cannot replace the foundational importance of proper lighting, optics, and application-specific tuning.

We propose a balanced approach: augmenting smart cameras with targeted enhancements—such as optimized lighting or purpose-built algorithms—to achieve higher accuracy and repeatability without reintroducing unnecessary complexity. Through practical examples, including inspection verification and OCR, attendees will learn how to combine simplicity with precision to build more robust vision solutions.

Key takeaways
•    When AI is—and isn’t—the right tool
•    Why foundational system design still matters
•    How to improve results with minimal hardware or software additions
•    Practical strategies for verification and OCR applications
•    A framework for balancing simplicity, accuracy, and reliability

In this keynote, Dr. Daniel Lau will deliver a clear, practical comparison of the major 3D imaging technologies used in industrial machine vision. He will examine structured‑light systems, time‑of‑flight cameras, stereo vision, and laser triangulation—outlining how each method captures 3D data and the implications for accuracy, speed, surface coverage, and environmental robustness.

For each technology, he’ll break down core operating principles, critical performance parameters, typical use cases in automation and inspection, and key integration factors such as calibration, lighting, processing demands, and mechanical constraints.

Attendees will gain a grounded understanding of the strengths and limitations of each approach to help them confidently evaluate, specify, and deploy the right 3D vision solution for their application requirements.