Inspection intelligence, in your hands.

It enables food manufacturers to capture production data, build and validate their own inspection models and operate them in production without data-science expertise.

Food quality decisions depend on information about products, materials and processes. But conventional food inspection often captures only part of that information – and adapting inspection to new products or quality requirements can require specialist expertise, calibration and time.

Limited visibility

Relevant product characteristics may be difficult to detect visually – or become visible only after quality has already been lost.

Specialist dependency

Building and adapting advanced inspection models often requires dedicated vision or data-science expertise.

Fragmented Workflows

Data capture, model creation and production inspection are often handled in separate tools, specialist environments and implementation steps.

From sensing to inspection in one system.

Highsensor ONE combines RGB or hyperspectral imaging (HSI) with Highsensor ONE Studio, the software environment that connects data capture, model creation, validation and live inspection.

Choose the sensing technology that fits the application. ONE Studio guides the workflow from capturing data to operating the validated inspection model in production.

See what is visible. Reveal what is not.

RGB and hyperspectral imaging capture different types of information. The right choice depends on what you need to detect, classify or measure in your food production process.

Both imaging technologies are integrated into the same Highsensor ONE Studio workflow.

Same product. Different information.

What would you like to inspect?

Highsensor ONE brings AI-based food inspection to different quality tasks — from visible defect detection and automated grading to spectral and material-property analysis.

Find deviations early.

Detect visible defects, anomalies and unwanted product characteristics during food production.

Examples

  • Visible defects
  • Surface deviations
  • Food anomaly detection
  • Damaged products
  • Unexpected product characteristics

Turn product characteristics into quality decisions.

Use food quality classification and automated grading to assign products to defined classes based on visible or measurable characteristics.

Examples

  • Automated food grading
  • Quality classes
  • Sorting criteria
  • Shape and size characteristics
  • Appearance-based classification

Make material properties measurable.

Use hyperspectral information for validated measurement applications based on spectral and material characteristics.

Application targets

  • Moisture content measurement
  • Dry matter measurement
  • Spectral characteristics
  • Material-property differentiation