ZEISS industrial CT scan showing internal defects in a cast metal component with color-coded porosity.

Artificial intelligence in x-ray technology

ZADD Segmentation

Name: ZADD Segmentation
Brand: ZEISS

AI-based defect inspection for computed tomography

The app ZADD Segmentation transforms the analysis of 3D X-ray data with AI-based automated inspection. ZADD – an acronym for ZEISS Automated Defect Detection – detects small and fuzzy defects in components reliably and quickly even on poor image quality. Defects and abnormalities are detected, segmented and evaluated using AI algorithms. Seamlessly integrated into your ZEISS INSPECT X-Ray workflow, it leverages pre-trained or customized AI models – for maximum efficiency, reliability, and scalable solutions.

Start now

Seamlessly integrate AI into your quality processes

Adaptable solutions for diverse industrial applications

Engineers reviewing 3D CT measurement data on a ZEISS METROTOM industrial CT scanner for quality inspection.

Robust solutions even for demanding inspection tasks

To be able to do continuous process monitoring and sort out defective components in a value chain at an early stage, the 3D data must be evaluated reliably and quickly. However, CT data is often affected by noise and artifacts, which makes reliable defect detection difficult. Traditional software reaches its limits here. ZADD Segmentation offers the solution: Seamlessly integrated into your workflow with ZEISS INSPECT X-Ray, the app detects defects at a human level and solves previously unsolvable tasks. Develop your solutions quickly and reliably – without any AI expertise. Pre-trained or customized AI models make AI accessible and efficient. Experience precision and speed in combination like never before.

Three-dimensional visualizations showing internal defects and volume particles in components analyzed with ZADD Segmentation.

Versatile applications for different industry requirements

ZADD Segmentation supports demanding quality standards, for example in the automotive, electronics, and medical industries. Hidden defects that pose a risk to component stability and functionality are detected early on using industrial computed tomography and AI. Automated defect detection with ZADD Segmentation is fast and reliable, even on poor image quality with artifacts. Additionally, automated volume inspection enables precise measurement of fill levels, such as powder in inhalers. It can also be used to inspect complex assemblies for completeness or to analyze solder joints in electronic components to detect gas inclusions or other defects.

    
          How ZADD Segmentation works​
        
    Good part or bad part? ZEISS Automated Defect Detection (ZADD) supports this decision with Artificial Intelligence. Complete your evaluation with the ZADD Segmentation app for ZEISS INSPECT X-Ray. Watch this video to see how it works on the example of a casting part.

Third-party Content Blocked

The video player is blocked due to your cookie preferences. To change the settings and play the video, please click the button below and consent to use of "Functional" tracking technologies.

Please note that our software is now called ZEISS INSPECT X-Ray

Leverage efficiency through AI

Three examples of how AI speeds up inspection

From 8 to ~2 hours

The inspection process of stator hairpin welds can in certain cases be reduced by a quarter – from around 8 hours to less than 2 hours – by switching from a manual process using microscopy to AI-supported inspection using CT. The non-destructive process is stable and nearly achieves process speed.

~10 times faster

The inspection of medical implants can be made approximately ten times faster by switching from traditional methods to automated AI-supported image analysis. For example ZADD Segmentation can detect over 900 small defects in a component within five minutes in certain use cases – and with an optimized setup, even in less than a minute.

Reduced cycle time by ~75%

Cycle time for inspecting castings can be reduced by up to 75% in specific use cases when leveraging a pre-trained AI model, compared to manual analysis performed by a human.

Quick and easy start with pre-trained AI models for a wide range of applications

ZADD Segmentation offers pre-trained AI models that deliver impressive results in a variety of application areas.

3D CT visualization of internal defects and porosity in a casting part analyzed with a pre-trained AI model from ZEISS.

Casting inspection

The casting model automatically detects porosities and internal defects caused, for example, by cavities. It ensures high-quality results and can be adapted to similar materials.

3D CT image of an EV stator showing porosities in hairpin welding heads in red analyzed with a pre-trained AI model from ZEISS.

Hairpin inspection in stators

The hairpin model detects enclosed porosities in welding heads of electric motor stators and can be used flexibly for different stator sizes – no prior alignment or precise mesh representation required.

Industrial CT image of a medical inhaler with powder levels in blister packs analyzed with a pre-trained AI model from ZEISS.

Filling level measurement

This AI model detects different volumes in components, such as powder levels in blister packs for inhalers, and enables non-destructive filling level control.

Abstract geometric icon with octagonal network design representing ZEISS AI models that can be trained for specific applications.

Your application

Pre-trained AI models are continuously developed and expanded. To create AI models tailored to your individual needs, simply book our AI model training service.

Highest accuracy and performance

Find nearly all relevant defects with confidence, even with demanding defect specifications. Excellent performance in shopfloor inspection tasks.
Speed through automation

AI-powered high-throughput inspection automates repetitive tasks, reduces the need for manual labor and personnel, and enables inline inspections.
Reliability and a strong partner

Our proven solutions and many years of expertise ensure your process stability under demanding conditions – already successfully in use by industrial customers.
Integration end-to-end

ZADD Segmentation integrates seamlessly into your workflows and offers an end-to-end process – all from a single provider.
Flexibility – no AI expertise needed

The choice is yours: whether you opt for a pre-trained AI model or a customized solution tailored by our service, you don't need any AI expertise.
Easy collaboration

Efficiently prepare your AI model training data and collaborate seamlessly with our AI model training service.

Workflow

Data aquisition

Use our CT portfolio for data acquisition, e.g. the high-power ZEISS VoluMax 9 titan or the high-precision ZEISS METROTOM series for state-of-the-art computed tomography measurements
Segmentation

Find defective areas in the acquired data using Deep Machine Learning (ML) with ZADD Segmentation
Particularly well suited for defect analysis with suboptimal volume data (e.g. due to noise, coarse resolution or artifacts)
Learn from examples, no complicated parameter-tuning is necessary
Use pre-trained ML models to get started quickly
Create regions of interest (ROIs) for time-optimized evaluations
Evaluation

Visualize your data with powerful tools in 3D and 2D
Determine metrics for the detected defects, like diameter, volume or sphericity
Create filters to select defects with a property above or below a given threshold
Make use of complex evaluations like P202, P203, porosity or distance-to-surface
Reporting and statistics

Evaluation in illustrative measurement reports
Easy transfer of measurement reports in PDF format
Archiving the data enables long-term tracking of defects
Advanced evaluation and statistical functions with ZEISS PiWeb Reporting Plus
The statistical process control enables the recognition of process correlations and optimizations

Get started now with ZADD Segmentation

FREE DEMO
Contact us for a personal demo

Ready to start? Our service will accompany you from the beginning whether selecting the right ML model or developing a specially trained solution. We support you in the operation, optimization and evaluation performance of the system and solve your individual inspection tasks in many cases.

Request now
Try for free
Experience the app for 30 days

Discover the full potential with a free 30-day trial. Explore the app’s powerful features and see how it can transform your quality assurance processes.

Get a free trial

To use the ZADD Segmentation app, you need a ZEISS INSPECT X-Ray Pro license with the Advanced X-Ray Defect Detection app.
Sure! There is a 30 day free trial. Simply get a trial here.
AI offers flexibility and adaptability, avoiding overfitting that is common in traditional solutions. It continuously improves and adapts to new challenges, ensuring long-term efficiency and performance.
Yes, AI can be used in regulated domains. Models are optimized, undergo regulatory approval, and are frozen for use. Model behavior is fully traceable, ensuring consistent results when the same model is applied to identical datasets.

Contact us

Would you like to learn more about our products or services? We are happy to provide you with more information or a demo – from remote or onsite.

ZEISS Quality Software Store

Easily order software and apps

ZEISS Metrology Portal

Your digital access point to all metrology services

ZEISS Academy Metrology

Your individual metrology training

ZEISS Quality Tech Guide

Your online help that provides technical information about ZEISS Quality Software

Get in touch

Request a quote, your software demo or contact our service and support now

Form is loading...

Next Step:

Interest Inquiry
Personal Details
Company Details

If you want to have more information on data processing at ZEISS please refer to our data privacy notice.

ZADD Segmentation

Seamlessly integrate AI into your quality processes

Robust solutions even for demanding inspection tasks

Versatile applications for different industry requirements

How ZADD Segmentation works