Non-Destructive Inspection

The Non-Destructive Inspection component is a collection of software tools related to computer vision analysis. The Non-Destructive Inspection – Computer Vision Suite spans from traditional techniques to contemporary innovation, while embracing the design-time and the run-time concepts. This opens the possibility of designing complex computer vision algorithms exploiting image processing techniques and tools and deploying them to a production line.


  • Easy development of complex Computer Vision algorithms

  • Visual debugging tools for easier development and testing

  • Modular approach to have flexible, extensible, and optimized functionalities

  • Easy implementation of complex Deep Learning / Neural Networks models

  • Real-time and historical processing of images

Play Video
Play Video


The feature allows developers to visually build complex Computer Vision algorithms using atomic functions. Developers can connect multiple functions to create an algorithm and utilize graphic tools for testing and debugging. The Designer offers debugging tools, such as the Object Dumper, which displays output parameters of each function, facilitating fast and reliable development.


The component executes the algorithms created in the Designer at run-time. It can process real-time or historic data from cameras, enabling the algorithm to analyze and extract insights from the visual input. The results of the algorithm can be published in the Service & Message Bus, facilitating integration with other ZDMP Components.

Modular Architecture

The Computer Vision component is designed with a modular approach. Each module contains a list of functions that run specific algorithms and have custom dependencies. The Designer showcases the available modules and functions, providing flexibility and allowing developers to choose the desired modules based on their specific use case.

AI Image Classification (AIC) and Labelling (AIL)

The AIC tool allows the correct classification of images into different classes using AI models. Users can train the models on labelled datasets and perform inference on new images. The AIL tool helps create datasets, annotate images, and train neural networks for object detection tasks. Users can create projects, upload images, generate structures, and annotate images directly using the labelling tool.

Additional resources

Learn more about i4FS by visting the project website for general information, the wiki for information about the core components, the Technical Manual for API documentation, and downloading the repository’s source code.

Training Academy

Get a better understanding of the global architecture and information flow.

Source code

Our source code is opensource and available on our Gitlab repository.

Software Documentation

Read our easy to follow documentation to learn how to use the i4 Components.