We are SYNTHETICA

We encounter industrial problems with computer vision.

Our tools? Synthetic datasets, Artificial Intelligence and our experienced team.

Learn more
About Us

The SYNTHETICA project

Artificial Intelligence applications, based on Machine Learning methods, are widely accepted as promising technologies in manufacturing and are successfully used in many computer-vision tasks in manufacturing.  These state-of-the-art techniques are requiring large volumes of annotated datasets for training.  However, such an approach is expensive, prone to errors and labor as well as time intensive, especially in highly complex and dynamic production environments. Synthetic datasets can be utilized for accelerating the training phase of DL by creating suitable training datasets. The SYNTHETICA project has developed a framework for generating datasets and deploying them for AI model training with main purpose the encounter of industrial vision problems in the factory.

SYNTHETICA has already applied this new paradigm in two industrial computer-vision pilot cases: a) aluminum profiles detection with ALUMINCO and ii) feature recognition of one-of-a-kind 3D printed parts with Prima Additive.

OUR PILOTS

Automated vision-based measurement of aluminum profiles in baskets.

Learn more

Vision based feature recognition of metal printed objects for post processing tasks.

Learn more
Our Services

What do we offer?

SYNTHETICA is a team, ready to examine, structure and implement computer vision solutions to your industrial problem. With a manufacturing expertise needed for software integration in industrial sites, SYNTHETICA finds solutions that work and are cost-effective.

Image classification
    Image classification

    Image classification is the task of assigning a label or class to an entire image. Images are expected to have only one class for each image. In image classification problems, we are not interested in how many objects do we recognize, but in classifying them among certain, given categories.

    Object Recognition
      Object Recognition

      More versatile than Image classification, Object recognition is focused on localizing objects in an image, while also classifying them to certain categories. The localization feature of object recognition serves for many purposes, such as counting objects, creating sequences and linking them with their real-world coordinates for collaboration with other processes (e.g., robotic arm picking, AR/VR and post processing tasks).

      Special features recognition and custom solutions
        Special features recognition and custom solutions

        Aside from the basic computer vision applications, the SYNTEHTICA team is ready to adapt computer vision solutions to your needs, offering a great variety of features to be recognized and compliance with external software.

        Data generation
          Data generation

          Do you need to develop your own solution but you lack the necessary data? SYNTHETICA may create any kind of image-related data for your needs and offer them regardless of use.

          Support
            Support

            Do you need assistance in developing your own solution? SYNTHETICA support team provides support, consultancy and investigation of potential expansion on your current AI implementations. We guide you and help you customize your solutions.

            news & Events
            SYNTHETICA’s Teaser Release
            EIT-M article publication
            SYNTHETICA’s Teaser Release
            SYNTHETICA’s Teaser Release
            EIT-M article publication

            Discover the essence of innovation with SYNTHETICA’s teaser.

            Immerse yourself in our vision for the future and experience the blend of innovation and precision that SYNTHETICA brings to manufacturing.

            Watch our Teaser

            Explore the latest endorsement of our project, EIT-M has featured an insightful article on our innovative endeavors. Click the button below to explore the featured article.

            Read EIT-Manufacturing’s Article
            CONSORTIUM