Vision AI

EMMA uses Artificial Intelligence Technology to raise the efficiency and efficacy of your microbial QC. Welcome to the next level of automation in quality control!

What is vision AI?

Vision AI harnesses the power of artificial intelligence to analyze and interpret visual information, offering valuable insights for microbiologists studying diverse organisms and ecosystems. By leveraging advanced machine learning algorithms, vision AI can identify specific features within images, such as bacteria, color identification, or growth patterns. This technology enablesmicrobiologists to automate time-consuming repetitive tasks, such as image classification or object detection, streamlining data analysis and accelerating quality control processes. Additionally, vision AI facilitates the extraction of meaningful information from large datasets.

Why vision AI?

Traditional computer vision solutions comes with several challenges to efficiently automate image analysis, especially when shape and size of objects differ a lot.

Here’s why machine learning can positively impact computer vision projects:

  • ‍10 x faster image labelling
  • Full traceability & transparency (no black box algorithms)
  • The ability to resolve much complexer use cases
  • No constant retraining is needed
  • Scalable & Robust


At Microtechnix, 2 pre-trained out-of-the-box vision AI models are available for immediate deployment at customers:

  • EMdi assistant: detects colony growth on plates based on a binary classification model
  • EMdi automation: automatically counts colonies on positive plates based on an object detection model


These AI models can, on request, be re-trained with customer specific data to further optimise performance characteristics to match specific customer requirements. Based on a secure cloud platform developed by ML6, we provide a user-friendly environment to label images that can be used to re-train the existing models to perform better for the specific tasks and environments its used for.

Building a representative dataset

Essential in the overall development of a performant vision AI model is the collection of high quality data, subsequent analysis and finally the validation of the data.

The dataset that support the pre-trained models include balanced data buckets from :

  • Negative plates (no colony)
  • Plates containing defects (writing, crack, injection point, etc.)
  • Plates with fogging (light condensation)
  • Positive plates (bacteria present)
  • Positive plates (mold present)


This results in a highly diverse dataset representing a real world environment.

Data Labeling

Data labelling was performed by in-house imaging and microbiology experts to ensure correct labels are applied across the entire dataset. By ensuring microbiology experts and imaging experts agree on the data label, the 4-eyes principle was applied to guarantee the highest quality labelled dataset.

AI training

The developed AI-models were trained on in-house generated representative datasets.

The key performance objectives are:

  • No false negatives
  • <5% false positives
  • Counting accuracy exceeding 98% for Petri dishes with less than 100 CFUs
  • Able to run on a local computer (edge device)





Curated datasets are split into 3 categories:

  • Train
  • Validate
  • Test

To ensure proper evaluation of the AI model performance. A balanced split of data buckets is made, enabling performance validation on large numbers.

How can end users benefit from AI solutions?

Image analysis is a time intensive process and is prone to human errors. Assisted or automated diagnostics enables more accurate analysis at a fraction of the time and cost of traditional methods.

Implementing AI offers various benefits:

  • higher reproducibility
  • reduce human errors by reducing repetitive tasks for collaborators
  • building collective intelligence that is centrally stored
  • scalable across different locations

All benefits above can be realized keeping ALCOA+ principles in mind, ensuring full data integrity.

Product combinations

    Environmental Monitoring



    Membrane filter analysis



    Growth promotion testing



    EMMA HT | high throughput automation & digitization

    Imaging systems

    Imaging systems

    EMMA RL | automate & digitize microbial QC

    Imaging systems

    Imaging systems

    EMMA | digitize microbial QC

    Imaging systems

    Imaging systems


Teach & Read




Transforming microbial quality control

Discover more