Computer Vision : Case Studies

Colonies in Petri Dishes

⚡ Problem:

– Precise identification of various microorganism types from Petri dishes.

– Numerous similarities among different classes of microorganisms.

– No pre-existing solutions were available on the market for such tasks.


For our Client, a Human Stem Cells Lab, the objective was to achieve precise identification of various microorganism types from images of Petri dishes.

No pre-existing solutions were available on the market for such tasks. Consequently, the model needed to be developed from scratch.

The primary challenge was from the numerous similarities among different classes of microorganisms. It was imperative to achieve intelligent recognition to ensure the accurate identification and documentation of various colony types.

The neural network that we created was able to fully achieve this task and provided precise recognition of the types and the colony counts.

Colonies in Petri Dishes
⚙️ Results and Solutions
A database comprising images was created.
Through the utilization of machine learning techniques, an intelligent counting, identification and documentation of various colony types algorithm was completed for a precise recognition of the types and the colony counts.
The processing time for multiple images was reduced from several hours to less than a couple of minutes.
95%

Accuracy rate

Target reached. The model’s precision outperformed human accuracy.
99.9%

Drop of the processing time

From 30 min per image to 0.5 sec
100%

Consistent classification.

Prevent changes in classification interpretations between employees or over time.
Contact us today to schedule a consultation and embark on your journey
to data-driven success.
TRY TRY Contact Contact