Projects

An algorithm to recognize dead and live cells in yeast images

Type A set of scripts
TECHNOLOGIES OpenCV, Python
AREAS OF EXPERTISE Image processing, mapping, Computer Vision Technologies
TEAM 1 developer

This project started as an idea of our client who has a private brewery. He wanted to use a modern solution to optimize the workflow. His idea was related to cell analysis using a microscope. The primary use of microscopes in the brewery and cell counts is that they are useful for determining pitching rate, remaining cell density when bottling beer and determining yeast densities in yeast sediment. Doing this process manually, without an algorithm can take from 30 minutes to an hour. So, client needed an algorithm to recognize dead and live cells.

Challenges

Our main challenge with this project was to perform cell recognition in order to understand how many of them are dead and how many are alive. 

Solutions

We have developed a script, that receives microscope images as input and marks dead cells on them. As an output, the script returns images with marked cells on them

Results

Business value

By using an algorithm for this task and not doing this process manually you can save an hour a day of your worker. And if we assume that the average working day lasts 8 hours, we’ve successfully saved 12,5% of an average business day.

AR Office application
AR Office application
An ML based solution for photo processing
An ML based solution for photo processing