Menu

Machine learning for image segmentation, classification and object tracking

We have been developing software for image classification, segmentation and object tracking, based on computer vision and machine learning approaches to data analysis; These algorithms allow one to track individual molecules or cells in large populations over very long periods of time, reconstruct lineages and study cell movement or sub-cellular protein localisation.

In particular, we have developed deep convolutional neural networks for analysing time-lapse microscopy data. Here is an example of automatically segmenting, tracking and classifying cells using deep-learning:


More details can be found at:
http://github.com/quantumjot