Imaging is one of the most popular data modalities. Our own brain uses visual processing as the primary way to make sense of the world, so there is no surprise humanity invented so many different ways to make still copies of the world - images. Also current deep learning revolution started with Convolutional Neural Networks winning of the biggest image recognition challenges - Imagenet. In this edition of the Data Science Seminar we have invited several specialists that work with images on a daily basis and in very different areas: behaviour analysis, robotics, satellite imagery and microscopy.