This tutorial will introduce how to analyze images in Python, mainly using scikit-image. We hope students leave with the ability to:
- Understand a general workflow for analyzing images
- Anticipate and avoid some of the most common pitfalls in image analysis
- Build intuition around the tradeoffs inherent in analytical choices
- Feel comfortable and confident working with current Python-based tools for image analysis
- Have better conversations with their collaborators
- Know where to find additional information and assistance
We'll cover the basics of how to:
- Pre-process data using filtering, binarization and segmentation techniques
- Inspect, count and measure attributes of objects and regions of interest in the data
- Visualize 2D and 3D data using napari
The workshop consists of explanatory discussions interspersed with hands-on exercises. We strongly encourage you to bring a laptop with all required packages installed in order to fully participate. Please follow the instructions here
The course is intended for those who have basic familiarity with Python (e.g., at the level covered in a software carpentry workshop). Basic familiarity with the Jupyter notebooks and the command line is helpful but not required.
We recommend the following introductory materials:
- Python: Software Carpentry workshop on "Plotting and Programming in Python"
- Python: Codecademy Python3 course (free with trial).
- Command line: Codecademy command line course (free with trial).
- Jupyter notebooks: Coderefinery Jupyter workshop.
This course is an adaptation of one originally developed for the 2019 imageXD workshop using material from the scikit-image tutorials. We gratefully acknowledge the work of the original authors of the course material, particularly: Alexandre de Siqueira, Daniela Ushizima, and Stefan van der Walt.
This course was first taught during one day of a CZI-sponsored workshop in Chicago, IL on October 18, 2019.
We warmly welcome and encourage members of the scientific community to submit updates and improvements through github.
We adhere to the license of the original materials: CC0 1.0 Universal
For questions, please contact Nicholas Sofroniew.