Python Workshop: Image Processing

Toby Hodges   2016-04-06   Comments Off on Python Workshop: Image Processing

Date/Time
Date(s) - 2016-04-06 - 2016-04-07
09:30 CEST - 12:00 CEST

Location
EMBL Heidelberg - ATC Computer Training Lab

Categories


Description

This is a tutorial to exemplify fundamental concepts of automated image processing and segmentation, using Python.

This course assumes a basic knowledge of the Python Programming Language. For those at EMBL, this means that you have participated in a beginners course for programming, preferably a Python course.

Task

Segmentation of 2D confocal fluorescence microscopy images of a membrane marker in confluent epithel-like cells.

Programming Concepts And Content Discussed In This Tutorial

  • Python scripts, functions
  • Standard variable types: array, dictionaries
  • Control flow
  • Modules, packages, importing modules and packages and using them
  • Importing data
  • Using the documentation
  • Arrays and manipulation (dimensions, indexing, slicing, arithmetic)
  • Visualising images
  • Debugging by printing relevant information and plotting images at appropriate stages
  • Exporting data and writing files

Image Processing Concepts And Content Discussed In This Tutorial

  • Loading and visualising images
  • Images are arrays of numbers; they can be indexed, sliced, etc…
  • Images contain 3 types of information: Intensity, Shape, Size (a good segmentation pipeline uses them all)
  • Preprocessing: smoothing, background substraction
  • Segmentation: adaptive thresholding, distance transformation, detection of maxima, watershed
  • Filtering: Discarding undesired objects, e.g. fused cells
  • Analysis: Extracting measurements from segmentation
  • Saving output (segmentation, data, graphs)
  • Automation (for all files in a directory): demonstration of advantages and example applications of automated image analysis

Tutors: Karin Sasaki (CBM), Jonas Hartman (Gilmour Lab), Kota Miura (ALMCF), Toby Hodges (Bio-IT)

Bookings

This event is fully booked.