PyJAMAS documentation

Image analysis has become central for the interpretation and quantification of biological microscopy images. Recent advances in imaging systems and computer hardware have enabled the application of machine learning to the analysis of biological images. Python has emerged as the computer language of choice for machine learning and computer vision. Python is easy to learn for non-computer experts, provides highly optimized numerical packages for machine learning, image processing and analysis, and supports open source development.

PyJAMAS is a Python-based platform for the analysis of microscopy images. PyJAMAS can be used for image processing, object detection—using both machine learning and traditional approaches—, and quantitation of cellular dynamics. PyJAMAS can be extended using plugins written in Python; and the PyJAMAS application programming interface enables the use of PyJAMAS in Python programs and scripts.

Contents:

• Installation
  • The app
  • Using pypi
  • Using virtual environments
• Handling images
• Image annotation
• Image transformations
• Watershed-based image segmentation
• Balloon-based image segmentation
• Object segmentation using linear classifiers
  • Creating training sets
  • Training a classifier
  • Using a classifier
• Object segmentation using deep neural networks
  • Creating training sets
  • Training a U-Net
  • Training a U-Net in Colab
  • Using a U-Net
• Measuring images
  • Measuring individual annotation files
  • Batch measurements
• Using plugins
• Sample plugin
• A more complex plugin
• The PyJAMAS API
  • pjs.io
  • pjs.options
  • pjs.image
  • pjs.classifiers
  • pjs.annotations
  • pjs.measurements
  • pjs.batch
  • pjs.plugins
  • pjs.about
• Citing PyJAMAS
• Sponsors

Indices and tables

• Index

• Module Index

• Search Page