Skip to main content

Algorithms and tools for stitching microscopy images taken at different focal lengths

Project description

Multifocal Image Stitching

Documentation Build Status
Build Status

This package aims to:

  • Accurately compute translation parameters between two images taken with a translation and focus change
  • Be tolerant of high levels of noise and blurriness caused by the focus change

This package does not:

  • Account for other non-translational camera models
  • Calculate subpixel-level stitching coordinates
  • Perform focus stacking or blending of images in any manner


Matching using low-frequency features:

Matching using high-frequency features:


To install from pypi:

pip install multifocal-stitching


Ensure the images to be stitched are sequentially named in <dir>, then run:

python -m multifocal_stitching <dir>

Most images can be stitched successfully with the default settings. To fine-tune settings with the CLI:

python -m multifocal_stitching -h
usage: [-h] [-v] [--ext EXT] [--imgs IMGS [IMGS ...]] [--no_merge] [--workers WORKERS]
                   [--min_overlap MIN_OVERLAP] [--early_term_thresh EARLY_TERM_THRESH]
                   [--use_wins USE_WINS [USE_WINS ...]] [--peak_cutoff_std PEAK_CUTOFF_STD]
                   [--peaks_dist_threshold PEAKS_DIST_THRESHOLD]
                   [--filter_radii FILTER_RADII [FILTER_RADII ...]]
                   [--stitching_result STITCHING_RESULT] [--result_dir RESULT_DIR]
                   [--resize_factor RESIZE_FACTOR] [--save_gif]

positional arguments:
  dir                   Base directory

  -h, --help            show this help message and exit
  -v, --verbose         Increase output verbosity (default: False)
  --ext EXT             Filename extension of images (default: .jpg)
  --imgs IMGS [IMGS ...]
                        Stitch only provided images in provided order, otherwise will run in batch
                        mode over all images in directory (default: None)
  --no_merge            Disable generating merged images (default: False)
  --workers WORKERS     Number of CPU threads to use in FFT (default: 2)
  --min_overlap MIN_OVERLAP
                        Set lower limit for overlapping region as a fraction of total image area
                        (default: 0.125)
  --early_term_thresh EARLY_TERM_THRESH
                        Stop searching when correlation is above this value (default: 0.7)
  --use_wins USE_WINS [USE_WINS ...]
                        Whether to try using Hanning window (default: (0,))
  --peak_cutoff_std PEAK_CUTOFF_STD
                        Number of standard deviations below max value to use for peak finding
                        (default: 1)
  --peaks_dist_threshold PEAKS_DIST_THRESHOLD
                        Distance to consider as part of same cluster when finding peak centroid
                        (default: 25)
  --filter_radii FILTER_RADII [FILTER_RADII ...]
                        Low-pass filter radii to try, smaller matches coarser/out-of-focus features
                        (default: (100, 50, 20))
  --stitching_result STITCHING_RESULT
                        Stitching result csv file (default: stitching_result.csv)
  --result_dir RESULT_DIR
                        Directory to save merged files (default: merged)
  --resize_factor RESIZE_FACTOR
                        Whether to resize the images saved by a factor (default: 1)
  --save_gif            Whether to save a gif alternating between the merged files (default: False)

Project details

Download files

Download the file for your platform. If you're not sure which to choose, learn more about installing packages.

Source Distribution

multifocal-stitching-0.2.1.tar.gz (11.0 kB view hashes)

Uploaded Source

Built Distribution

multifocal_stitching-0.2.1-py3-none-any.whl (9.8 kB view hashes)

Uploaded Python 3

Supported by

AWS AWS Cloud computing and Security Sponsor Datadog Datadog Monitoring Fastly Fastly CDN Google Google Download Analytics Microsoft Microsoft PSF Sponsor Pingdom Pingdom Monitoring Sentry Sentry Error logging StatusPage StatusPage Status page