Disclaimer: This site and the resources available on it were created for the benefit of Carnegie Mellon University. If you are not affiliated with Carnegie Mellon University, your use of these resources is at your own risk. Carnegie Mellon University makes no warranties, accepts no liability related to its use, and provides no support or guarantee of future availability. By accessing this site, you agree to use the data, source code, and binary files for non-commercial purposes only, and to acknowledge in your publications that they were provided by Professor Takeo Kanade's Cell Image Analysis Group.

Download Source Code

Preconditioning For Phase Contrast Image [download source code]
This source code implements preconditioning for phase contrast microscopy image, which provides two different algorithms for use to choose:
1) preconditioning based on a linear imaging model: The source code implements a restoration method for phase contrast image by understanding its optics. We derive a linear imaging model corresponding to the phase contrast optics and formulate a quadratic optimization function to restore the authentic phase contrast image without halos or shade-off artifacts. With artifacts removed, high quality segmentation can be achieved by simply thresholding the restored images.
2) a modified method based on dictionary representation: we construct a dictionary based on diffraction patterns of phase contrast microscopes. By formulating and solving a min-l1 optimization problem, each pixel is restored into a feature vector corresponding to the dictionary representation. Cells in the images are then segmented by the feature vector clustering.
Requires: Matlab
Phase Contrast Image Restoration Via Dictionary Representation of Diffraction Patterns [pdf]
Understanding the Phase Contrast Optics to Restore Artifact-Free Microscopy Images for Segmentation [pdf]

Image Stabilizer Plugin for ImageJ [download binaries] [download source code]
This plugin stabilizes jittery image stacks using the Lucas-Kanade algorithm. It supports both grayscale and color images.
Download Image_Stabilizer.class and Image_Stabilizer_Log_Applier.class to the plugins folder and restart ImageJ. Alternatively, download and to the plugins folder or subfolder. Compile and run it using Plugins/Compile and Run. Restart ImageJ and there will be a new "Image Stabilizer" command and a new "Image Stabilizer Log Applier" command in the Plugins menu or its submenu.
Requires: ImageJ 1.38q or later & Java Runtime Environment (JRE) 5.0 or later
Copyright (C) 2008-2009 Kang Li. All rights reserved.

Download Data

Cell Image Analysis Archive   []
We developed a website to make available cell image sequences, ground truth data, and our algorithms' results to researchers working on cell image analysis. Using this site, researchers can download either single sequences of images or groups of sequences of images.

Each download file for a single sequence contains:
  1. a sequence of cell images
  2. a xml or text file for the ground truth data
  3. a xml or text file for the result of our algorithms