List of image databases
Here you can find some databases of microscopic images, click on the database name to view its description.
You can also download some of these databases.
Microscopical Image Database (Serous cytology)
This database contains 10 color microscopic images from serous cytology. A ground truth is also available for each image. Each region of the ground truth region corresponds to a given nucleus and has a specific label. The background has the label one. Figures below illustrate the purpose of the image processing process: the extraction of cellular components (left: original image, center: ground truth, right: segmented image). Please Note that in this segmentation process, cytoplasm is also extracted but is not available in the ground truth.
You can access to this database by the following link. Download the Serous Image Database.
You are free to use the dataset for non-commercial research and educational purposes. In exchange, we request only that you cite our IEEE trans. IP paper:
author={O. Lezoray and H. Cardot},
title={Cooperation of color pixel classification schemes and color watershed :
a study for microscopical images},
journal={IEEE transactions on Image Processing},
volume={11},
year={2002},
pages={783-789},
number={7}
}
Microscopical Image Database (Bronchial cytology)
This database contains 8 color microscopic images from bronchial cytology. A ground truth is also available for each image in three classes (nucleus, cytoplasm, and background pixels). Pixels have a label specifying their classes (2: nucleus, 1: cytoplasm, 0: background). Figures below illustrate the purpose of the image processing process: the classification of pixels (left: original image, center: ground truth, right: segmented image).
You can access to this database by the following link. Download the Bronchial Image Database.
You are free to use the dataset for non-commercial research and educational purposes. In exchange, we request only that you cite our IJRA paper:
author={C. Meurie and O. Lezoray and C. Charrier and A. Elmoataz},
title={Combination of multiple pixel classifiers for microscopic image segmentation},
journal={IJRA (IASTED International Journal of Robotics and Automation)},
volume={20},
year={2005},
pages={63--69},
number={2},
note={Special issue on Colour Image Processing and Analysis for Machine Vision,
ISSN 0826-8185}
}
Microscopical Cell Image Database (Serous cytology)
This database contains about 3900 cells that have been extracted from Microscopical image (Serous cytology). This database has been classified into 18 cellular categories by experts. To a cell is associated two images: a color image and a binary image that indicates the nuclear segmentation.
You can access to this database by the following link. Download the Microscopical Cell Image Database.
You are free to use the dataset for non-commercial research and educational purposes. In exchange, we request only that you cite our MVA paper:
Author = {O. Lezoray and A. Elmoataz and H. Cardot},
Journal = {Machine Vision and Applications},
Pages = {166-171},
Title = {A Color object recognition scheme: application to cellular sorting},
Volume = {14},
Year = {2003}
}