mahdihosseini / foucspath

Dataset for Natural Focus Blurr Assessment in Digital Pathology

FoucsPath

Focus Quality Assessment for Digital Pathology (Microscopy) Images

FocusPath is a dataset compiled from diverse Whole Slide Image (WSI) scans in different focus (z-) levels. Images are naturally blurred by out-of-focus lens provided with GT scores of focus levels. The dataset can be used for No-Reference Focus Quality assessment of Digital Pathology/Microscopy images.

Where to Download?

The downlink for dataset is
[https://drive.google.com/open?id=1TlPszQjwhnlBU6LScKBkUa78eA7oq13X]

More Information

For more information on FocusPath dataset please visit
https://sites.google.com/view/focuspathuoft

FocusPath Specefics

• 864 image patches of 1024x1024 (sRGB) with different out-of-focus levels
• Image patches are cropped across nine (9) different whole slide images
• 16 different Z-levels are used to generate different out-of-focus images
• Tissue slides are selected from diverse color stain information

Related Publication:

Hosseini, Mahdi S., Yueyang Zhang, and Konstantinos N. Plataniotis. "Encoding Visual Sensitivity by MaxPol Convolution Filters for Image Sharpness Assessment." IEEE Transactions on Image Processing (2019).

---

Author:

Mahdi S. Hosseini
Email: [email protected]
http://www.dsp.utoronto.ca/~mhosseini/

---

Citation:

@article{8672094,
author={M. S. {Hosseini} and Y. {Zhang} and K. N. {Plataniotis}},
journal={IEEE Transactions on Image Processing},
title={Encoding Visual Sensitivity by MaxPol Convolution Filters for Image Sharpness Assessment},
year={2019},
volume={28},
number={9},
pages={4510-4525},
doi={10.1109/TIP.2019.2906582},
ISSN={1057-7149},
month={Sep.},
}