VFPy

A project supporting extended analyses of ophthalmic Visual Field tests.

Aim

This project aims at automated digitalization of Ophthalmic Visual Field Test results using optical character recognition (OCR). With that, it provides a bases for more extended analyses of those test results.

License

This project is shared under the GPL-3.0 licence.

Basic usage

Set path to tesseract OCR

First specify the path of the tesseract executable

from vfpy.core.utils.ocrutils import set_path_to_tesseract
set_path_to_tesseract(r'absolute_path_to_tesseract\tesseract.exe')

Run OCR

from vfpy.devices import hfa

dcmfile = 'path_to_hfa_dicom_file.dcm'
hfascan = hfa.from_dicom(dcmfile)

hfascan.process()

savedir = 'path_to_savedirectory'
hfascan.save(savedir)

hfascan.close()

Dependencies

This project depends on the following third-party python packages and software

Python packages

1. Pandas (including OpenPyXl and XlsxWriter)
2. Numpy
3. Opencv-python
4. Wand
5. Pytesseract
6. Pydicom

Software

1. Tesseract OCR
2. Ghostscript
3. ImageMagick

Versions

While the project should work with most versions of the above described packages and software, it has been tested with th following versions:

Package/Software	Version
Pandas	0.25.2
OpenPyXl	3.0.0
XlsxWriter	1.2.8
Numpy	1.17.3
Opencv-python	4.1.1.26
Wand	0.4.5
Pytesseract	0.3.0
Pydicom	1.3.0
Tesseract	v5.0.0-alpha.20191010
Ghostscript	9.26
ImageMagick	6.9.3

Contributors

1. Luc van Vught
2. Jan-Willem Beenakker