Skip to content

Segmentation, validation and annotation of scanned images of museum specimens

License

Notifications You must be signed in to change notification settings

bwprice/inselect

 
 

Repository files navigation

Inselect

Travis status

A tool for the semi-automated segmentation and annotation of scanned images of museum specimen trays.

You can download the latest release of Inselect for Windows, for Mac and the Python source from our Project page.

Windows development environment

  • Install git ;
  • Download the latest build of Anaconda, Python 2.7.x build, and install using default options;
  • Download OpenCV (2.x version) and extract the archive;
  • Copy the file <open cv extract root>/build/python/2.7/x86/cv2.pyd to <anaconda root>/Lib/site-packages (Replace x86 by 64 as appropriate);
  • Get the Inselect source:
git clone https://github.com/NaturalHistoryMuseum/inselect.git
cd inselect
python inselect.py

To build the Windows installer

pip install cx_Freeze
build.bat

The installer will in the dist directory.

OS X development environment

  • Install git ;
  • Download the latest build of Anaconda, Python 2.7.x build, and install using default options ;
  • Install precompiled OpenCV package:
conda install -c https://conda.binstar.org/jjhelmus opencv
  • Install other dependencies:
conda install PySide
  • Get the Inselect source:
git clone https://github.com/NaturalHistoryMuseum/inselect.git
cd inselect
./inselect.py

To build the OS X installer

Install homebrew.

pip install pyinstaller
brew install upx
./build.sh

Ubuntu 12.04-LTS development environment

apt-get install python-pip git python-pyside python-opencv python-numpy python-scipy python-matplotlib python2.7-dev
git clone https://github.com/NaturalHistoryMuseum/inselect.git
cd inselect
./inselect.py

Toolbar icons in the compiled application,

If the toolbar icons in inselect/data change then you need to refresh a Python file:

pyside-rcc icons.qrc > inselect/gui/icons.py

This taken from a stackoverflow thread

License

Inselect is Copyright (c) 2014, The Trustees of the Natural History Museum, London and licensed under the Modified BSD License. See the LICENSE file for more information.

About

Segmentation, validation and annotation of scanned images of museum specimens

Resources

License

Stars

Watchers

Forks

Packages

No packages published

Languages

  • Python 99.5%
  • Shell 0.5%