Skip to content
New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

How to use flandmark_simple_example on new dataset [MATLAB] #60

Open
wants to merge 17 commits into
base: develop
Choose a base branch
from

Conversation

DanielSan1234
Copy link

I would use flandmark_simple_example on my dataset. I have the images jpg in my dataset, but I don't have the .det. Is it possible obtain automaticaly the files .det by the images .jpg?

uricamic and others added 8 commits November 4, 2015 15:17
Python interface (minimal version)
Python Interface - examplary usage (ipython notebook)
python interface mac os
Multi-view learning scripts for MATLAB (initial version, not checked compeltely yet)
@uricamic
Copy link
Owner

Hi @DanielSan1234,

sure, you can use e.g. the Viola-Jones face detector to obtain the face boxes (see http://www.mathworks.com/help/vision/ref/vision.cascadeobjectdetector-class.html), just bear in mind that the format of face bbox for CLandmark is [x_min, y_min, x_max, y_max] unlike the MATLAB face detector which has [x, y, width, height].

@DanielSan1234
Copy link
Author

Hi @uricamic,

thank you for response!

uricamic and others added 9 commits July 25, 2016 09:11
Paper2cite changed to more relevant IMAVIS paper.
Windows batch scripts added to make the compilation and installation
easy on Windows platform. Tested on Windows 10 64bit, MATLAB interface
with MATLAB 2015b, and Python interface with Python 2.7 from Anaconda
64bit
Minor changes in the C++ library (elimination of warnings for new compilers)
Update of build scripts for successful build on Windows 10 + Visual Studio 2017 + Anaconda
New Python example for jointmv models
Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment
Labels
None yet
Projects
None yet
Development

Successfully merging this pull request may close these issues.

4 participants