Fix the documentation to use bob.ip.facedetect instead of opencv

@andre.anjos the only problem I see here is that in the documentation it says the bounding box is better to be square but bob.ip.facedetect bounding boxes have an aspect ratio of 5:6.

added 1 commit

• 1e2dfe3b - [doc] fix print command for python 3

Compare with previous version

This is how it will look like using facedetect compared the results from opencv: https://www.idiap.ch/software/bob/docs/latest/bob/bob.ip.flandmark/master/plot/show_lena.hires.png

marked as a Work In Progress

Thanks for this update - can we enlarge the bounding box provided by bob.ip.facedetect, say, by 20%? What would be the results then?

added 1 commit

• 45c1e696 - [doc] improve example using bob.ip.facedetect

Compare with previous version

unmarked as a Work In Progress

Ok now the example is working again:

Excellent! Good job.

mentioned in commit 6decf95c

merged