I am starting down this road to build a haartraining app for OSX. I have been digging around the web and here is what I have found so far:
svn checkout http://tutorial-haartraining.googlecode.com/svn/trunk/ tutorial-haartraining-read-only
If anyone has some info or guidance
I’m really curious what this is going to be used for More face-recognition things?
There are some good tutorials about that, just I´ve look for one and in the opencv forum and I found a reference to this one that looks simple-and-clear. all that is necessary to create samples and do the training is inside the opencv, and it´s true, there are the source inside this folder_\OpenCV\apps\HaarTraining\src_
Also there are this tool to get directly the samples, any way will be so great implement this tool inside Of.
Hope that helps
So i have been able to compile opencv on osx and creating haarcascade using the opencv executables. The step:
- create positive samples (you can do this many ways - multiple images or a single image)
- create negative sample (these images can not have the object you are tracking in them)
- … some vec/dat things
- build a training file.
I wrote a class using an old face tracking app to be just ofxHaarTracking so that you can just load and track haar files. After awhile of piecing many tutorial together I was able to build a haarcascade.xml file
I think that OF will be a killer part in creating the samples for the training. I want to move onto that next. Ohh man this stuff is fun.
Here is what I have so far. Read about it here. I need to bundle this all up and post.
Really nice work!
I just took a look in O’Reilly’s book about OpenCV, and it got a chapter about face detection and Haar Classifier. Haven’t read it, but looks like it got some theory about how it works, and some samples.
Hey - thats crazy dope!
It would be great to have a haar uploader page where people can post their trained haar files.
love the training pictures too:
this is really great! :shock:
Cool man. Keep up the good work!
Are you going to publish some code? im curios, and It could be so usefully for a lot of people…
Hey Todd, it would be great if you could share code from this project.
Also, Theo: on this page http://gias720.dis.ulpgc.es/Gias/modesto-eng.html there’s a link to a paper that has a great summary of about 20 public domain classifiers (frontal face, profile face, head and shoulders, left, right eye, eye pair, nose, mouth). There are also a few available for download here ftp://mozart.dis.ulpgc.es/pub/Software/HaarClassifiers/FaceFeaturesDetectors.zip
It’s unclear whether those are the ones mentioned in the report, or specially trained classifiers…