Dear Monks,
Does anyone know of a way to get a perl-application to do (basic) face-recognition (having a 'corpus' of faces, i'd like to know whether a given face of a person is in that corpus)? There seems to be something like that, using the OpenCV library, in python, but i can't find anything for perl. I'd be happy with some command-line tool that simply spits out some parseable numbers on STDOUT, so i could incorporate it in my perl scripts, but most, if not all, things i found online are basically C(++) libraries, so i'dhave to go the XS route, which i'd really rather not do. Besides, the 'command line API' would have the big benefit that the face recognition would be easily swappable. Additionally, any other kind of trivially usable biometrics-package would be great to know of - fingerprints, speaker/voice recognition, etc.
So, any tips?

thanks,
-schweini

Update: Oh, i meant to ask for something that actually claims to work - there are a lot of projects around that start with "This prject will someday provide...", or "This is pre-alpha software..." and so on. I was looking for somthing at least in a more usable state...

---

---

• Are you posting in the right place? Check out Where do I post X? to know for sure.
• Posts may use any of the Perl Monks Approved HTML tags. Currently these include the following:

  <code> <a> <b> <big> <blockquote> <br /> <dd> <dl> <dt> <em> <font> <h1> <h2> <h3> <h4> <h5> <h6> <hr /> <i> <li> <nbsp> <ol> <p> <small> <strike> <strong> <sub> <sup> <table> <td> <th> <tr> <tt> <u> <ul>

• Snippets of code should be wrapped in <code> tags not <pre> tags. In fact, <pre> tags should generally be avoided. If they must be used, extreme care should be taken to ensure that their contents do not have long lines (<70 chars), in order to prevent horizontal scrolling (and possible janitor intervention).
• Want more info? How to link or How to display code and escape characters are good places to start.