Editing Facial Action Coding System (section)

== Method ==
Using the FACS<ref>{{cite book|title=Encyclopedia of Human Behavior|vauthors=Freitas-Magalhães|date=2012|publisher=Elsevier/Academic Press|isbn=978-0-12-375000-6|veditors=Ramachandran VS|volume=2|location=Oxford|pages=173–183|chapter=Microexpression and macroexpression}}</ref> human coders can manually code nearly any anatomically possible facial expression, deconstructing it into the specific "action units" (AU) and their temporal segments that produced the expression. As AUs are independent of any interpretation, they can be used for any higher order decision making process including [[emotion recognition|recognition of basic emotions]],  or pre-programmed commands for an ambient intelligent environment. The FACS manual is over 500 pages in length and provides the AUs, as well as Ekman's interpretation of their meanings.

The FACS defines AUs,  as contractions or relaxations of one or more muscles. It also defines a number of "action descriptors", which differ from AUs in that the authors of the FACS have not specified the muscular basis for the action and have not distinguished specific behaviors as precisely as they have for the AUs.

For example, the FACS can be used to distinguish two types of [[smile]]s as follows:<ref name="pmid17484588">{{cite journal | vauthors = Del Giudice M, Colle L | title = Differences between children and adults in the recognition of enjoyment smiles | journal = Developmental Psychology | volume = 43 | issue = 3 | pages = 796–803 | date = May 2007 | pmid = 17484588 | doi = 10.1037/0012-1649.43.3.796 }}</ref>
* the insincere and voluntary [[Pan-Am smile]]: contraction of ''[[zygomatic major]]'' alone
* the sincere and involuntary [[Duchenne smile]]: contraction of ''zygomatic major'' and inferior part of ''[[orbicularis oculi]]''.

The FACS is designed to be self-instructional. People can learn the technique from a number of sources including manuals and workshops,<ref>{{Cite web |last=Rosenberg |first=Erika L. |name-list-style=vanc |title=Example and web site of one teaching professional |url=http://www.erikarosenberg.com/FACS.html |url-status=dead |archive-url=https://web.archive.org/web/20090206232546/http://www.erikarosenberg.com/FACS.html |archive-date=2009-02-06 |access-date=2009-02-04}}</ref> and obtain certification through testing.<ref>{{Cite web |title=Facial Action Coding System |url=https://www.paulekman.com/facial-action-coding-system/ |access-date=2019-10-23 |website=Paul Ekman Group |language=en-US}}</ref>

Although the labeling of expressions currently requires trained experts, researchers have had some success in using computers to automatically identify the FACS codes.<ref>[http://www.cs.wpi.edu/~matt/courses/cs563/talks/face_anim/ekman.html Facial Action Coding System.] Retrieved July 21, 2007.</ref> One obstacle to automatic FACS code recognition is a shortage of manually coded ground truth data.<ref>{{Cite arXiv |last1=Song |first1=Juan |last2=Liu |first2=Zhilei |date=10 Mar 2023 |title=Self-supervised Facial Action Unit Detection with Region and Relation Learning |class=cs.CV |eprint=2303.05708 }}</ref>