FACER

• Designer: uncredited
• Publisher: FACER
• Players: 2+
• Age:  2+
• Time: 5 minutes
• Amazon affiliate link: https://amzn.to/49YbQTT
• Played with review copy provided by publisher

FACER is a unique card game that turns facial recognition into a fun and strategic challenge. Set in a world where every card features a distinct face, FACER tasks players with identifying similarities between these faces using information from a machine learning algorithm. The result is a game that blends strategy, perception, and a touch of data science in an accessible and engaging way.

In FACER, each card showcases a unique face on the front, while the back provides similarity scores to other cards in the deck. Gameplay is flexible, offering two main modes: Competitive Mode, where players vie to assemble the strongest hand of similar faces, and Cooperative Mode, where players team up to find increasingly similar pairs. Both modes challenge players’ observational skills and strategic thinking.

Whether competing or cooperating, FACER offers a quick-to-learn experience with surprising depth. Players of all ages can enjoy the thrill of discovery while gaining an intuitive understanding of how machine learning works. With endless combinations of faces and strategies, every game is a fresh and exciting puzzle. Ideal for game nights, family gatherings, or casual play, FACER is more than just a game—it’s a journey into the art and science of facial recognition, made fun for everyone.

—

There are a number of different ways to play:

Competitive Mode (Poker): Players compete to build the strongest “hand” based on the similarity of the faces they hold. Think poker, but with faces. The more similar the faces, the stronger the hand. It’s a test of your perception, strategy, and maybe just a little bit of bluffing.  You can choose to play Draw Poker or Stud or even Hold’Em.  Cards are dealt face up to the table in front of each player. When you get to the end of the hand, you arrange your cards in order and then sum the similarity score of the adjacent cards to come up with your final score.

Cooperative Mode (The Mind): Alternatively, players can join forces to find pairs of faces that share varying degrees of similarity. The goal? Work together to create more and more similar pairs and win the game as a team. It’s a subtle exercise in communication, teamwork, and a shared sense of observation.  Each player gets a hand of four cards dealt face up in front of them.  One card is laid in the center of the table.  Any player can play at any time; when a card is played, you look at the correlation score.  Each successive play this round must have a more similar score than the previous. Each player needs to play once per round.  If all players play legally, discard all the cards and deal a new starting card to the table.  If all players can play all their cards, the group wins.

Matcher (Apples to Apples):  Each player has a hand of 5 cards.  The deck is placed in the center and each player tries to play a card from their hand that best matches the top card of the deck.  Once everyone has played, all players now place a betting chip on the card they think is the best match.  Points are scored:  +3 points to the player who played the best match.  +2 points to each player who bet on the correct best match.  +1 point to the player who had the most bets on their card.  Continue to a target score or a fixed number of rounds.

My thoughts on the game

FACER is an interesting idea, more a concept than a game though.  We tried a couple of the different modes, and the cooperative mode seemed to work the best of all of them.  In all of the other forms, it felt like whoever was lucky enough to be dealt a pair or set of cards that were obviously similar just did better.  I have no idea how to run a 512 dimensional array in my brain, so I play FACER like Potter Stewart looked at porn – I know it when I see it.  At least in the cooperative game, you have to make interesting decisions in finding pairs that are on all parts of the familiar spectrum.  But, for everything but the extremes (either very alike or very unalike), I found myself mostly guessing at what the familiarity coefficient would be.

OK, if you’re interested – here is the “scientific explanation”: 

“Analyzing faces might be difficult, but machine learning is here to help. The barcode-like horizontal plots below the faces show the embeddings generated by FaceNet. All values of the 512-dimensional embeddings are min-max normalized to the range of [0, 1] so that the card with the lowest value gets 0 and the card with the highest value gets 1. The scaled values are represented by a linear colormap, where white corresponds to the lowest value and a representative low-luminance color of the image (selected by k-means clustering) denotes the highest value. The shapes (●, ■) represent the first 2 principal components of the embeddings. Faces are grouped into 4 clusters (♠, ♥, ♣, ♦) using agglomerative clustering with cosine distance and average linkage based on the FaceNet embeddings. The values on the backs of the cards are the cosine similarities between the 2 corresponding face embeddings multiplied by 100 and rounded to the nearest integer. The optimal arrangement of your poker hand is actually a solution to an open traveling salesperson problem in a 512-dimensional space. By the way, do the people on the cards exist, or were they just created by generative artificial intelligence?”

Interestingly, if you like the game, you can even make your own deck by uploading your own pictures… 

If you’re a gamer looking for a great game, let’s face it, this isn’t it.  If you’re predisposed to the science behind the game, this can be a neat pickup.  I have donated my copy to a local computer science department at a nearby university, and I bet they’ll enjoy exploring the concepts behind FACER.  It’s probably interesting in that arena… not as much on my game table.

Amazon affiliate link: https://amzn.to/49YbQTT