An Israeli start-up says it can take one look at a person’s face and realize character traits that are undetectable to the human eye.

Faception said it’s already signed a contract with a homeland security agency to help identify terrorists. The company said its technology also can be used to identify everything from great poker players to extroverts, pedophiles, geniuses and white collar-criminals. […]

Faception recently showed off its technology at a poker tournament organized by a start-up that shares investors with Faception. […] Two of those four were among the event’s three finalists. To make its prediction Faception analyzed photos of the 50 players against a Faception database of professional poker players.

{ Washington Post | Continue reading }

According to film mythology, the Soviet filmmaker Lev Kuleshov conducted an experiment in which he combined a close-up of an actor’s neutral face with three different emotional contexts: happiness, sadness, and hunger. The viewers of the three film sequences reportedly perceived the actor’s face as expressing an emotion congruent with the given context.

It is not clear, however, whether or not the so-called “Kuleshov effect” really exists. The original film footage is lost and recent attempts at replication have produced either conflicting or unreliable results.

The current paper describes an attempt to replicate Kuleshov’s original experiment using an improved experimental design. In a behavioral and eye tracking study, 36 participants were each presented with 24 film sequences of neutral faces across six emotional conditions. For each film sequence, the participants were asked to evaluate the emotion of the target person in terms of valence, arousal, and category. The participants’ eye movements were recorded throughout.

The results suggest that some sort of Kuleshov effect does in fact exist.

{ Perception | Continue reading }

When leaning forward to kiss to a romantic partner, individuals tend to direct their kiss to the right more often than the left. Studies have consistently demonstrated this kissing asymmetry, although other factors known to influence lateral biases, such as sex or situational context, had yet to be explored. The primary purpose of our study was to investigate if turning direction was consistent between a romantic (parent-parent) and parental (parent-child) kissing context, and secondly, to examine if sex differences influenced turning bias between parent-child kissing partners. […]

The results indicated that the direction of turning bias differed between kissing contexts. A right-turn bias was observed for romantic kissing; a left-turn bias was exhibited for parental kissing. There was no significant difference of turning bias between any parent-child kissing partners. Interpretations for the left-turn bias discuss parental kissing as a learned lateral behavior.

{ Laterality: Asymmetries of Body, Brain and Cognition | Continue reading }

publicity still { Joe Dallesandro and Sylvia Miles in Heat (1972) }

Previous studies have found that facial appearance can predict both the selection and performance of leaders. Little is known about the specific facial features responsible for this relationship, however.

One possible feature is mouth width, which correlates with the propensity for physical combat in primates and could therefore be linked to one’s perceived dominance and achievement of greater social rank. […]

We observed that mouth width correlated with judgments of CEOs’ leadership ability and with a measure of their actual leadership success. Individuals with wider mouths were also more likely to have won U.S. senate, but not gubernatorial, races. Mouth width may therefore be a valid cue to leadership selection and success.

{ Journal of Experimental Social Psychology | Continue reading }

photo { Gregory Crewdson }

In every minute we have hundreds of thousands of body language signals that are pouring out from us and broadcasting how we’re feeling and thinking to everyone around. So even when you manage to control your facial expression consciously, sooner or later what’s called a “micro-expression” is going to flash. And even if it’s as fast as 17 milliseconds, people will catch that because that is how fast people read each others’ facial expressions. So trying to control your facial expressions is not just impossible, it will even backfire. Since the micro-expressions will be incongruent with the main expression, they’ll give the impression that something is not quite right and you can end up seeming fake — which, of course, ruins trust and charisma.

{ Olivia Fox Cabane | Continue reading }

In Experiment 1 (N = 218), where female participants rated male facial attractiveness, the facilitative effect of smiling was present when judging long-term partners but absent for short-term partners. This pattern was observed for East Asians as well as for Europeans. […]

Related to this issue, Morrison et al. (2013) compared the attractiveness of faces displaying the six basic emotions (anger, disgust, fear, happiness, sadness, and surprise). Faces with a happy expression were rated to be more attractive than faces with the other emotions, but they were rated as attractive as neutral ones.

{ Evolutionary Psychology | Continue reading }

related { Transferring the expressions of one person’s face to the other in realtime }

After London’s 2011 riots, the superrecognizers combed through thousands of hours of footage; Collins alone identified an incredible 190 faces among the rioters. Today, Neville heads London’s central forensic image team, which has tested thousands of police officers and identified 152 super-recognizers. These face-spotting stars normally work in their local stations, building up a mental library of the area’s criminals, and periodically attach to New Scotland Yard to solve crimes.

{ National Geographic | Continue reading }

Dr. Jack Berdy has just introduced “Pokertox,” a program of Botox and facial fillers designed to enhance a player’s “poker face,” their ability to hide any sign of facial emotion that might tip off other card players on whether they have a good or bad hand.

{ Huffington Post | Continue reading | Thanks Tim }

photo { Broomberg & Chanarin }

An experimental algorithm out of Facebook’s artificial intelligence lab can recognise people in photographs even when it can’t see their faces. Instead it looks for other unique characteristics like your hairdo, clothing, body shape and pose. […]

The final algorithm was able to recognise individual people’s identities with 83 per cent accuracy.

{ NewScientist | Continue reading }

California-based company Face First is rolling out a system for retailers that it says will “boost sales by recognising high-value customers each time they shop” and send “alerts when known litigious individuals enter any of your locations.”

“What facial recognition allows is a world without anonymity,” says Bedoya. “You walk into a car dealership and the salesman knows your name and how much you make.”

Another company, called Churchix is marketing facial recognition systems for churches. Once the faces of a church’s membership have been added to a database, the system tracks their attendance automatically. It also claims to be able to discern demographic data about the entire congregation, including age and gender.

{ NewScientist | Continue reading }

photo { Aaron McElroy }

The dentolabial smile, where the teeth are seen behind the lips, starts to emerge in the first decades of the 20th century. This is attributed to an increased emphasis of awareness of the body and art of cosmetics due to the evolution of social life and the change in habits and manners. Teeth began to play an increasingly important role as more attention was paid to the face, which exhibited more open and unrestricted emotions.

{ Ronald E. Goldstein, Esthetics in Dentistry | Continue reading | Thanks Tim}

art { Leonardo da Vinci, Lady with an Ermine, 1489–90 }

related { Big brands said to want models with at least 10,000 Instagram followers }

Facebook will soon be able to ID you in any photo

The intention is not to invade the privacy of Facebook’s more than 1.3 billion active users, insists Yann LeCun, a computer scientist at New York University in New York City who directs Facebook’s artificial intelligence research, but rather to protect it. Once DeepFace identifies your face in one of the 400 million new photos that users upload every day, “you will get an alert from Facebook telling you that you appear in the picture,” he explains. “You can then choose to blur out your face from the picture to protect your privacy.” Many people, however, are troubled by the prospect of being identified at all—especially in strangers’ photographs. Facebook is already using the system, although its face-tagging system only reveals to you the identities of your “friends.”

{ Science | Continue reading }

related { Bust detection algorithm }

photo { Rachel Roze }

In the mirror we see our physical selves as we truly are, even though the image might not live up to what we want, or what we once were. But we recognize the image as “self.” In rare instances, however, this reality breaks down. […]

How can the recognition of self in a mirror break down?

There are at least seven main routes to dissolution or distortion of self-image:

1. psychotic disorders
2. dementia
3. right parietal-ish or otherwise right posterior cortical strokes and lesions
4. the ‘strange-face in the mirror’ illusion
5. hypnosis
6. dissociative disorders (e.g., depersonalization, dissociative identity disorder
7. body image issues (e.g., anorexia, body dysmorphic disorder)

{ The Neurocritic | Continue reading }

The strange-face-in-the-mirror illusion […] a never-before-described visual illusion where your own reflection in the mirror seems to become distorted and shifts identity. […] To trigger the illusion you need to stare at your own reflection in a dimly lit room. […] The participant just has to gaze at his or her reflected face within the mirror and usually “after less than a minute, the observer began to perceive the strange-face illusion.”

{ Mind Hacks | Continue reading }

Merely changing the face of a model in an ad increases the number of potential purchasers by as much as 15% (8% on average), according to a study being published by the Institute for Operations Research and the Management Sciences.

{ Informs | Continue reading }

art { Martial Raysse, Life is so complex, 1966 | more }

related { Real-time makeup using projection mapping }

Automatically detecting human social intentions from spoken conversation is an important task for dialogue understanding. Since the social intentions of the speaker may differ from what is perceived by the hearer, systems that analyze human conversations need to be able to extract both the perceived and the intended social meaning.

We investigate this difference between intention and perception by using a spoken corpus of speed-dates in which both the speaker and the listener rated the speaker on flirtatiousness.

Our flirtation- detection system uses prosodic, dialogue, and lexical features to detect a speaker’s intent to flirt with up to 71.5% accuracy.

{ Stanford | PDF }

related { First Impressions Count, But How? }

Major theories propose that spontaneous responding to others’ actions involves mirroring, or direct matching.

Responding to facial expressions is assumed to follow this matching principle: People smile to smiles and frown to frowns.

We demonstrate here that social power fundamentally changes spontaneous facial mimicry of emotional expressions, thereby challenging the direct-matching principle.

{ Journal of Experimental Psychology: General | PDF }

When humans fight hand-to-hand the face is usually the primary target and the bones that suffer the highest rates of fracture are the parts of the skull that exhibit the greatest increase in robusticity during the evolution of basal hominins. These bones are also the most sexually dimorphic parts of the skull in both australopiths and humans. In this review, we suggest that many of the facial features that characterize early hominins evolved to protect the face from injury during fighting with fists. Specifically, the trend towards a more orthognathic face; the bunodont form and expansion of the postcanine teeth; the increased robusticity of the orbit; the increased robusticity of the masticatory system, including the mandibular corpus and condyle, zygoma, and anterior pillars of the maxilla; and the enlarged jaw adductor musculature are traits that may represent protective buttressing of the face.

If the protective buttressing hypothesis is correct, the primary differences in the face of robust versus gracile australopiths may be more a function of differences in mating system than differences in diet as is generally assumed. In this scenario, the evolution of reduced facial robusticity in Homo is associated with the evolution of reduced strength of the upper body and, therefore, with reduced striking power.

The protective buttressing hypothesis provides a functional explanation for the puzzling observation that although humans do not fight by biting our species exhibits pronounced sexual dimorphism in the strength and power of the jaw and neck musculature. The protective buttressing hypothesis is also consistent with observations that modern humans can accurately assess a male’s strength and fighting ability from facial shape and voice quality.

{ Biological Reviews | Continue reading }

It’s a con­cept that had become uni­ver­sally under­stood: humans expe­ri­ence six basic emotions—happiness, sad­ness, anger, fear, dis­gust, and surprise—and use the same set of facial move­ments to express them. What’s more, we can rec­og­nize emo­tions on another’s face, whether that person hails from Boston or Borneo.

The only problem with this con­cept, according to North­eastern Uni­ver­sity Dis­tin­guished Pro­fessor of Psy­chology Lisa Feldman Bar­rett, is that it isn’t true at all.

{ Northeastern | Continue reading }

art { Richard Hamilton, Swingeing London 67 (f), 1968-9 | Acrylic paint, screenprint, paper, aluminium and metalised acetate on canvas }

Previous research has shown that men with higher facial width-to-height ratios (fWHRs) have higher testosterone and are more aggressive, more powerful, and more financially successful. We tested whether they are also more attractive to women in the ecologically valid mating context of speed dating.

Men’s fWHR was positively associated with their perceived dominance, likelihood of being chosen for a second date, and attractiveness to women for short-term, but not long-term, relationships.

{ Psychological Science | PDF }

related { Finger lengths as a key to desirability in romantic couples }

{ When a shopper enters Reebok’s flagship store in New York City, a face-detection system analyzes 10 to 20 frames per second to build a profile of the potential customer. The algorithms can determine a shopper’s gender and age range as well as behavioral and emotional cues, such as interest in a given display (it tracks glances and the amount of time spent standing in one place). Reebok installed the system, called Cara, in May 2013; other companies are following suit. Tesco recently unveiled a technology in the U.K. that triggers digital ads at gas stations tailored to the viewer’s age and gender. | Popular Science | full story }

{ How To Make Your Face (Digitally) Unforgettable | NPR | MIT | PDF }