The ancient Egyptians knew a lot about vivisection and could distinguish the liver from the kidney by touch. Swaddling mummies from morning to evening and doing medical treatment (from trepanation to removal of tumors), you will inevitably learn to understand anatomy.
The richness of anatomical details was more than offset by the confusion with understanding the function of organs. Priests, physicians, and common people boldly placed the mind in the heart, and the brain was assigned the role of producing nasal mucus.
After 4 years, it's hard to afford to laugh at the fellahs and pharaohs - our computers and data collection algorithms look cooler than papyrus scrolls, and the brain still mysteriously produces who knows what.
So in this article it was supposed to talk about the fact that emotion recognition algorithms reached the speed of mirror neurons in interpreting the signals of the interlocutor, when it suddenly turned out that the nerve cells were not what they seem.
Decision errors
In childhood, a child follows the faces of his parents and learns to reproduce a smile, anger, complacency and other emotions, so that throughout his life in different situations he smiles, frowns, gets angry - just like his relatives did.
Many researchers believe that the imitation of emotions is built by a system of mirror neurons. However, some scientists express skepticism about this theory: we do not yet understand the function of all brain cells.
The brain model stands on the shaky ground of hypotheses. There is no doubt about only one thing: the "firmware" of the gray matter from birth contains features and bugs, or, rather, features that affect behavior.
Mirror or other neurons are responsible for the imitative response, this system works only at a basic level of recognition of the simplest intentions and actions. This is enough for a child, but damn little for an adult.
We know that emotions largely depend on the acquired experience of a person's interaction with his native culture. Nobody thinks you're a psychopathif among cheerful people you will smile, feeling pain, because in adulthood emotions are used as a means of adapting to the conditions of existence.
We don't know what the other person is really thinking. Making assumptions is easy: he smiles, it means he's having fun. The mind has an innate property to erect castles in the air of consistent pictures of what is happening.
One has only to try to determine how the existing assumptions correspond to the truth, how the shaky ground of hypotheses will begin to move: a smile - sadness, a frown - happiness, a trembling of the eyelids - pleasure.
The German psychiatrist Franz Karl MΓΌller-Lyer in 1889 showed a geometric-optical illusion associated with a distortion in the perception of lines and figures. The illusion is that the segment framed by the outward-facing tips appears to be shorter than the segment framed by the tails. In fact, the length of both segments is the same.
The psychiatrist also drew attention to the fact that the contemplator of the illusion, even after measuring the lines and listening to the explanation of the neurological background of the perception of the image, continues to consider one line shorter than the other. It is also interesting that this illusion does not look the same for everyone - there are people who are less susceptible to it.
Psychologist Daniel Kahneman that our slow analytical mind recognizes the Mueller-Lyer trick, but the second part of the mind, which is responsible for the cognitive reflex, automatically and almost instantly responds to the stimulus that arises, and makes erroneous judgments.
A cognitive error is not just a mistake. You can understand and admit that when looking at an optical illusion, you cannot trust your eyes, but communicating with real people is like traveling through an intricate maze.
As early as 1906, the sociologist William Sumner proclaimed the universality of natural selection and the struggle for existence, transferring the principles of animal existence to human society. In his opinion, people united in groups elevate their own group by refusing to analyze facts that threaten the integrity of the community.
Psychologist Richard Nisbett "Telling more than we can know: Verbal reports on mental processes" demonstrates people's reluctance to believe statistics and other generally accepted data that are not consistent with their existing beliefs.
The Magic of Big Numbers
Watch this video and see how the actor's expression changes.
The mind quickly βputs labelsβ and builds assumptions in the face of insufficient data, which leads to paradoxical effects, which are clearly visible in the experiment conducted by director Lev Kuleshov.
In 1929, he shot close-ups of an actor, a plate filled with soup, a child in a coffin, a young girl on a sofa. Then the film with the actor's plan was cut into three parts and glued separately with frames showing a bowl of soup, a child and a girl.
Independently of each other, viewers come to the conclusion that in the first fragment the hero is hungry, in the second fragment he is saddened by the death of a child, in the third fragment he is fascinated by the girl lying on the sofa.
In reality, the expression on the actor's face does not change in all cases.
And if you saw a hundred frames, would the catch be revealed?
Based on data on the statistical validity of the truth of non-verbal behavior in large groups of people, psychologist Paul Ekman a comprehensive tool for objective measurement of facial movements - "facial movement coding system".
He is of the opinion that artificial neural networks can be used to automatically analyze people's facial expressions. Despite significant criticism (Ekman's airport security program controlled trials), there is a grain of common sense in these arguments.
Looking at one smiling person, one can assume that he is deceiving, and in fact he is up to no good. But if you (or the camera) see a hundred people smiling, chances are most of them are actually having funβlike watching a stand-up comedian perform.
In the example of large numbers, it is not so important that some people are able to manipulate emotions so cleverly that even Professor Ekman will be fooled. In the words of risk expert Nassim Taleb, the antifragility of a system is greatly enhanced when a cold, unbiased camera becomes the subject of observation.
Yes, we do not know how to recognize a lie in the face - with or without artificial intelligence. But we understand perfectly well how to determine the level of happiness for a hundred or more people.
Emotion recognition for business
The simplest way to determine emotions from a face image is based on the classification of key points, the coordinates of which can be obtained using various algorithms. Usually, several dozen points are marked, tying them to the position of the eyebrows, eyes, lips, nose, jaw, which allows you to capture facial expressions.
Evaluation of the emotional background using machine algorithms is already helping retailers integrate online into offline as much as possible. The technology allows you to evaluate the effectiveness of advertising and marketing campaigns, determine the quality of customer service and service, as well as identify abnormal behavior of people.
Using algorithms, you can track the emotional state of employees in the office (an office with sad people is an office of low motivation, despondency and decay) and the "happiness index" of employees and customers at the entrance and exit.
Alfa-Bank in several branches a pilot project to analyze customer emotions in real time. The algorithms build an integral indicator of customer satisfaction, identify trends in the change in the emotional perception of a branch visit, and give an overall assessment of the visit.
At Microsoft about testing the system for analyzing the emotional state of the audience in the cinema (an objective assessment of the quality of the film in real time), as well as to determine the winner in the nomination "Audience Award" at the Imagine Cup competition (the team whose performance the audience reacted to most positively won) .
All of the above is just the beginning of an entirely new era. At North Carolina State University, students' faces were filmed by a camera during their educational courses. computer vision system that recognizes emotions. Based on the data obtained, the teachers modified the teaching strategy.
In the educational process, in general, not enough attention is paid to the assessment of emotions. But you can evaluate the quality of teaching, student involvement, identify negative emotions, and plan the educational process based on the information received.
Face Recognition Ivideon: demographics and emotions
Now a report on emotions has appeared in our system.
A separate field "Emotion" appeared on the face detection event cards, and a new type of reports is available on the "Reports" tab in the "Faces" section - by hours and by days:
It is possible to upload the initial data of all detections and generate your own reports based on them.
Until recently, all emotion recognition systems operated at the level of experimental projects that were tested with caution. The cost of such pilots was very high.
We want to make analytics a part of the familiar world of services and devices, so from today "emotions" are available to all Ivideon customers. We do not introduce a special tariff plan, we do not provide special cameras and in every possible way we level all possible barriers. Tariffs remain unchanged, everyone can connect the analysis of emotions along with face recognition for 1 rubles. per month.
The service is presented in user. And on we have collected even more interesting facts about the Ivideon face recognition system.
Source: habr.com