Human vision has evolved to recognize human figures in all different cases whether it is the real world or art through representations.
The situation becomes a little more complicated when more abstract art forms are involved, such as cubism or surrealism in which the shapes are altered, making their recognition more difficult. If people have proven themselves to have difficulty recognizing a person on a Picasso table, things do not seem to be so simple for computers.
Στο ερώτημα αυτό, στο κατά πόσο δηλαδή ένα πρόγραμμα υπολογιστή μπορεί να αναγνωρίσει ανθρώπινες φιγούρες σε πίνακες ζωγραφικής που εντάσσονται στο κίνημα του κυβισμού προσπάθησαν να απαντήσουν ορισμένοι επιστήμονες του πανεπιστημίου του Μπέρκλι στην California of the USA in their study "Recognizing People in Cubism".
Cubism was one of the most influential movements in 20th century painting, with pioneering painters such as Georges Braque and Pablo Picasso. In the images of the respective panels the figures are presented zigzagged, as if the optics that would have observers from different angles were joined. As a result, a cubic painting contains many fragments of the painter's perception of the same object.
The method followed by researchers their task was to select a list of 218 cubic paintings with titles that indicated they contained human figures. They then asked 18 participants to rate the degree of abstraction in each image, on a scale of 1 to 5, and to draw a rectangle around each person.
Then they turned to their computers, trying to reproduce the results. For this purpose they used algorithms based on neural networks, a technique that in recent years has revolutionized the field of recognitionς προσώπου καθώς χρησιμοποιεί υπάρχοντα δεδομένα για να εκπαιδευθεί και να βελτιώσει την απόδοσή της. Εκπαιδεύοντας αρχικά το σύστημά τους με photos of people, they then fed it the database of 218 tables they had presented to research participants, with the same requirement that they place an outline around each person.
The results give a very useful look at how computational vision algorithms work and are also revealing to human perception. Without being surprised, people are better off in the cubic estimation, accumulating twice as much in relative assessment as the computers. As the removal in the table increases, the results for the algorithm become more and more destructive, unlike people who do not seem to be so affected. This observation contradicts a widespread perception of neurologists that people perceive objects by analyzing their individual parts
Φαίνεται πάντως πως αν η υπολογιστική όραση μπορεί να ανταγωνιστεί την ανθρώπινη και ακόμη και να την ξεπεράσει σε φυσιολογικές συνθήκες, οι αφηρημένες συνθήκες που τους υποβάλλει η τέχνη δείχνει πως η ανθρώπινη αντίληψη είναι πολύ πιο ευέλικτη και αξιόπιστη. Τα αποτελέσματα πάντως της συγκεκριμένης έρευνας θα αξιοποιηθούν για τη βελτιστοποίηση της όρασης των υπολογιστών, οι οποίοι μία μέρα όχι πολύ μακριά από σήμερα, μπορεί να βρεθούν σε θέση να εκτιμήσουν καλύτερα ένα πίνακα modern art.
Source: naftemporiki.gr
