A team of machine learning develope has created a-|||-system for making caricatures of people`s faces.In a-|||-caricature, the artist creates a drawing of a face,with-|||-different parts of it greatly enlarged,or exaggerated. The-|||-pictures or images are usually made to make the person-|||-look funny.-|||-Such drawings can be difficult for machines to-|||-produce.This is because the human face is made up of-|||-complex shapes with a lot of extremely small-|||-details.Generally, good caricatures require skill artists-|||-who can effectively exaggerate faces, while still staying-|||-true to life.-|||-Kaidi Cao led the research.He says other machine-|||-systems for creating caricatures depend on a series of-|||-rules, which are based on how people would draw.But-|||-his team`s system uses machine learning to create the-|||-caricatures from thousand of examples made by-|||-experienced artists.-|||-In a paper explaining his research,Cao said other-|||-machine-based systems appear to pay more attention to-|||-appearance and style.But his team`s research uses a-|||-second machine learning tool to add "geometric-|||-exaggeration",The new method improves on existing-|||-ones"in terms of visual quality and preserving-|||-identity",In addition,the system gives users more-|||-ability to change results in both shape exaggeration and-|||-appearance.-|||-The team tested how recognizable its caricatures-|||-were to human test subjects.People were shown-|||-caricatures and then asked to choose the correct one-|||-from a group of images with faces that looked very-|||-similar.Test results showed that in many cases, people-|||-had difficulty choosing the correct image when the-|||-caricatures were created with the older methods.The-|||-researchers said this was because such systems often-|||-created caricatures that were far too exaggerated or-|||-unclear.Not surprising gly, the most easily recognized-|||-caricatures in the experiment were made by humans.But-|||-the researchers said their system performed better in-|||-tests with human subjects than the older methods.-|||-To date, the team has mostly worked on-|||-developing caricatures of people`s faces.But the-|||-researchers say they plan to expand on this in the future-|||-to include full bodies and other objects.They also plan-|||-to explore turning the current model around to permit-|||-caricature-to-photo translation.The team says it believes-|||-this might be useful for facial recognition of caricature-|||-独家原创试题-|||-caricature/`kxenktitar(r)/ n.人物漫画-|||-xx exaggerate /lg 'xxd30rcwv. 扩大;夸张identity-|||-/a(i)^1demtan n.. 身份-|||-1.What kind of caricatures does Kaidi Cao`s team-|||-mainly develop?-|||-A.Objects. B.Animals.-|||-C.People`s faces. D. (e)^1s shapes.-|||-2.Why is it hard for machines to draw a caricature of-|||-the face?-|||-A.There are fewer examples to learn.-|||-B.Skilled artists are unwilling to teach.-|||-C.The human face has complex shapes with small-|||-details.-|||-D.They pay too much attention to appearance.-|||-3.Which of the following caricatures is the easiest to be-|||-recognized?-|||-A.The caricatures made by humans.-|||-B.The caricatures made with a series of rules.-|||-C.The caricatures made by the new systems.-|||-D.The caricatures made by the older methods.-|||-4. (t)^6s the passage mainly about?-|||-A.A research on how people would draw.-|||-B.Ways to create caricatures of people`s faces.-|||-C.New machine systems to make caricature faces.-|||-D.A team of machine learning developers`new plans.