{"id":105450,"date":"2022-11-03T09:36:47","date_gmt":"2022-11-03T07:36:47","guid":{"rendered":"https:\/\/prohoster.info\/blog\/novosti-interneta\/ispolzovanie-mashinnogo-obucheniya-dlya-opredeleniya-emoczij-i-kontrolya-nad-svoej-mimikoj"},"modified":"2022-11-03T09:36:47","modified_gmt":"2022-11-03T07:36:47","slug":"ispolzovanie-mashinnogo-obucheniya-dlya-opredeleniya-emoczij-i-kontrolya-nad-svoej-mimikoj","status":"publish","type":"post","link":"https:\/\/prohoster.info\/en\/blog\/news\/ispolzovanie-mashinnogo-obucheniya-dlya-opredeleniya-emoczij-i-kontrolya-nad-svoej-mimikoj","title":{"rendered":"Using machine learning to detect emotions and control facial expressions","gt_translate_keys":[{"key":"rendered","format":"text"}]},"content":{"rendered":"
Andrey Savchenko from the Nizhny Novgorod branch of the Higher School of Economics published the results of his research in the field of machine learning related to emotion recognition in the faces of people present in photographs and videos. The code is written in Python using PyTorch and is distributed under the Apache 2.0 license. Several pre-trained models are available, including those suitable for use on mobile devices. <\/p>\n
Based on the library, another developer created the program sevimon, which allows tracking changes in emotions using a camera and helps control facial muscle tension, for example, to alleviate strain, indirectly affecting mood and, with prolonged use, to prevent the appearance of facial wrinkles. The CenterFace library is used to determine the position of the face in the video. The sevimon code is written in Python and is distributed under the AGPLv3 license. When launched for the first time, it downloads models, after which the program requires no internet connection and operates entirely offline. Instructions for running on Linux\/UNIX and Windows are provided, along with a Docker image for Linux. <\/p>\n
Sevimon works as follows: first, a face is detected in the camera image, then the face is matched with each of the eight emotions (anger, contempt, disgust, fear, joy, neutrality, sadness, surprise), after which a similarity score is given for each emotion. The obtained values are logged in a text format for subsequent analysis by the sevistat program. For each emotion, upper and lower value limits can be set in the configuration file, and a reminder is issued when these limits are crossed. \n Source: opennet.ru<\/a> <\/p>","protected":false,"gt_translate_keys":[{"key":"rendered","format":"html"}]},"excerpt":{"rendered":"